{"id":"CU27023","slug":"causal-modeling-of-treatment--CU27023","source":{"id":"CU27023","dataset":"techtransfer","title":"Causal modeling of treatment effect trajectories from survival data","description_":"

This technology is a computational framework that uses observational clinical data to estimate how treatment effects on patient survival change over time, supporting comparative effectiveness research and personalized treatment decisions.

\r\r

Unmet Need: Unbiased estimates of how treatment benefit changes over time

\r\r

Observational clinical datasets are a valuable source of evidence on real-world treatment effectiveness, but treatment is not randomly assigned and follow-up is often incomplete due to right censoring. Conventional survival analyses typically summarize a treatment’s effect with a single metric, such as a hazard ratio, or assume its relative benefit stays constant over time. These simplifications can obscure how treatment benefit changes over time and mask differences across patient subgroups, limiting their value for precision medicine, treatment sequencing, and comparative effectiveness research. There is a need for robust analytical methods that account for these limitations and accurately characterize how treatment effects vary over time across patient populations.

\r\r

The Technology: A computational framework that tracks treatment benefit over time

\r\r

This technology is a computational framework that uses observational clinical data to estimate how a treatment’s effect on survival changes continuously over time. It models treatment assignment using propensity scores, then combines causal survival forests with doubly robust estimation and censoring adjustment to generate treatment-effect estimates across a range of follow-up times. Parametric and spline-based smoothing methods convert these estimates into a continuous treatment-effect trajectory, from which the framework derives interpretable features such as time of peak effect, maximum effect magnitude and treatment-effect half-life. It can also characterize how treatment effects vary across patient subgroups and applies multiple statistical checks to assess the robustness of its causal estimates.

\r\r

This technology has been validated using clinical data from 2,651 head and neck squamous cell carcinoma patients drawn from the publicly available RADCURE dataset.

\r\r

Applications:

\r\r\r\r

Advantages:

\r\r\r\r

Lead Inventor:

\r\r

Igor Shuryak, M.D. Ph.D.

\r\r

Related Publications:

\r\r\r\r

Tech Ventures Reference:

\r\r\r","tags":["Chemotherapy","Drug development","Half-life","Machine learning","Precision medicine","Radiation therapy","Robust statistics","Squamous cell carcinoma"],"file_number":"CU27023","collections":[],"meta_description":"Causal survival framework estimates how treatment benefits evolve over time in observational data, revealing peak effects and subgroups.","apriori_judge_output":"{\"scores\":{\"novelty\":4.0,\"potential_impact\":4.0,\"readiness\":3.0,\"scalability\":4.0,\"timeliness\":4.0},\"weighted_score\":3.95,\"risks\":[\"Reliance on observational data may bias results if unmeasured confounding persists\",\"Computational complexity could hinder rapid deployment\",\"Regulatory acceptance of time-varying causal estimates may be uncertain\",\"Need for extensive user validation across diverse therapeutic areas\"],\"one_sentence_take\":\"Strong novelty and impact with robust causal-timeTrajectory approach, though readiness and deployment risk require broader real-world validation and regulatory alignment.\"}","inventors":["Everest Yang","Igor Shuryak"],"manager":"Joan Martinez","depts":["Computer Science","Radiation Oncology"],"divs":["Columbia University Medical Center (CUMC)"],"date_released":"2026-10-30"},"highlight":{},"matched_queries":null,"score":0.0}