https://mw.hh.se/caisr/api.php?action=feedcontributions&feedformat=atom&user=AwaashISLAB/CAISR - User contributions [en]2026-04-04T11:39:32ZUser contributionsMediaWiki 1.35.13https://mw.hh.se/caisr/index.php?title=Leveraging_LLMs_for_Clinical_Note_Annotation_and_Uncertainty_Estimation&diff=5345Leveraging LLMs for Clinical Note Annotation and Uncertainty Estimation2023-10-27T07:33:38Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will investigate the potential of LLMs to simplify clinical note annotation along with uncertainty estimation, contributing to improved healthcare data management.<br />
|Keywords=Machine Learning, Large Language Models, Uncertainty Estimation, Electronic Health Records<br />
|TimeFrame=2023-2024<br />
|References=Yang, Zhichao, et al. "Multi-label few-shot ICD coding as autoregressive generation with prompt." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37. No. 4. 2023.<br />
<br />
Liu, Leibo, et al. "Automated icd coding using extreme multi-label long text transformer-based models." Artificial Intelligence in Medicine (2023): 102662.<br />
<br />
Hu, Edward J., et al. "Lora: Low-rank adaptation of large language models." arXiv preprint arXiv:2106.09685 (2021).<br />
<br />
Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." Advances in neural information processing systems 31 (2018).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python)<br />
|Supervisor=Awais Ashfaq, Prayag Tiwari<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
This Master's thesis project aims to harness Large Language Models (LLMs) for automating clinical note annotation, with a specific focus on generating validated diagnostic and procedure codes (ICD and KVÅ) that hold clinical significance. Beginning with the MIMIC-III dataset and extending to real Swedish clinical data, the project will explore the following technical and scientific directions:<br />
<br />
1. Model Training: Investigate cutting-edge techniques for training LLMs, including fine-tuning strategies, domain adaptation, and transfer learning, to optimize their performance for clinical note annotation.<br />
<br />
2. Uncertainty Estimation Methods: Develop and implement uncertainty estimation methods such as evidential deep learning to provide confidence scores for the model's annotations.<br />
<br />
3. Real-World Clinical Utility: Evaluate the clinical utility of the generated diagnostic and procedure codes by collaborating with healthcare professionals and analyzing the impact of these codes on patient care, data management, and reimbursement processes.<br />
<br />
4. Multi-Language Adaptation: Explore methods for adapting the LLM models to the Swedish language, ensuring their effectiveness in a non-English clinical setting.<br />
<br />
5. Ethical Considerations: Address ethical and privacy concerns related to patient data, ensuring compliance with healthcare regulations and data protection laws.<br />
<br />
<br />
The core research question, "How can LLMs be effectively trained and deployed to produce clinically validated codes?" will guide these technical and scientific directions. Additionally, the student is encouraged to propose and explore their own research questions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Leveraging_LLMs_for_Clinical_Note_Annotation_and_Uncertainty_Estimation&diff=5344Leveraging LLMs for Clinical Note Annotation and Uncertainty Estimation2023-10-27T06:36:36Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will investigate the potential of LLMs to simplify clinical note annotation along with uncertainty estimation, contributing to improved healthcare data management.<br />
|Keywords=Machine Learning, Large Language Models, Uncertainty Estimation, Electronic Health Records<br />
|TimeFrame=2023-2024<br />
|References=Yang, Zhichao, et al. "Multi-label few-shot ICD coding as autoregressive generation with prompt." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37. No. 4. 2023.<br />
<br />
Liu, Leibo, et al. "Automated icd coding using extreme multi-label long text transformer-based models." Artificial Intelligence in Medicine (2023): 102662.<br />
<br />
Hu, Edward J., et al. "Lora: Low-rank adaptation of large language models." arXiv preprint arXiv:2106.09685 (2021).<br />
<br />
Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." Advances in neural information processing systems 31 (2018).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python)<br />
|Supervisor=Awais Ashfaq<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
This Master's thesis project aims to harness Large Language Models (LLMs) for automating clinical note annotation, with a specific focus on generating validated diagnostic and procedure codes (ICD and KVÅ) that hold clinical significance. Beginning with the MIMIC-III dataset and extending to real Swedish clinical data, the project will explore the following technical and scientific directions:<br />
<br />
1. Model Training: Investigate cutting-edge techniques for training LLMs, including fine-tuning strategies, domain adaptation, and transfer learning, to optimize their performance for clinical note annotation.<br />
<br />
2. Uncertainty Estimation Methods: Develop and implement uncertainty estimation methods such as evidential deep learning to provide confidence scores for the model's annotations.<br />
