Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 3, 2026Cardiology ResearchOpen Access

Prediction of Risk of Cardiovascular Events in Patients With Stable Angina Using Artificial Intelligence: A Systematic Review

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Traditional risk scores rely on linear, population-oriented assumptions, while the utility of AI approaches for predicting cardiovascular events in stable angina needed evaluation.

Do artificial intelligence models improve the prediction of cardiovascular events in adults with stable angina compared to traditional risk scores?

Population

Adults with stable angina evaluated across five research studies

Comparison

AI models vs traditional risk prediction approaches

Design

Systematic review guided by PRISMA 2020

Key result

Artificial intelligence models enhanced discrimination for obstructive coronary artery disease and adverse cardiovascular outcomes in patients with stable angina, achieving AUCs ranging from 0.78 to >0.95.

Authors

SKSunil KumarASAbdullah Abdul SamiMKManish Kumar

Discussion

Loading...

Member takes

Overview

AI may enhance risk stratification in stable angina via ECG and clinical data; supports broader AI integration but requires prospective validation.

Key Points

  • To evaluate artificial intelligence models developed to predict cardiovascular events and risk stratification in adults with stable angina pectoris.
  • Followed PRISMA 2020 systematic review guidelines.
  • Screened 1,250 articles and included 5 studies specifically predicting cardiovascular risk in stable angina populations.
  • Evaluated data modalities including electronic health records, Seattle Angina Questionnaire scores, Gensini angiography scores, and 12-lead ECGs.
  • AI models achieved area under the receiver operating characteristic curve (AUC) values ranging from moderate (0.78–0.83) to excellent (>0.95) depending on outcome and data richness.
  • Machine learning and deep learning approaches enhanced discrimination for obstructive coronary artery disease and adverse cardiovascular outcomes compared to linear risk tools.
  • Review identified significant study heterogeneity, high variability in feature selection, and a lack of external validation and clinical implementation.

Study Design

Type

Systematic Review (n=39,655)

Structured PICO

Do artificial intelligence models improve the prediction of cardiovascular events in adults with stable angina compared to traditional risk scores?

P
Population
A systematic review of 5 studies comprising 39,655 adult patients with stable angina or chronic coronary syndrome to evaluate artificial intelligence models for predicting cardiovascular events.
E
Exposure
Artificial intelligence (AI) models, including machine learning and deep learning, utilizing data modalities such as electronic health records, 12-lead ECG, and clinical variables.
C
Comparator
Traditional clinical risk scores (e.g., Diamond-Forrester, Framingham Risk Score, PROCAM) or standard clinical assessment.
O
Outcome
Prediction of cardiovascular events (including myocardial infarction, stroke, heart failure, mortality) and obstructive coronary artery disease.composite

Main Result

Effect estimate: AUC 0.78 to >0.95

Artificial intelligence models show promise in predicting cardiovascular events in patients with stable angina, but current evidence is limited by a small number of studies, high heterogeneity, and a lack of external validation.

Limitations

  • Limited number of studies met the inclusion criteria (only 5 studies).
  • Lack of clinical validity and independent external validation.
  • High heterogeneity in datasets, outcome definitions, and final set of features.
  • Lack of fine-grained data on secondary prevention drugs such as antiplatelets and statins.
  • Potential for algorithmic bias based on sex, age, and socioeconomic status.
  • Limited number of studies
  • Lack of clinical validity
  • High heterogeneity in final set of features
  • Lack of external validation
  • Implementation limitations

Cite This Study

Kumar et al. (2026) conducted a systematic review in Stable angina (n=39,655). Artificial intelligence models (machine learning and deep learning) vs. Traditional risk scores was evaluated on Prediction of cardiovascular events and obstructive coronary artery disease (AUC 0.78 to >0.95). Artificial intelligence models enhanced discrimination for obstructive coronary artery disease and adverse cardiovascular outcomes in patients with stable angina, achieving AUCs ranging from 0.78 to >0.95.

synapsesocial.com/papers/6a9934ea636c6408cfa7cbaehttps://doi.org/10.14740/cr2211
View Full Paper
Ask AI
Bookmark
Share