The Master of Health Science in Medical Artificial Intelligence is a hybrid graduate degree offered by the Yale School of Medicine, designed for professionals seeking to lead the development and implementation of artificial intelligence tools in healthcare. The program provides rigorous, multidisciplinary training in machine learning, data science, software engineering, regulatory affairs, and clinical applications, grounded in real-world medical environments.
Building on Yale’s Certificate Program in Medical Software and Medical AI, the degree prepares graduates to bridge the gap between emerging AI technologies and the complexities of patient care and healthcare delivery. Learners complete core and elective coursework, culminating in an independent project or oral examination, and participate in in-person bootcamp sessions in New Haven at the start of each semester.
Copy Link
Copy Link
Prerequisites:
An undergraduate degree in a technical field such as computer science, data science, engineering, statistics, or medicine, along with relevant professional experience. Physicians with appropriate technical training are encouraged to apply. Applicants must reside in the United States, Canada, or Mexico.
Copy Link
For computer scientists, data scientists and engineers with strong Python skills — building the next generation of ML models and regulated software products. Graduates go on to careers across medtech, pharma and health care.
Graduates of this track find employment in roles such as product designers, software engineers, machine learning scientists and data analysts in the medical device sector, the pharmaceutical sector, the consumer technology sector (e.g., consumer wearables) and the healthcare sector. The program will also equip them to transition to research careers in this area.
Competencies
Built for clinicians, regulatory professionals and health care managers — leading the governance and implementation of medical AI health care systems. Graduates pursue roles as Chief Medical AI Officers, AI regulatory specialists and Medical Informatics Officers.
Graduates of this track find employment in roles such as chief medical AI or medical officers, or AI regulatory specialists in the medical device sector, the pharmaceutical sector, the consumer technology sector (e.g., consumer wearables) and the healthcare sector. Graduates with a medical background may also find employment as (or promotion to) Medical Informatics Officers in Major Healthcare Systems or Lead AI physicians for clinical units.
Competencies
Copy Link
The program is offered in a hybrid format and consists of three major components:
Program Schedule
| Year | Period | Course Content |
|---|---|---|
| 1 | August | In-Person Week 1 — Program Introduction (1 credit hour) |
| 1 | Fall | 2 core courses (6 credit hours) |
| 1 | January | In-Person Week 2 — Project Advisor Selection (1 credit hour) |
| 1 | Spring | 2 core courses + project planning (6 credit hours) |
| 1 | Summer | 1 project work practicum (4 credit hours) |
| 2 | Fall | 2 elective courses* (6 credit hours) |
| 2 | Spring | 2 elective courses* (6 credit hours) |
*A student may substitute up to two elective courses in Year 2 with additional project work practicums.
Copy Link
The initial curriculum will consist of four core courses and six elective courses. Students will be allowed to substitute a core course with an additional elective course, if they demonstrate knowledge of the material in the core course. All substitutions will have to be approved by the director.
| Course No. | Course Name | Track | Description |
|---|---|---|---|
| TBD | Mathematical Foundations of AI | Both Tracks | An overview of probability, statistics, optimization, classical machine learning (classification, regression, clustering, feature selection), model evaluation, and calibration. |
| TBD | Medical AI Context | Both Tracks | An introduction to healthcare from a systems perspective, with an emphasis on units/procedures where data is generated, including electronic health record systems, medical imaging, and clinical and regulatory requirements for medical AI applications. |
| TBD | Computational Foundations of AI | Both Tracks | Standards used to store and transfer medical data (e.g., HL7, DICOM, database schemas) and core background to the programming environments, tools, and libraries used to analyze such data. |
| TBD | Medical AI Lab | Both Tracks | 14 interactive assignments that will familiarize students with the use of software tools and libraries to visualize, curate, and analyze medical data, including the creation and evaluation of medical AI algorithms. |
| Course No. | Course Name | Track | Description |
|---|---|---|---|
| TBD | Analyzing Medical Data I: Text + Clinical Data | Technical Track | Techniques for the analysis of clinical data typically stored in the electronic health record system, including data formats, natural language processing, and the creation of AI models for these types of data. |
| TBD | Analyzing Medical Data II: Imaging, Sensor and Omics Data | Technical Track | Data sources typically stored outside the electronic health record system, including medical imaging data, sensor/wearable data, and genetics and multi-omics datasets. |
| TBD | Deep Neural Networks, Transformers, and Generative Models | Technical Track | Deep neural network architectures, transformers and their use in generative models, including large language models, imaging models, multimodal models, and custom language models. |
| TBD | AI Software Engineering in a Regulated Context | Both Tracks | FDA regulations that govern medical software and medical AI, core international standards, the overall regulatory process, AI software engineering lifecycle, and risk management techniques. |
| TBD | Security and Privacy | Both Tracks | Cybersecurity challenges in healthcare and medical AI, including data poisoning, prompt injection attacks, and adversarial attacks. Privacy regulations (HIPAA, GDPR) and de-identification techniques for medical data. |
| TBD | Clinical Decision Support and Digital Health Systems | Both Tracks | Creation, implementation, evaluation, monitoring, and governance of clinical decision support systems, as well as emerging digital health solutions, challenges, and opportunities. |
| TBD | Healthcare Systems, Quality and Operational Efficiency | Both Tracks | How complex healthcare systems operate, including the business side of the process (e.g., reimbursement, insurance), and the development and use of AI tools for quality improvement and operational efficiency. |
Copy Link
Required: undergraduate transcript, personal statement, and three letters of recommendation.
Limited financial aid available, including support for in-person summer project work in New Haven.
Copy Link
For questions, contact us at mhs-medicalai@yale.edu.
Copy Link
Director
Professor of Biomedical Informatics & Data Science, and Radiology & Biomedical Imaging; Associate Director of Biomedical Imaging Data Sciences, Yale Biomedical Imaging Institute; Director of Medical Software and Medical Artificial Intelligence Certificate Program, Department of Biomedical Informatics & Data Science, Yale Biomedical Imaging Institute
Co-Director
Professor of Pediatrics (Emergency Medicine) and of Emergency Medicine; Chief Health Information Officer, YNHHS; Chief Health Information Officer, Yale School of Medicine & Yale New Haven Health, Yale School of Medicine; Vice Chair of Clinical Systems, Biomedical Informatics & Data Science