<br />
3. Real-World Clinical Utility: Evaluate the clinical utility of the generated diagnostic and procedure codes by collaborating with healthcare professionals and analyzing the impact of these codes on patient care, data management, and reimbursement processes.<br />
<br />
4. Multi-Language Adaptation: Explore methods for adapting the LLM models to the Swedish language, ensuring their effectiveness in a non-English clinical setting.<br />
<br />
5. Ethical Considerations: Address ethical and privacy concerns related to patient data, ensuring compliance with healthcare regulations and data protection laws.<br />
<br />
<br />
The core research question, "How can LLMs be effectively trained and deployed to produce clinically validated codes?" will guide these technical and scientific directions. Additionally, the student is encouraged to propose and explore their own research questions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Multivariate_Time_Series_Analysis_with_Irregularly_Sampled_Data&diff=5288Multivariate Time Series Analysis with Irregularly Sampled Data2023-10-09T08:47:30Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will devise methods for handling irregularly sampled multivariate time series data, addressing missing data and modeling temporal relationships for applications in healthcare<br />
|Keywords=Machine Learning, Multivariate Time Series, Explainable AI<br />
|TimeFrame=2023-2024<br />
|Prerequisites=Statistics, Neural Networks, Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq, Prayag Tiwari<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
The research will commence with a comprehensive review of existing methods, encompassing interpolation techniques and traditional time series models. The student will then explore advanced statistical and machine learning approaches, including dynamic Bayesian networks and deep learning architectures, tailored to irregularly sampled multivariate time series.<br />
<br />
The methodologies will be rigorously evaluated using synthetic and real-world datasets, emphasizing predictive accuracy and insights extraction. Potential research directions include:<br />
<br />
1. Developing a dedicated imputation method for irregularly sampled multivariate time series.<br />
2. Investigating the application of attention networks, or others for capturing temporal dependencies.<br />
3. Applying the proposed methodologies to real-life healthcare challenges like early detection of diseases.<br />
4. Investigating model interpretability for insights into underlying processes.<br />
<br />
Additionally, the student is encouraged to propose and explore their own research questions and directions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Multivariate_Time_Series_Analysis_with_Irregularly_Sampled_Data&diff=5276Multivariate Time Series Analysis with Irregularly Sampled Data2023-09-29T08:48:35Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will devise methods for handling irregularly sampled multivariate time series data, addressing missing data and modeling temporal relationships for applications in healthcare<br />
|Keywords=Machine Learning, Multivariate Time Series, Explainable AI<br />
|TimeFrame=2023-2024<br />
|Prerequisites=Statistics, Neural Networks, Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
The research will commence with a comprehensive review of existing methods, encompassing interpolation techniques and traditional time series models. The student will then explore advanced statistical and machine learning approaches, including dynamic Bayesian networks and deep learning architectures, tailored to irregularly sampled multivariate time series.<br />
<br />
The methodologies will be rigorously evaluated using synthetic and real-world datasets, emphasizing predictive accuracy and insights extraction. Potential research directions include:<br />
<br />
1. Developing a dedicated imputation method for irregularly sampled multivariate time series.<br />
2. Investigating the application of attention networks, or others for capturing temporal dependencies.<br />
3. Applying the proposed methodologies to real-life healthcare challenges like early detection of diseases.<br />
4. Investigating model interpretability for insights into underlying processes.<br />
<br />
Additionally, the student is encouraged to propose and explore their own research questions and directions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Leveraging_LLMs_for_Clinical_Note_Annotation_and_Uncertainty_Estimation&diff=5275Leveraging LLMs for Clinical Note Annotation and Uncertainty Estimation2023-09-29T08:45:16Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will investigate the potential of LLMs to simplify clinical note annotation along with uncertainty estimation, contributing to improved healthcare data management.<br />
|Keywords=Machine Learning, Large Language Models, Uncertainty Estimation, Electronic Health Records<br />
|TimeFrame=2023-2024<br />
|References=Liu, Leibo, et al. "Automated icd coding using extreme multi-label long text transformer-based models." Artificial Intelligence in Medicine (2023): 102662.<br />
<br />
Hu, Edward J., et al. "Lora: Low-rank adaptation of large language models." arXiv preprint arXiv:2106.09685 (2021).<br />
<br />
Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." Advances in neural information processing systems 31 (2018).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python)<br />
|Supervisor=Awais Ashfaq<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
This Master's thesis project aims to harness Large Language Models (LLMs) for automating clinical note annotation, with a specific focus on generating validated diagnostic and procedure codes (ICD and KVÅ) that hold clinical significance. Beginning with the MIMIC-III dataset and extending to real Swedish clinical data, the project will explore the following technical and scientific directions:<br />
<br />
1. Model Training: Investigate cutting-edge techniques for training LLMs, including fine-tuning strategies, domain adaptation, and transfer learning, to optimize their performance for clinical note annotation.<br />
<br />
2. Uncertainty Estimation Methods: Develop and implement uncertainty estimation methods such as evidential deep learning to provide confidence scores for the model's annotations.<br />
<br />
3. Real-World Clinical Utility: Evaluate the clinical utility of the generated diagnostic and procedure codes by collaborating with healthcare professionals and analyzing the impact of these codes on patient care, data management, and reimbursement processes.<br />
<br />
4. Multi-Language Adaptation: Explore methods for adapting the LLM models to the Swedish language, ensuring their effectiveness in a non-English clinical setting.<br />
<br />
5. Ethical Considerations: Address ethical and privacy concerns related to patient data, ensuring compliance with healthcare regulations and data protection laws.<br />
<br />
<br />
The core research question, "How can LLMs be effectively trained and deployed to produce clinically validated codes?" will guide these technical and scientific directions. Additionally, the student is encouraged to propose and explore their own research questions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Multivariate_Time_Series_Analysis_with_Irregularly_Sampled_Data&diff=5274Multivariate Time Series Analysis with Irregularly Sampled Data2023-09-29T08:44:26Z<p>Awaash: Created page with "{{StudentProjectTemplate |Summary=This thesis seeks to advance the field of multivariate time series analysis, specifically targeting datasets with irregular sampling interval..."</p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=This thesis seeks to advance the field of multivariate time series analysis, specifically targeting datasets with irregular sampling intervals.<br />
|Keywords=Machine Learning, Multivariate Time Series, Explainable AI<br />
|TimeFrame=2023-2024<br />
|Prerequisites=Statistics, Neural Networks, Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq, <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
The research will commence with a comprehensive review of existing methods, encompassing interpolation techniques and traditional time series models. The student will then explore advanced statistical and machine learning approaches, including dynamic Bayesian networks and deep learning architectures, tailored to irregularly sampled multivariate time series.<br />
<br />
The methodologies will be rigorously evaluated using synthetic and real-world datasets, emphasizing predictive accuracy and insights extraction. Potential research directions include:<br />
<br />
1. Developing a dedicated imputation method for irregularly sampled multivariate time series.<br />
2. Investigating the application of attention networks, or others for capturing temporal dependencies.<br />
3. Applying the proposed methodologies to real-life healthcare challenges like early detection of diseases.<br />
4. Investigating model interpretability for insights into underlying processes.<br />
<br />
Additionally, the student is encouraged to propose and explore their own research questions and directions.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Uncertainty_quantification_for_data_driven_clinical_decision_making&diff=5272Uncertainty quantification for data driven clinical decision making2023-09-29T08:36:57Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will build upon the field of evidential deep learning to identify and understand when the model says 'I don't know'<br />
|Keywords=Evidential deep learning, uncertainty quantification, electronic health records<br />
|TimeFrame=2023-2024<br />
|References=Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." arXiv preprint arXiv:1806.01768 (2018).<br />
<br />
Amini, Alexander, et al. "Deep evidential regression." arXiv preprint arXiv:1910.02600 (2019).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq, Slawomir Nowaczyk<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Neural networks are increasingly being used in many safety critical decision processes, thereby necessitating reliable uncertainty estimates along with predictions. Healthcare is no different and reliable and accurate predictions carry great importance, since they may contribute to an incorrect clinical decision risking a human life in addition to severe ethical and financial costs.<br />
<br />
Data for the project comes from MIMIC-III (an open source EHR database)<br />
<br />
