Course Overview
This is an introductory course on Health Informatics, where we will cover existing health informatics tools within hospitals to capture and safeguard patient health data to build innovations (research and development) for better patient care. This course will provide an introductory level understanding of health informatics such as electronic medical records (EMR), electronic health records (EHR), medical vocabularies (SNOMED CT, LIONIC, ICD9 etc), the data model for interoperability, and most importantly how to integrate innovations (research and development) on top EHR systems. Additionally, students will learn how health informatics is an integral part of medicine and biology concerning terminologies, ontologies, vocabularies and interoperability and informatics is an essential component towards knowledge synthesis and novel insight generation towards better understanding human health and disease in clinical and non-clinical settings. Also, students will learn about various statistical machine learning methods used for health research, their pros and cons; along with a couple of advanced machine learning that can be applied to clinical decision support systems and clinical trials. The lectures are segmented into technology [T] and innovation [I] on top of the technology used in health informatics, along with a couple of introductory advanced topics [*].
Learning Outcomes
- Students will know about existing information technology for healthcare such as electronic health records (EHR), and electronic medical records (EMR); and how they work from the point of view of hospital administration, physicians/clinicians, nurses and patient care with the hospital ecosystem and beyond hospital ecosystem services such as mobile technologies.
- Based on the learning, hands-on programming session and resources discussed, students in groups (maximum of 3 students) need to build any components of a synthetic EHR system as a prototype using existing open source technologies available based on the group's strength, motivation and ambition.
- Appreciate the need for reliable evidence-generation methodology that can inform clinical decision-making.
- Understand the differences between different study designs and the methods of interpreting a study results and the statistical principles underlying such inference.
- Prospective versus Retrospective
- Experimental versus Observational
- Appreciate the pros and cons of observational studies as methods for generating medical evidence the challenges in inferring causality
- Appreciate how experimental results may be interpreted within a probabilistic framework, the limitations of the experimental method and safeguards needed for experimenting with human subjects.
- Understand commonly used observational designs, their strengths and limitations and key statistical considerations in their design.
- Appreciate and get an overview of common approaches for adjusting for exposure likelihood and confounding.
Prerequisites
Recommended but NOT mandatory
- Previous courses:
- BIO-34223/BIO-6423-1: Human
- Physiology CS-2384-1: Digitization and Privacy
- CS-2385-1: Natural Language Processing: Theory and Applications
- Computer programming experience:
- Any modern high-level programming languages such as Python, go etc
- Prior software development expertise
- Knowledge of databases
Grading Scheme
- Absolute grading
- Quizzes: 15%
- Assignments: 15%
- Mid-term: 20%
- Final: 20%
- Projects: 30%
