Ignorer la navigation
An AI Tool to Make Clinical Trials More Inclusive
Article

An AI Tool to Make Clinical Trials More Inclusive

An artificial-intelligence tool called Trial Pathfinder can run clinical-trial emulations using healthcare data from people with cancer, and can learn how to optimize trial-inclusion eligibility criteria, while maintaining patient safety.

Nature, 2021
References: Liu et al. (2021)


Editorial Rating

8

Qualities

  • Analytical
  • Scientific
  • Engaging

Recommendation

The AI software Trial Pathfinder offers hope for medical clinicians looking to safely expand and diversify clinical drug trials, for cancer and other diseases. Chunhua Weng and James Rogers outline a Stanford University research project, led by Ruishan Liu, which revealed the possibility of including people in trials who have often been excluded for reasons of age, health or gender. 

Summary

Clinical trial success often depends on enrolling people who meet study criteria within a specific time period.

Sometimes the inability to find enough appropriate people for a clinical trial leads to inferior conclusions. But a new software allows clinicians to include more diverse participants safely, by analyzing real-world cancer patient data.

Most clinical trials endeavor to sign up low-risk people. They exclude elderly individuals, pregnant women or people with co-morbidities other than the targeted condition. Such exclusions weed out those who are physically weak, or have toxic drug intolerance, in order to ensure trial uniformity. This strategy excludes some people who might benefit from the treatment being studied. Sometimes it results in a smaller-than-optimal study group which compromises, delays or even ends the trial.

Eligibility criteria are often established by using old trial data or by arbitrary trial design decisions. A recent study looked at ways electronic health records (EHRs) could modify a trial’s eligibility criteria to grow...

About the Authors

Chunhua Weng and James R. Rogers are members of the Department of Biomedical Informatics at Columbia University.


Comment on this summary