The student will go through the state-of-the-art in Bayesian and Evidential Learning to quantify prediction uncertainties. Focus will be on identifying and understanding when the model says "I don't know". <br />
<br />
For questions contact Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Leveraging_LLMs_for_Clinical_Note_Annotation_and_Uncertainty_Estimation&diff=5271Leveraging LLMs for Clinical Note Annotation and Uncertainty Estimation2023-09-29T08:18:58Z<p>Awaash: Created page with "{{StudentProjectTemplate |Summary=The student will investigate the potential of LLMs to simplify clinical note annotation along with uncertainty estimation, contributing to im..."</p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will investigate the potential of LLMs to simplify clinical note annotation along with uncertainty estimation, contributing to improved healthcare data management.<br />
|Keywords=Machine Learning, Large Language Models, Uncertainty Estimation, Electronic Health Records<br />
|TimeFrame=2023-2024<br />
|References=Liu, Leibo, et al. "Automated icd coding using extreme multi-label long text transformer-based models." Artificial Intelligence in Medicine (2023): 102662.<br />
<br />
Hu, Edward J., et al. "Lora: Low-rank adaptation of large language models." arXiv preprint arXiv:2106.09685 (2021).<br />
<br />
Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." Advances in neural information processing systems 31 (2018).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python)<br />
|Supervisor=Awais Ashfaq <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
This Master's thesis project aims to harness Large Language Models (LLMs) for automating clinical note annotation, with a specific focus on generating validated diagnostic and procedure codes (ICD and KVÅ) that hold clinical significance. Beginning with the MIMIC-III dataset and extending to real Swedish clinical data, the project will explore the following technical and scientific directions:<br />
<br />
1. Model Training: Investigate cutting-edge techniques for training LLMs, including fine-tuning strategies, domain adaptation, and transfer learning, to optimize their performance for clinical note annotation.<br />
<br />
2. Uncertainty Estimation Methods: Develop and implement uncertainty estimation methods such as evidential deep learning to provide confidence scores for the model's annotations.<br />
<br />
3. Real-World Clinical Utility: Evaluate the clinical utility of the generated diagnostic and procedure codes by collaborating with healthcare professionals and analyzing the impact of these codes on patient care, data management, and reimbursement processes.<br />
<br />
4. Multi-Language Adaptation: Explore methods for adapting the LLM models to the Swedish language, ensuring their effectiveness in a non-English clinical setting.<br />
<br />
5. Ethical Considerations: Address ethical and privacy concerns related to patient data, ensuring compliance with healthcare regulations and data protection laws.<br />
<br />
<br />
The core research question, "How can LLMs be effectively trained and deployed to produce clinically validated codes?" will guide these technical and scientific directions. Additionally, the student is encouraged to propose and explore their own research questions within this framework, promoting innovation and adaptability throughout the project.</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Uncertainty_quantification_for_data_driven_clinical_decision_making&diff=4975Uncertainty quantification for data driven clinical decision making2021-10-13T11:32:21Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will build upon the field of evidential deep learning to identify and understand when the model says 'I don't know'<br />
|Keywords=Evidential deep learning, uncertainty quantification, electronic health records<br />
|TimeFrame=Flexible<br />
|References=Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." arXiv preprint arXiv:1806.01768 (2018).<br />
<br />
Amini, Alexander, et al. "Deep evidential regression." arXiv preprint arXiv:1910.02600 (2019).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq, <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Neural networks are increasingly being used in many safety critical decision processes, thereby necessitating reliable uncertainty estimates along with predictions. Healthcare is no different and reliable and accurate predictions carry great importance, since they may contribute to an incorrect clinical decision risking a human life in addition to severe ethical and financial costs.<br />
<br />
Data for the project comes from MIMIC-III (an open source EHR database)<br />
<br />
The student will go through the state-of-the-art in Bayesian and Evidential Learning to quantify prediction uncertainties. Focus will be on identifying and understanding when the model says "I don't know". <br />
<br />
For questions contact Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Uncertainty_quantification_for_data_driven_clinical_decision_making&diff=4974Uncertainty quantification for data driven clinical decision making2021-10-13T11:31:59Z<p>Awaash: Created page with "{{StudentProjectTemplate |Summary=The student will build upon the field of evidential deep learning to identify and understand when the model says 'I don't know' |Keywords=Evi..."</p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=The student will build upon the field of evidential deep learning to identify and understand when the model says 'I don't know'<br />
