01 — Research

Three threads, one closed loop

We develop computational methods for cancer care that observe how patients change during treatment, translate those signals into timely treatment decisions, and make those advances practical and accessible in real-world care.

01 Monitor
02 Adapt
03 Deliver
IMAGING BLOOD WEARABLE EVOLVING PATIENT STATE
01 · Monitor

Response monitoring & biomarker discovery

What is changing — and can we measure it?

Cancer treatment produces biological and physiological changes long before they become visible as conventional clinical endpoints. We develop and validate biomarkers that capture this evolving patient state during therapy, with particular emphasis on measurements that are longitudinal, low-burden, and practical to acquire repeatedly.

Our work spans digital biomarkers derived from wearable physiological sensing, imaging biomarkers that characterize tumor evolution from routinely acquired treatment imaging, and molecular biomarkers, including circulating tumor DNA and other blood-based measures. Across modalities, the goal is the same: identify signals that tell us, early and reliably, how an individual patient is responding.

Current directions
DIGITAL HEALTH · LONGITUDINAL IMAGING · ctDNA · CARDIOVASCULAR PHYSIOLOGY · IMMUNE MONITORING
SIGNAL DECIDE CONTINUE ADAPT PREDICT + OPTIMIZE ACTIONABLE TREATMENT
02 · Adapt

Dynamic treatment adaptation

We have a signal — what should change, and when?

A biomarker becomes clinically useful when it can inform a decision. We develop computational methods that translate evolving patient signals into timely, actionable treatment interventions.

This requires deciding not only how treatment should change, but whether and when adaptation is warranted under uncertainty. Our work spans optimal stopping and sequential decision-making, biologically informed adaptive radiotherapy, bilevel and multicriteria optimization, and the integration of machine-learning-based outcome and toxicity models directly into treatment planning. The goal is to move from prediction to prescription: using what we learn about the patient to determine the next best treatment decision.

Current directions
ADAPTIVE RT · OPTIMAL STOPPING · BILEVEL OPTIMIZATION · RISK-INFORMED PLANNING · AI-INFORMED OPTIMIZATION · DECISION-MAKING UNDER UNCERTAINTY
PATIENT HEALTH SYSTEM BROADER ACCESS
03 · Deliver

Accessible & patient-centered delivery

How do we make better cancer care reach more patients?

Precision should not require complexity that puts it out of reach. We design monitoring and decision-support systems with scalability, patient burden, and clinical resources in mind, so that advances in personalization can extend beyond highly specialized settings.

This principle shapes both sides of our work: patient-facing digital health technologies that enable inexpensive, longitudinal monitoring outside the clinic, and health-system optimization tools that help allocate scarce treatment resources more effectively. Projects such as CardiMom and NexusRT aim to make sophisticated monitoring and treatment delivery easier to use, easier to access, and more responsive to the needs of individual patients.

Current directions
DIGITAL HEALTH · PATIENT-FACING TOOLS · NEXUSRT · RESOURCE OPTIMIZATION · CLINICAL IMPLEMENTATION · SCALABLE CARE
Selected translation
2025– NexusRT — optimization-based radiation oncology scheduling → Treatment access · capacity management · clinical decision support
2025– Wearable-enabled remote cardiovascular monitoring → Patient-facing iPhone / Apple Watch platform
Patent Personalization of cancer treatment during radiotherapy US Patent ID 2019PF00235
The common thread

From observation to action

Across these programs, the underlying question is the same: what can we learn about a patient's evolving state, and how should that information change the next decision? We approach that problem using mathematical optimization, statistical learning, machine learning, and decision-making under uncertainty.

PATIENT → MEASUREMENT → STATE → RESPONSE / RISK → DECISION → TREATMENT → PATIENT
2026 Bi-level multi-criteria optimization for risk-informed radiotherapy ↗ Schubert M, Teichert K, Bortfeld T, Liao X, Ajdari A · Physics in Medicine & Biology, 71:135037
2025 Radiation doses to cardiac substructures predict elevation in high-sensitivity cardiac troponin T levels ↗ Chen X et al., Ajdari A et al. · International Journal of Radiation Oncology, Biology, Physics
2024 Embedding machine-learning-based toxicity models within radiotherapy treatment-plan optimization ↗ Maragno D, Buti G, Birbil SI, Liao Z, Bortfeld T, den Hertog D, Ajdari A · Physics in Medicine & Biology, 69(7)
2021 Toward personalized radiation therapy of liver metastasis: importance of serial blood biomarkers ↗ Ajdari A, Xie Y, Richter C, Niyazi M, Duda DG, Hong TS, Bortfeld T · JCO Clinical Cancer Informatics, 5:315–325
2019 Towards optimal stopping in radiation therapy ↗ Ajdari A, Niyazi M, Nicolay NH, Thieke C, Jeraj R, Bortfeld T · Radiotherapy and Oncology, 134:96–100

Complete publication list on Google Scholar.