Pooyan Kazemian

Pooyan Kazemian’s research lies at the intersection of artificial intelligence (AI), machine learning, and data-driven optimization, focusing primarily on healthcare management applications. His work addresses pressing problems in the areas of healthcare operations, medical decision making, and health policy, aiming to improve quality of care, access to care, and health outcomes while reducing costs. Kazemian is particularly interested in novel applications of deep learning and AI to enhance the operational aspects of healthcare delivery and support complex medical and policy decisions. He also employs machine learning and robust optimization techniques to develop personalized disease monitoring and treatment strategies and to inform evidence-based public health policy.

Another area of Kazemian’s research involves developing novel methods for trustless and verifiable AI by leveraging advanced cryptographic techniques, such as zero-knowledge proofs. These methods aim to improve the security, trustworthiness, and reliability of medical AI tools, especially those deployed as Software as a Medical Device (SaMD).

Kazemian’s research has been published in leading journals such as Management Science, Production and Operations Management, JAMA Internal Medicine, and Annals of Internal Medicine. His work has been featured in major media outlets, including NPR, The New York Times, Science Codex, Yahoo Finance, and Business Standard.

Prior to joining UC San Diego in 2025, Kazemian was on the faculty at Case Western Reserve University (2020–2025) and Harvard Medical School (2017–2020). He received his Ph.D. in Industrial and Operations Engineering from the University of Michigan in 2016.

Selected Publications:

Contextual Learning with Online Convex Optimization: Theory and Application to Medical Decision-Making (with Keyvanshokooh E, Zhalechian M, Shi C, Van Oyen MP). Management Science. Published online on May 02, 2025.

Dynamic Monitoring and Control of Irreversible Chronic Diseases with Application to Glaucoma (with Helm JE, Lavieri MS, Stein JD, Van Oyen MP). Production and Operations Management. 2019 May;28(5):1082-1107.

Interpretable Hierarchical Deep Learning Model for Noninvasive Alzheimer’s Disease Diagnosis (with Zokaeinikoo M, Mitra P). INFORMS Journal on Data Science. 2023 Oct;2(2):183-96.

Coordinated and Priority-Based Surgical Care: An Integrated Distributionally Robust Stochastic Optimization Approach (with Keyvanshokooh E, Fattahi M, Van Oyen MP). Production and Operations Management. 2022 April;31(4):1510-1535.

Mitigating the COVID-19 Pandemic Through Data-Driven Resource Sharing (with Keyvanshokooh E, Fattahi M, Freedberg K). Naval Research Logistics. 2024 Feb;71(1):41-63.

Evaluation of the Cascade of Diabetes Care in the United States, 2005-2016 (with Shebl FM, McCann N, Walensky RP, Wexler DJ). JAMA Internal Medicine. 2019;179(10):1376-1385.

College Campuses and COVID-19 Mitigation: Clinical and Economic Value (with Losina E, Leifer V, Millham L, Panella C, Hyle EP, Mohareb AM, Neilan AM, Ciaranello AL, Freedberg KA). Annals of Internal Medicine. 2021 Apr;174(4):472-83.

Cost-effectiveness of Public Health Strategies for COVID-19 Epidemic Control in South Africa: A Microsimulation Modelling Study (with Reddy KP, Shebl FM, Foote JH, Harling G, Scott JA, Panella C, Fitzmaurice KP, Flanagan C, Hyle EP, Neilan AM, Mohareb AM, Bekker LG, Lessells RJ, Ciaranello AL, Wood R, Losina E, Freedberg KA, Siedner MJ).  Lancet Global Health. 2021 Feb 1;9(2):e120-9.

The Cost-effectiveness of Human Immunodeficiency Virus (HIV) Preexposure Prophylaxis and HIV Testing Strategies in High-risk Groups in India (with Costantini S, Kumarasamy N, Paltiel AD, Mayer KH, Chandhiok N, Walensky RP, Freedberg KA). Clinical Infectious Diseases. 2020 Feb 3;70(4):633-42.

Development and Validation of PREDICT-DM: A New Microsimulation Model to Project and Evaluate Complications and Treatments of Type 2 Diabetes Mellitus (with Wexler DJ, Fields NF, Parker RA, Zheng A, Walensky RP). Diabetes Technology and Therapeutics. 2019 Jun;21(6):344-355.

Methodological Areas:

• Artificial Intelligence
• Machine Learning
• Computer Vision
• Natural Language Processing
• Optimization Modeling
• Causal Inference
• Zero-knowledge Cryptography

Application Domains:

• Healthcare Operations Management
• Medical Decision Making
• Public Health Policy