|Keywords=Evidential deep learning, uncertainty quantification, electronic health records<br />
|TimeFrame=Flexible<br />
|References=Sensoy, Murat, Lance Kaplan, and Melih Kandemir. "Evidential deep learning to quantify classification uncertainty." arXiv preprint arXiv:1806.01768 (2018).<br />
<br />
Amini, Alexander, et al. "Deep evidential regression." arXiv preprint arXiv:1910.02600 (2019).<br />
|Prerequisites=Statistics; Neural Networks; Programming (Python or Matlab)<br />
|Supervisor=Awais Ashfaq, <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Neural networks are increasingly being used in many safety critical decision processes, thereby necessitating reliable uncertainty estimates along with predictions. Healthcare is no different and reliable and accurate predictions carry great importance, since they may contribute to an incorrect clinical decision risking a human life in addition to severe ethical and financial costs.<br />
<br />
Data for the project comes from MIMIC-III (an open source EHR database)<br />
<br />
The student will go through the state-of-the-art in Bayesian and Evidential Learning to quantify prediction uncertainties. Focus will be on identifying and understanding when the model says "I don't know". <br />
<br />
For questions: contact Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4523Awais Ashfaq2020-02-09T14:51:33Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
My blog [https://awaisashfaq.com/ awaisashfaq.com]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4522Awais Ashfaq2020-02-09T14:51:06Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
My blog [https://awaisashfaq.com/]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4521Awais Ashfaq2020-02-09T14:50:49Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
Bolg [https://awaisashfaq.com/]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4520Awais Ashfaq2020-02-09T14:50:37Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
Bolg [https://awaisashfaq.com/]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4519Awais Ashfaq2020-02-09T14:50:24Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
http://islab.hh.se/mediawiki/Awais_Ashfaq<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
Bolg [https://awaisashfaq.com/]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4274Awais Ashfaq2019-09-16T14:56:24Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisor'''<br />
[[Slawomir Nowaczyk]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=4076Awais Ashfaq2018-10-21T00:30:49Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisors'''<br />
[[Slawomir Nowaczyk]] and [[Anita Sant'Anna]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4010Biases in electronic health records2018-10-11T04:53:18Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records (EHRs) is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHRs than normal patients. Thus prediction models are likely to be biased towards the sicker population. In the realm of machine learning, this is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models built using EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change (if any) in model performance and discuss it in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Would you require more information about the project, feel free to contact Awais Ashfaq (awais.ashfaq@hh.se).</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4007Biases in electronic health records2018-10-10T14:27:57Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records (EHRs) is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. In the realm of machine learning, this is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change (if any) in model performance and discuss it in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Would you require more information about the project, feel free to contact Awais Ashfaq (awais.ashfaq@hh.se).</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4006Biases in electronic health records2018-10-10T14:24:38Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records (EHRs) is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. In the realm of machine learning, this is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss it in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Would you require more information about the project, feel free to contact Awais Ashfaq (awais.ashfaq@hh.se).</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4005Biases in electronic health records2018-10-10T14:24:25Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records (EHR) is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. In the realm of machine learning, this is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss it in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Would you require more information about the project, feel free to contact Awais Ashfaq (awais.ashfaq@hh.se).</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4004Biases in electronic health records2018-10-10T14:19:26Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. In the realm of machine learning, this is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss it in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Would you require more information about the project, feel free to contact Awais Ashfaq (awais.ashfaq@hh.se).