Electronic Medical Records
Immerse yourself in this two-day intensive boot camp of seminars and hands-on analytical sessions that will provide an overview of electronic health data opportunities, statistical challenges, and latest techniques in electronic medical records.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
The Electronic Medical Records Boot Camp is a two-day intensive boot camp of seminars and hands-on analytical sessions to provide an overview of electronic health data opportunities, statistical challenges, and latest techniques.
- Explore the power and potential of Electronic Medical Records, understanding their significance in health studies and personalized medicine.
- Discover open-access datasets worldwide, facilitating broader research opportunities and insights.
- Learn techniques for preparing, transforming, and integrating EMR/EHR data, overcoming challenges of heterogeneity and volume.
- Address confounding factors, biases, and missing data in EMR/EHR analysis. Gain proficiency in comparative effectiveness and predictive analytics methodologies.
To contact support for this course, please email [email protected].
Course Prerequisites
- Each participant must have an introductory background in statistics.
- Each participant must be familiar with R.
- Each participant must have a laptop/computer with latest versions of R and R-Studio downloaded and installed prior to the first day of the workshop. R and R-Studio are available for free download and installation on Mac, PC, and Linux devices.
- Each participant will be required to apply for access to MIMIC-III data, requiring completion of specific HIPAA training to receive credentials.
What You Will Learn
Over the last decade, Electronic Health Records (EHRs) and Electronic Medical Records (EMRs) systems have been increasingly implemented at US hospitals. Huge amounts of longitudinal and detailed patient information, including lab tests, medications, disease status, and treatment outcome, have been accumulated and are available electronically. Extensive effort has been dedicated to developing advanced clinical data processing and data management in order to integrate patient data into a computable collection of rich longitudinal patient profiles. EMR/EHRs provide unprecedented opportunities for cohort-wide investigations and knowledge discovery. They are important data resources for building predictive models for disease diagnosis and prognosis, thus enabling personalized medicine.
Despite the great potential, analyzing such large, scattered and heterogeneous observational patient data is still technically challenging. This two-day intensive workshop will go over opportunities and potentials of EMR/EHR for health and medical studies, statistical challenges and pitfalls for analyzing EMR/EHR, and the latest developments of multiple techniques to address those challenges, followed by hands-on computer lab sessions and case studies to put concepts into practice.
By the end of the electronic medical records training, participants will be familiar with the following topics:
- Power and potentials of EMR/EHR data.
- Open-access datasets across the world.
- Preparation, transformation and integration of EMR/EHR.
- Confounding, bias and missing data in EMR/EHR and statistical methods addressing these challenges.
- Statistical methods for comparative effectiveness.
- Statistical methods for predictive analysis.
Instructors
Dr. Wang is Professor of Biostatistics in the department of Biostatistics at Mailman School of Public Health. Her research focuses on methodological development in observational studies using electronic health records data and multi-omics data, especially methods for multiple domain fusion or multi-omics integration.
Dr. Gu is an Assistant Professor of Biostatistics. She has a broad interest in developing innovative statistical methods and easy-to-use computational tools to advance precision health by integrating real-world data and evidence collected from diverse populations and large datasets. Her research interests include robust and efficient data integration in precision health research, methods for use in biobank data, electronic health records, and disparity research.