Time series LLMs with Reasoning
Many of the signals that matter most in the real world come as numerical time series: heart-rate and ECG traces in hospitals, stock prices and economic indicators in finance, or […]
Kimia Ghobadi
CSSE Associate Director
Research Projects
Patient State Modeling in Critical Care: LLMs and Continuous State Estimation
Precise modeling of patient states in critical care–essential for timely intervention and outcome prediction–remains constrained by two fundamental challenges: 1) existing models struggle to integrate heterogeneous data streams (e.g. physiological […]
The Impact of AI Scribe on Primary Care Workload
Primary care clinicians spend large amounts of their working hours, both in- and outside of the clinic, updating electronic health record (EHR) documentation for patients. In response, LLM-based AI tools […]
Scheduling in Surgery and Homecare
We study healthcare scheduling across the patient care pathway, from surgery to post-discharge home care. The first project focuses on operating room scheduling with ward inpatient capacity constraints. Elective surgery […]
Inverse Optimization for Utility Functions
Many real decisions are shaped by an optimization problem that nobody has fully written down. The constraints may come from expert rules, safety limits, or clinical guidelines, while the objective […]
Optimizing Capacity Management Decisions for Healthcare Systems Under Stress
Healthcare systems face increasing pressure from demand surges caused by pandemics, natural disasters, and seasonal illnesses. When hospitals operate near capacity, patient outcomes often deteriorate and staff burnout increases; however, […]
Feasible Regions Recovery of Optimization Models
Many real decisions are constrained in ways that are only partly written down. A clinician may accept one treatment plan and reject another, a dietitian may approve some meal plans […]
Inventory Management and PPE Procurement
Most inventory models address demand uncertainty but give limited attention to lead time uncertainty, particularly endogenous lead time uncertainty, and often ignore stockpile policies and large-scale disruptions. We propose a […]
Patient Mobility and Falls Risk Assessment Tools
This project utilizes data-drive optimization and machine learning methods to improve the quality of inpatient fall risk assessment and decision-making. Our team has developed novel optimization models to increase the […]
Radiation Therapy Treatment Planning via Inverse Optimization
This project tackles a practical bottleneck in radiation therapy planning: even with modern planning software, clinicians often have to “tune” dose-volume limits for tumors and nearby organs through repeated trial-and-error, […]
Towards Global Optimality in Stereotactic Radiation Therapy
This work focuses on brain stereotactic radiosurgery for patients with multiple metastases to identify a single “isocenter” location, the point the machine rotates around as it delivers radiation from many […]
Personalized Dietary Approaches for Chronic Disease Management
This project develops a preference-aware inverse optimization + clustering framework for precision nutrition, aimed at producing diet recommendations that jointly reflect (i) expert dietary constraints (e.g., DASH-style nutrient limits) and […]
Covid-19 mortality in US counties
This work follows a healthcare-systems question across multiple waves of COVID-19 in the United States that “as clinical care, variants, vaccination, and hospital strain changed, did the factors linked to […]