</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4003Biases in electronic health records2018-10-10T14:15:47Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk,<br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. This is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4002Biases in electronic health records2018-10-10T14:15:04Z<p>Awaash: </p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk, <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. This is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Biases_in_electronic_health_records&diff=4001Biases in electronic health records2018-10-10T14:13:52Z<p>Awaash: Created page with "{{StudentProjectTemplate |Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data |Keywords=Machine Learning, Ele..."</p>
<hr />
<div>{{StudentProjectTemplate<br />
|Summary=To evaluate the impact of sample bias on the predictive value of machine learning models built using EHR data<br />
|Keywords=Machine Learning, Electronic health records, Sample bias<br />
|TimeFrame=Spring 2019<br />
|References=1. Verheij, Robert A., et al. "Possible Sources of Bias in Primary Care Electronic Health Record Data Use and Reuse." Journal of medical Internet research 20.5 (2018).<br />
2. Gianfrancesco, Milena A., et al. "Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data." JAMA internal medicine (2018).<br />
3. Johnson, Alistair EW, et al. "MIMIC-III, a freely accessible critical care database." Scientific data 3 (2016): 160035.<br />
|Prerequisites=Good knowledge of applied mathematics. An ability to implement state-of-the-art algorithms in a suitable programming environment. An interest in machine learning algorithms and medical data analysis.<br />
|Supervisor=Awais Ashfaq, Sławomir Nowaczyk, <br />
|Level=Master<br />
|Status=Open<br />
}}<br />
Predictive modeling with electronic health records is considered an essential step towards precision medicine and improving care quality. However, there is a potential risk of building biased and incorrect prediction models if the complexities and limitations of EHR data are not completely studied. For instance, data collection in EHRs depends on individual patient needs and health state. Sicker patients tend to have more data in EHR than normal patients. Thus prediction models built on EHR data are likely to be biased towards the sicker population. This is referred to as 'sample bias' because the distribution of the available data does not reflect the true environment. <br />
The goal of the project is to evaluate the impact of sample bias on different prediction models trained on EHR data. You will use the MIMIC-III database (see references) for this project.<br />
<br />
Tentative project plan:<br />
<br />
1- Scan through sources of potential bias in EHRs. (See references for a start)<br />
<br />
2- Build simple predictive models (Logistic regression, Neural nets, random forests etc.) to predict an outcome of interest (like in-hospital death) using the MIMIC-III database.<br />
<br />
3- Sub-sample the training and testing set based on your knowledge (from step 1) and re-run the developed models. For instance, you may sub-sample the data based on age, gender, the frequency of visits, time, place of visit etc.<br />
<br />
4- Evaluate the change in model performance and discuss in detail.<br />
<br />
5- Suggest possible solutions to overcome the impact of sample bias when building EHR driven prediction models. <br />
<br />
Deliverables:<br />
<br />
1- A succinct review of different biases in electronic health records and their impact on predictive models.<br />
<br />
2- A summary of recent (2017-2018) studies designed for predicting in-hospital deaths using EHR data.<br />
<br />
3- Results: Prediction performance of developed models using complete EHR data and its sub-samples.<br />
<br />
4- A critical analysis of the bias problem in light of your results.<br />
<br />
Contact: Awais Ashfaq (awais.ashfaq@hh.se)</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3852Awais Ashfaq2018-01-17T15:51:54Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisors'''<br />
[[Slawomir Nowaczyk]] and [[Anita Sant'Anna]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3851Awais Ashfaq2018-01-17T15:50:29Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisors'''<br />
[[Slawomir Nowaczyk]] and [[Anita Sant'Anna]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
{{PublicationsList}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3692Awais Ashfaq2017-10-24T11:27:21Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
[[Category:Staff]]<br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<br />
'''Supervisors'''<br />
[[Slawomir Nowaczyk]] and [[Anita Sant'Anna]]<br />
<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
Read my [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html project interview]<br />
