+1 877 705 1914• 24 / 7
HIPAA Compliant
ISO 27001 Certified

Actively Recruiting

All Ages
All Genders
ID07808866

Collaborative AI Model for Predicting Adverse Drug Reactions Using Real-World Clinical Data and Human-Machine Comparison

Led by Peking University Third Hospital · Updated on 2026-09-09

20000

Participants Needed

2

Research Sites

26 weeks

Total Duration

AI-Summary

What This Trial Is About

Researchers are developing a collaborative multi-agent prediction model to forecast adverse drug reactions ADRs by analyzing real-world clinical medical records. The study aims to validate the models performance using evidence-based data and compare its decision outputs with those made by clinical physicians, focusing on improving early identification of drug-related adverse events. This observational study includes both retrospective data collection and prospective patient evaluation. The study first collects past cases of desensitization related to ADRs to build the predictive model. It then prospectively enrolls patients to assess the models effectiveness and conducts comparative research involving expert blind assessments. Only de-identified historical medical data will be analyzed, and no new clinical interventions or treatments will be applied to participants. Participants involvement includes the use of their previously collected medical records containing detailed documentation of ADR events, medication history, and clinical outcomes. Researchers will measure the models accuracy, coverage rate of known and unknown ADRs, and expert-rated answer quality over periods up to 24 weeks. The study also evaluates subgroup differences, inter-rater consistency, and expert acceptance scores, ensuring no additional risks to participants throughout the study duration.

CONDITIONS

Brief Title

Multi-Agent Collaborative ADR Prediction With Human-Machine Decision Comparison

Research Team

W

Weilong Zhang

Not the Right Trial for You?

Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.

Already have an account? Log in here