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

Multi-Agent Collaborative Framework for Adverse Drug Reaction Prediction: Evidence-Based Verification and Human-Machine Decision Comparative Study

This study develops a multi-agent collaborative prediction model to forecast adverse drug reactions using real-world clinical medical records. It validates model performance via evidence-based data and compares decision outputs between the AI model and clinical physicians, aiming to improve early identification of drug adverse events. Only de-identified historical medical data will be analyzed; no new clinical interventions will be conducted, with no additional risks to participants.

Study Overview

• Status: Recruiting
• Conditions: Adverse Drug Reactions; Clinical Decision Support
• Intervention / Treatment: Other: Retrospective medical record data analysis only, no clinical intervention

Detailed Description

This observational study first retrospectively collects desensitization cases related to adverse drug reactions to construct a predictive model, and then prospectively enrolls patients to evaluate model efficacy and conduct comparative research with expert blind assessment.

• Study Type: Observational
• Enrollment (Estimated): 20000

Contacts and Locations

• Study Contact: Name: Weilong Zhang; Phone Number: 010-82266782; Email: zhangwl2012@126.com

Study Locations

• China
  • Beijing, China
    • Not yet recruiting
    • Peking University Third Hospital
  • Beijing Municipality
    • Beijing, Beijing Municipality, China
      • Recruiting
      • Peking University Third Hospital
      • Contact: Hongmei Jing, Dr.; Phone Number: 010-82266782; Email: hongmeijing@bjmu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

This study includes two types of research subjects:

Retrospective de-identified adverse drug reaction (ADR) medical records: A total of 253 ADR consultation cases covering anti-infectives, cardiovascular agents, anti-tumor drugs, central nervous system drugs and digestive system drugs. Each case contains complete medical history, medication records, ADR occurrence process and clinical outcome data, as well as at least one clinically confirmed definite ADR event.

Clinical evaluators: 20 licensed physicians or pharmacists holding intermediate or higher professional titles, with clinical pharmacy practice and regular participation in hospital ADR monitoring and consultation work.

Description

Inclusion Criteria:

• Cases shall involve drug categories including anti-infectives, cardiovascular agents, anti-tumor drugs, central nervous system drugs, digestive system drugs, etc. Each case must contain at least one definite adverse drug reaction (ADR) event, with complete supporting documentation (medical history, medication history, ADR occurrence process, and clinical outcome).

Exclusion Criteria:

• Cases with incomplete supporting documentation lacking medical history, medication history, ADR occurrence process or clinical outcome.
• Cases only with suspected or possible ADRs without definite clinical confirmation.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Coverage rate of known ADRs	Up to 8 weeks
Objective question accuracy	Up to 24 weeks
Concordance rate of predicted unknown ADRs	Up to 8 weeks
Expert-rated subjective answer quality	Up to 24 weeks

Secondary Outcome Measures

Outcome Measure	Time Frame
Subgroup differences in ADR recognition coverage rate	Up to 24 weeks
Inter-rater consistency	Up to 24 weeks
Subgroup differences in answer quality score	Up to 24 weeks
Rater acceptance scale score	Up to 24 weeks

Collaborators and Investigators

• Sponsor: Peking University Third Hospital

Study record dates

Study Major Dates

• Study Start (Actual): June 19, 2026
• Primary Completion (Estimated): June 19, 2027
• Study Completion (Estimated): December 19, 2027

Study Registration Dates

• First Submitted: August 18, 2026
• First Submitted That Met QC Criteria: September 2, 2026
• First Posted (Actual): September 9, 2026

Study Record Updates

• Last Update Posted (Actual): September 9, 2026
• Last Update Submitted That Met QC Criteria: September 2, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Chemically-Induced Disorders; Drug-Related Side Effects and Adverse Reactions
• Other Study ID Numbers: LLSC-2026288

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No