Artificial Clinic Intelligence (ACI): A Generative AI-Powered Modeling Platform to Optimize Patient Cohort Enrichment...

Area of Science:

• Biomedical Informatics
• Artificial Intelligence in Medicine
• Clinical Trial Design

Background:

• Clinical trial enrichment is crucial for drug development, focusing on patient recruitment based on predicted benefit or toxicity.
• Identifying predictive clinical parameters for novel or repurposed drugs in diverse populations remains a significant challenge.
• Existing Artificial Intelligence (AI) applications in clinical trials lack prospective prediction capabilities for therapeutic benefit in unseen patient groups.

Purpose of the Study:

• To propose a novel generative AI (GAI) framework, Artificial Clinic Intelligence (ACI), for advanced clinical trial enrichment.
• To enable prospective prediction of therapeutic intervention benefits for unseen patient populations.
• To inform clinicians on essential clinical parameters for optimizing patient selection prior to trial enrollment.

Main Methods:

• Development of a GAI-powered platform, Artificial Clinic Intelligence (ACI).
• Generation of synthetic patient data to model clinical trial enrichment scenarios.
• Modeling of clinical trial enrichment to identify key predictive patient characteristics.

Main Results:

• ACI provides a method for prospective prediction of patient benefit from therapeutic interventions.
• The platform models clinical trial enrichment by generating synthetic data.
• ACI identifies key clinical parameters that are enriched in prospective patients.

Conclusions:

• Artificial Clinic Intelligence (ACI) offers a novel approach to enhance clinical trial enrichment using GAI.
• The platform facilitates informed patient selection by predicting therapeutic benefits in unseen populations.
• ACI has the potential to improve the efficiency and success rate of clinical trials.