Adverse Drug Reactions, Clinical Decision Support
Conditions
Brief summary
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.
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.
Interventions
OTHERRetrospective medical record data analysis only, no clinical intervention
This study only analyzes de-identified historical electronic medical record data to build a multi-agent AI prediction model for adverse drug reactions. No drugs, medical devices, or clinical treatment interventions will be applied to any human subjects.
Sponsors
Peking University Third Hospital
Study design
Observational model
OTHER
Time perspective
OTHER
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
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.
Design outcomes
Primary
| 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
| 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 |
Countries
China
Contacts
CONTACTWeilong Zhang
Outcome results
None listed