<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3689HIPATCH2017-10-23T07:00:49Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halland Intelligent PATient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Health spending as a share of GDP in Sweden (11.0%) remains well above the OECD average (8.9%). In addition to ageing and advanced treatment procedures, a fundamental source of escalating costs is the unawareness of how and to what extent different sub-groups within healthcare utilize resources and contribute to quality. Hence, it gets challenging to unveil critical areas within healthcare that are truly responsible for high costs and low quality. <br />
<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
<br />
Read views from people involved in the project here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
Text by: Awais Ashfaq<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3688HIPATCH2017-10-23T03:54:11Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Hallland Intelligent PATient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Health spending as a share of GDP in Sweden (11.0%) remains well above the OECD average (8.9%). In addition to ageing and advanced treatment procedures, a fundamental source of escalating costs is the unawareness of how and to what extent different sub-groups within healthcare utilize resources and contribute to quality. Hence, it gets challenging to unveil critical areas within healthcare that are truly responsible for high costs and low quality. <br />
<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
<br />
Read views from people involved in the project here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
Text by: Awais Ashfaq<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3687HIPATCH2017-10-23T03:52:54Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Hallland Intelligent PAtienT-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Health spending as a share of GDP in Sweden (11.0%) remains well above the OECD average (8.9%). In addition to ageing and advanced treatment procedures, a fundamental source of escalating costs is the unawareness of how and to what extent different sub-groups within healthcare utilize resources and contribute to quality. Hence, it gets challenging to unveil critical areas within healthcare that are truly responsible for high costs and low quality. <br />
<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
<br />
Read views from people involved in the project here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
Text by: Awais Ashfaq<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3686Awais Ashfaq2017-10-22T19:50:38Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
Read my project interview here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3685HIPATCH2017-10-22T19:49:05Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Health spending as a share of GDP in Sweden (11.0%) remains well above the OECD average (8.9%). In addition to ageing and advanced treatment procedures, a fundamental source of escalating costs is the unawareness of how and to what extent different sub-groups within healthcare utilize resources and contribute to quality. Hence, it gets challenging to unveil critical areas within healthcare that are truly responsible for high costs and low quality. <br />
<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
<br />
Read views from people involved in the project here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
Text by: Awais Ashfaq<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3684Awais Ashfaq2017-10-22T19:42:33Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
Find my project interview here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3683HIPATCH2017-10-22T19:41:17Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
<br />
Read views from people involved in the project here [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3682HIPATCH2017-10-22T19:38:56Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
Managed by Affecto and owned by Region Halland, we use the Strategic Healthcare Analysis and Research Platform (SHARP) which is a unique integration of data sources from all levels of the care chain including measurements from primary care, ambulance, emergency care, inpatient care as well as the traditional EHR’s. This enables us to have a system’s approach to healthcare delivery which has shown to be an effective methodology to promote better health at a lower cost. <br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3681Awais Ashfaq2017-10-22T19:36:02Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
See my project description [https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html]<br />
<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3680Awais Ashfaq2017-10-22T19:34:10Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|url=https://www.hh.se/english/universitynews/news/reshapinghealthcarethroughartificialintelligence.65446507.html<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3679HIPATCH2017-10-22T19:31:21Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3678HIPATCH2017-10-22T19:29:58Z<p>Awaash: </p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|Description= Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/03<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
{{AssignProjPartner<br />
|projectpartner=Region Halland<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=File:AI.jpg&diff=3677File:AI.jpg2017-10-22T19:15:50Z<p>Awaash: </p>
<hr />
