Better prediction tools for cancer outcomes and postoperative opioid needs

New Statistical Methods for Modelling Cancer Outcomes

NIH-funded research University of Michigan at Ann Arbor · NIH-11321191

This project creates improved statistical tools to help doctors predict opioid needs after surgery and to predict outcomes for adults with lung cancer.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of Michigan at Ann Arbor NIH-funded
Lab location1 site (Ann Arbor, United States)
Project IDNIH-11321191 on NIH RePORTER

What this research studies

From a patient's point of view, researchers are using large real-world hospital databases to build new prediction methods that estimate how much opioid medicine adult surgery patients may need and how muscle-related measurements relate to lung cancer survival. They will combine data from thousands of surgical patients across many hospitals and from lung cancer cohorts to train these models and measure how uncertain the predictions are. The goal is to make predictions more reliable so clinicians can personalize prescriptions and care plans, including clinical, nutritional, and physical interventions. The work focuses on adult patients and uses existing clinical and laboratory data rather than experimental treatments.

Who could benefit from this research

Good fit: Ideal candidates are adults who are opioid-naïve undergoing surgery at participating hospitals and adults diagnosed with lung cancer who are included in the study cohorts.

Not a fit: Children, people under 21, and adults who are not treated at participating hospitals or who are outside the lung cancer or surgical cohorts are unlikely to benefit directly from this work.

Why it matters

Potential benefit: If successful, this could lead to safer, more personalized opioid prescribing after surgery and better-tailored care plans that may improve lung cancer outcomes.

How similar studies have performed: Related prediction efforts for opioid prescribing and for muscle metrics in cancer have shown promise, but combining large clinical databases with advanced uncertainty-focused statistical methods is relatively new.

Where this research is happening

Ann Arbor, 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 Cancer Model
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.