Ali Ajdari, PhD.
My research asks a simple question with a complicated answer: what if cancer treatment could learn from the patient as it unfolds? I develop computational methods that combine mathematical optimization, artificial intelligence, and longitudinal patient data to turn evolving treatment response into better clinical decisions — while there is still time to act.
Extract clinically meaningful signals from imaging, biomarkers, wearables, and longitudinal treatment data.
Use prediction and optimization to determine when treatment should change, and how it should change for an individual patient.
Build decision-support and optimization systems that make advanced cancer care more efficient, deployable, and accessible.
From methods to clinical systems.
Digital biomarker-assisted cardiovascular monitoring
Longitudinal physiological monitoring during and after radiotherapy using wearable-derived cardiovascular biomarkers.
Dynamic cardiovascular risk prediction & intervention
Integrating evolving heart-rate dynamics and cardiac dosimetry to identify risk during treatment and inform potential adaptation.
Bi-level optimization for biologically informed radiotherapy
Embedding predictive models and biological objectives within clinically interpretable treatment-plan optimization.
Optimization for radiation oncology access
Decision-support for patient scheduling, machine allocation, capacity utilization, and timely access to radiation therapy.