Causal modeling of treatment effect trajectories from survival data
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.
Unmet Need: Unbiased estimates of how treatment benefit changes over time
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.
The Technology: A computational framework that tracks treatment benefit over time
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.
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.
Applications:
- Comparative effectiveness research using real-world observational clinical data
- Precision medicine and treatment selection
- Oncology treatment-effect analysis
- Treatment sequencing and duration analysis
- Clinical research and drug development
- Identification of treatment-response heterogeneity
- Health technology assessment and outcomes research
Advantages:
- Characterizes how treatment benefit evolves continuously over time
- Accounts for non-random treatment assignment and incomplete patient follow-up inherent to observational data
- Generates interpretable, clinically actionable readouts such as peak effect timing and duration
- Identifies patient subgroups most likely to benefit from a given treatment
- Incorporates built-in robustness and validation checks to support confidence in causal estimates
- Applicable to any right-censored, observational survival dataset
Lead Inventor:
Related Publications:
Tech Ventures Reference:
IR CU27023
Licensing Contact: Joan Martinez