What is health informatics?
The AI Glossary
In our classes, we often pause to explain the ideas behind AI and the language used to describe it. These posts grew out of those conversations. They’re for anyone who would like to understand AI better, with no technical background assumed.
Health informatics studies how information and information systems can improve health and health care. It combines computing with knowledge of clinical work, human behavior and organizations. The subject is not simply how to store more data; it is how the right information reaches the right person in a useful form.
Consider an abnormal test result. The value may be stored correctly, yet the patient may still receive no follow-up. Someone needs to know that the result exists, understand what it means, take responsibility and confirm that the next action occurred. That is an information-and-workflow problem as well as a clinical one.
The field includes clinical informatics, which focuses on care delivery; public health informatics, which supports activities such as surveillance and outbreak response; research informatics, which helps organize and use research information; and consumer health informatics, which considers patients’ and the public’s needs. These areas overlap rather than forming completely separate disciplines.
A recurring concern is interoperability: whether different systems can exchange information and use it meaningfully. Moving a laboratory value between computers is not enough if the receiving system misinterprets the units, the patient identity or the date. Shared technical formats help, but shared meanings and well-designed processes are also required.
AI fits within this work. A model may help extract a finding from a report, summarize a record or identify a pattern. Informatics asks how that output becomes part of a dependable process, who can correct it and what happens when it is missing or wrong.
In a referral pathway, the most important improvement may be a clear definition of completion and a named person responsible for unresolved cases. AI can help find relevant documents or draft a message, but it cannot compensate for an organization that has not decided who owns the handoff. Health informatics provides the practical connection between information, technology and the people who need to use them.
Sources: AMIA — Informatics: Research and Practice; ASTP/ONC — Health IT Playbook: Electronic Health Records
To learn more, take a look at the AI in Health Care Certificate of Specialization from the Advanced Learning Academy at Harvard T.H. Chan School of Public Health. You can take an individual course or work toward the full certificate.
AI is a fast-moving field. This explanation reflects our class discussions and related material at the time of writing. Terminology, capabilities and tools may change.
For suggested additions or corrections, please email me at tpanch@hsph.harvard.edu.
Dr. Trishan Panch
Program Director, AI in Health Care
Harvard T.H. Chan School of Public Health — Advanced Learning Academy
Lead with AI in Health Care
The AI Pragmatist is a monthly newsletter from ALA faculty, with new explainers & essays from the Advanced Learning Academy