Related Experiment Video
Updated: Jan 13, 2026
In Silico Clinical Trials for Cardiovascular Disease
Published on: May 27, 2022
Using Artificial Intelligence to Adjudicate Major Adverse Cardiovascular Events in Clinical Trials
Pablo M Marti-Castellote1, Samarra Badrouchi2, Brian Claggett2
1Division of Cardiovascular Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA; Cardiovascular Disease Initiative, Broad Institute of Harvard University and Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Insights
Artificial intelligence (AI) effectively adjudicates major adverse cardiovascular events (MACE), showing high agreement with physician committees. This AI system could streamline MACE assessment in clinical trials, reducing costs and improving reproducibility.
Area of Science:
- Cardiovascular research
- Medical artificial intelligence
- Clinical trial methodology
Background:
- Major adverse cardiovascular events (MACE), including cardiovascular death, myocardial infarction (MI), and stroke, are critical clinical outcomes.
- Physician-led Clinical Events Committee (CEC) adjudication of MACE in global randomized trials is accurate but labor-intensive.
- Artificial intelligence (AI) offers a potential solution for cost-effective and reproducible MACE adjudication.
Purpose of the Study:
- To develop and validate an AI-based system for MACE adjudication.
- To compare the AI system's performance against traditional CEC adjudication in a large global clinical trial.
Main Methods:
- An AI system, "Auto-MACE," was developed using OpenAI's o1-mini language model for MACE adjudication.
- A Clinical Longformer model was employed to assign confidence levels to AI adjudications.
- Auto-MACE was validated against CEC adjudication in the PARADISE-MI trial involving 5,661 patients.
Main Results:
- Auto-MACE achieved confident adjudication for 69% of deaths, 46% of MIs, and 81% of strokes.
- Agreement between Auto-MACE and CEC was high for confident adjudications (97% for deaths, 89% for MIs, 88% for strokes).
- Overall agreement across all events was 86% for deaths, 76% for MIs, and 84% for strokes, with similar treatment effect estimates.
Conclusions:
- AI-based MACE adjudication demonstrates substantial agreement with CEC adjudication, particularly for cardiovascular death and stroke.
- The AI system's confidence level is crucial for high accuracy.
- Integrating AI for initial adjudication, with CEC review for uncertain cases, can optimize workload and maintain accuracy in clinical trials.
Background:
Major adverse cardiovascular events (MACE)-cardiovascular (CV) death, nonfatal myocardial infarction (MI), and nonfatal stroke-are highly relevant clinical outcomes. In global randomized trials, medical records review by a physician clinical events committee (CEC) is the conventional standard for adjudicating MACE but is labor intensive. Automated adjudication with the use of artificial intelligence (AI) could reduce cost and improve reproducibility.
Objectives:
In this study, the authors sought to develop and validate an AI-based adjudication system for MACE and compare its performance with CEC adjudication in a large global randomized trial.
Methods:
We developed an AI-based system ("Auto-MACE") that uses an iteratively refined prompt of the OpenAI o1-mini language model to adjudicate MACE events, and a Clinical Longformer model trained on adjudicated events to assign a confidence level. We validated Auto-MACE against CEC adjudication in the PARADISE-MI global clinical trial comparing sacubitril/valsartan and ramipril in 5,661 patients with MI complicated by systolic dysfunction or pulmonary congestion.
Results:
Auto-MACE provided a confident adjudication in 315/455 deaths (69%), 301/659 potential MIs (46%), and 136/167 potential strokes (81%). Auto-MACE agreed with the CEC adjudication in 97%, 89%, and 88% of confident events, respectively. Among all events, Auto-MACE agreed with CEC adjudications in 86% of deaths, 76% of potential MIs, and 84% of potential strokes. The estimated effect of sacubitril/valsartan vs ramipril on composite MACE was similar with Auto-MACE adjudication (HR: 0.91; 95% CI: 0.78-1.07) and CEC adjudication (HR: 0.90; 95% CI: 0.77-1.05).
Conclusions:
AI-based adjudication of MACE showed high agreement with human CEC adjudication, especially for CV death and stroke, and where the model was confident. Initial AI-based adjudication with CEC review of uncertain events may reduce workload while maintaining accuracy.
More Related Videos
Related Concept Videos
01:18Cardiovascular Drugs: Classification based on Therapeutic Indications
01:11Clinical Trials: Overview
01:26Heart Failure Drugs: Inhibitors of Renin-Angiotensin System
01:16Clinical Trials
There are four phases in a clinical trial. A phase one...
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:19Pharmacovigilance
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...