Development of novel solution techniques to solve large-scale Markov decision processes and their extensions, including partially observable Markov decision process as well as model-free frameworks such as reinforcement learning.
Development of sequential stochastic decision-making models for cancer care with focus on cancer screening and optimal fractionation in radiation therapy.
Hemmati, M., Ishizawa, S., Meza, R., Ostrin, E., Hanash, S. M., Antonoff, M., ... & Toumazis, I. (2024). Benchmarking lung cancer screening programmes with adaptive screening frequency against the optimal screening schedules derived from the ENGAGE framework: a comparative microsimulation study. EClinicalMedicine, 74.
Nosrat, F., Dede, C., McCullum, L. B., Garcia, R., Mohamed, A. S., Scott, J. G., ... Hemmati, M., Schaefer, A. J. & Fuller, C. D. (2025). Optimal timing of organs-at-risk-sparing adaptive radiation therapy for head-and-neck cancer under re-planning resource constraints. Physics and Imaging in Radiation Oncology, 100715.
Hosseinian, S., Hemmati, M., Dede, C., Salzillo, T. C., van Dijk, L. V., Mohamed, A. S., ... & Fuller, C. D. (2024). Cluster-Based Toxicity Estimation of Osteoradionecrosis via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification. International Journal of Radiation Oncology* Biology* Physics.
Toumazis, I., Cao, P., de Nijs, K., Bastani, M., Munshi, V., Hemmati, M., ... & Han, S. S. (2023). Risk model–based lung cancer screening: a cost-effectiveness analysis. Annals of internal medicine, 176(3), 320-332.
Mildebrath, D., Gonzalez, V., Hemmati, M., & Schaefer, A. J. (2020). Relating single-scenario facets to the convex hull of the extensive form of a stochastic single-node flow polytope. Operations Research Letters, 48(3), 342-349.
Hemmati, M., & Smith, J. C. (2016). A mixed-integer bilevel programming approach for a competitive prioritized set covering problem. Discrete Optimization, 20, 105-134.