<div></div>Awaashhttps://mw.hh.se/caisr/index.php?title=HIPATCH&diff=3676HIPATCH2017-10-22T19:11:32Z<p>Awaash: Created page with "{{ResearchProjInfo |Title=HIPATCH |ContactInformation=Antanas Verikas |ShortDescription=Halmstad Intelligent Patient-Centered Healthcare |Description= |LogotypeFile=AI.jpg |P..."</p>
<hr />
<div>{{ResearchProjInfo<br />
|Title=HIPATCH<br />
|ContactInformation=Antanas Verikas<br />
|ShortDescription=Halmstad Intelligent Patient-Centered Healthcare<br />
|Description= <br />
|LogotypeFile=AI.jpg<br />
|ProjectResponsible=Antanas Verikas<br />
|ProjectStart=2016/10/01<br />
|ProjectEnd=2020/09/30<br />
|ApplicationArea=Healthcare Technology<br />
|Lctitle=No<br />
}}<br />
__NOTOC__<br />
{{ShowResearchProject}}<br />
Advancement in computing technologies and machine learning algorithms has enabled us to analyze big amounts of data to enhance the efficiency and productivity of businesses in every industry. Healthcare is no different. The recent decade has witnessed huge advances in the amount of medical data generated and stored in almost every domain in the healthcare sector. The primary purpose of Electronic Health Records (EHR) is to facilitate and improve individual patient care. In addition to it, EHRs today, also serve as a data center for clinical research to improve healthcare management, patient safety and clinical decision support.<br />
<br />
<br />
{{ShowProjectPublications}}</div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3675Awais Ashfaq2017-10-22T18:54:59Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=User:Awaash&diff=3674User:Awaash2017-10-22T18:50:27Z<p>Awaash: Blanked the page</p>
<hr />
<div></div>Awaashhttps://mw.hh.se/caisr/index.php?title=Awais_Ashfaq&diff=3673Awais Ashfaq2017-10-22T18:48:22Z<p>Awaash: Created page with "{{Person |Family Name=Ashfaq |Given Name=Awais |Title=M. Sc. |Phone=+46 729 773 770 |Position=PhD Student |Email=mailto:awais.ashfaq@hh.se |Image=awais.jpg |Office=E505 |Affil..."</p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=M. Sc.<br />
|Phone=+46 729 773 770<br />
|Position=PhD Student<br />
|Email=mailto:awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|Affiliation=ISLAB, CAISR<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
{{AssignSubjectAreas<br />
|SubjectArea=Machine Learning<br />
}}<br />
{{AssignApplicationAreas<br />
|ApplicationArea=Healthcare<br />
}}<br />
'''Primary research interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General research interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=User:Awaash&diff=3672User:Awaash2017-10-22T18:41:46Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=MSc<br />
|Phone=+46 729 773 770<br />
|Position=PhD student<br />
|Email=awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|Subject=Biomedical engineering<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
'''Primary Research Interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General Research Interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=User:Awaash&diff=3671User:Awaash2017-10-22T18:40:58Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=MSc<br />
|Phone=+46 729 773 770<br />
|Position=PhD student<br />
|Email=awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|Subject=Biomedical engineering<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
<br />
'''Primary Research Interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General Research Interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=File:Awais.jpg&diff=3670File:Awais.jpg2017-10-22T18:38:21Z<p>Awaash: </p>
<hr />
<div></div>Awaashhttps://mw.hh.se/caisr/index.php?title=User:Awaash&diff=3669User:Awaash2017-10-22T18:37:30Z<p>Awaash: </p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=Masters<br />
|Phone=+46 729 773 770<br />
|Position=PhD student<br />
|Email=awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|Subject=Biomedical engineering<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
<br />
'''Primary Research Interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General Research Interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
[[Category:Staff]]<br />
<!--Remove or add comments --><br />
<!-- __NOTOC__ --><br />
{{ShowPerson}}<br />
{{InsertProjects}}<br />
<!-- {{PublicationsList}} --></div>Awaashhttps://mw.hh.se/caisr/index.php?title=User:Awaash&diff=3668User:Awaash2017-10-22T18:34:10Z<p>Awaash: Created page with "{{Person |Family Name=Ashfaq |Given Name=Awais |Title=Masters |Phone=+46 729 773 770 |Position=PhD studenr |Email=awais.ashfaq@hh.se |Image=awais.jpg |Office=E505 |Subject=Bio..."</p>
<hr />
<div>{{Person<br />
|Family Name=Ashfaq<br />
|Given Name=Awais<br />
|Title=Masters<br />
|Phone=+46 729 773 770<br />
|Position=PhD studenr<br />
|Email=awais.ashfaq@hh.se<br />
|Image=awais.jpg<br />
|Office=E505<br />
|Subject=Biomedical engineering<br />
}}<br />
{{AssignProjects<br />
|project=HIPATCH<br />
}}<br />
<br />
'''Primary Research Interest'''<br />
* Predictive modeling using Electronic Health Records<br />
** Intelligible deep learning for robust patient representation<br />
** Patient outcome prediction and risk estimation<br />
<br />
'''General Research Interests'''<br />
* Health economic analysis, policy research, patient privacy and data security <br />
<br />
{{PublicationsList}}<br />
<br />
[[Category:staff]]</div>Awaash