Key result
The novel AI-based cardiovascular risk score (AICVD) demonstrated high predictive performance for cardiac events with an AUC of 0.853, outperforming conventional risk scores like Framingham and QRisk3.
Why the study?
CVD risk scores in the Indian population are limited by scarce research and poor performance of conventional models.
Does a novel Artificial Intelligence based Cardiovascular Risk Score (AICVD) improve the prediction of cardiovascular events compared to conventional risk scores in an Indian population?
Cohort (n=31,599)
Yes
Does a novel Artificial Intelligence based Cardiovascular Risk Score (AICVD) improve the prediction of cardiovascular events compared to conventional risk scores in an Indian population?
A novel AI-based cardiovascular risk score developed on an Indian population significantly outperforms conventional risk scores like Framingham and QRisk3 in predicting 10-year CVD events.
May aid risk stratification clinically; leaves open external validation before practice change.
Cardiovascular diseases (CVD) are one of the most prevalent diseases in India amounting for nearly 30% of total deaths. A dearth of research on CVD risk scores in Indian population, limited performance of conventional risk scores and inability to reproduce the initial accuracies in randomized clinical trials – has led to this study on large-scale patient data. The objective is to develop an Artificial Intelligence based Risk Score (AICVD) to predict CVD Event (e.g. Acute MI / ACS) in next 10 years and compare the model with the Framingham Heart Risk Score (FHRS) and QRisk3.Our study included 31,599 participants aged 18-91 years from 2009 - 2018 in six Apollo Hospitals in India. A multi-step risk factors selection process using Spearman correlation coefficient and propensity score matching yielded 21 risk factors. A Deep Learning Hazard Model was built on risk factors to predict event occurrence (classification) and time to event (hazard model) using multi-layered neural network. Further, the model was validated with independent retrospective cohorts of participants from India and the Netherlands and compared with FHRS and QRisk3.The Deep Learning Hazard model had a good performance (AUC 0.853). Validation and comparative results showed AUCs between 0.84 to 0.92 with better Positive Likelihood Ratio (AICVD-6.16 to FHRS–2.24 and QRisk3–1.16) and Accuracy (AICVD– 80.15% to FHRS 59.71% and QRisk3 51.57%). In the Netherlands cohort, AICVD also outperformed the Framingham Heart Risk Model (AUC - 0.737 vs 0.707).This study concludes that the novel AI based CVD risk score has a higher predictive performance for cardiac events than conventional risk scores.
No takes yet. Share an insight, caveat, or question.
Kumar et al. (2021) conducted a cohort in Cardiovascular Disease (n=31,599). Artificial Intelligence Based Cardiovascular Risk Score (AICVD) vs. Framingham Heart Risk Score (FHRS) and QRisk3 was evaluated on Predictive performance for cardiovascular events (AUC) (AUC 0.853, 95% CI 0.831-0.875). The novel AI-based cardiovascular risk score (AICVD) demonstrated high predictive performance for cardiac events with an AUC of 0.853, outperforming conventional risk scores like Framingham and QRisk3.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: