Two-step AI to predict non-cancer deaths in people with cancer

SCH: Screening and confirmatory machine learning for explainable modeling of non-cancer deaths in cancer patients

NIH-funded research Rutgers Biomedical and Health Sciences · NIH-11210793

This project uses a two-step machine learning approach on health records and genetic data to help identify which cancer patients may be at risk of dying from non-cancer causes.

Quick facts

Grant typeR37 grant
Study typeNIH-funded research
Funding institutionRutgers Biomedical and Health Sciences NIH-funded
Lab location1 site (Newark, UNITED STATES)
Project IDNIH-11210793 on NIH RePORTER

What this research studies

From a patient's perspective, researchers will combine electronic health records and genomic ('omic') data from people with breast, colorectal, prostate, and lung cancer to look for patterns linked to non-cancer deaths. They plan to use a screening AI to flag many possible risks with very high sensitivity, then a confirmatory AI to narrow those flags with very high specificity. The team emphasizes explainable models so findings are understandable to doctors and meet FAIR data principles. The work aims to create tools and workflows that could be used in clinical care to better protect survivors from preventable non-cancer causes of death.

Who could benefit from this research

Good fit: Adults with breast, colorectal, prostate, or lung cancer who can share their medical records and genomic data with the research team would be the primary candidates for participation or data contribution.

Not a fit: People without those cancer types, those unwilling to share health or genetic data, or patients whose care does not generate accessible EHR or genomic records are unlikely to benefit directly from this project.

Why it matters

Potential benefit: If successful, this work could help clinicians identify patients at higher risk of non-cancer death so they can offer earlier prevention or tailored follow-up.

How similar studies have performed: While many AI models have been used to predict cancer outcomes, using separate screening and confirmatory explainable AI specifically to predict non-cancer deaths in cancer patients is relatively new.

Where this research is happening

Newark, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions Breast CancerCancer ModelCancer PatientCancer SurvivorCancerModel
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.