# Prognostic Models for Predicting Coronary Heart Disease Risk in Patients with Type 2 Diabetes Mellitus: A Systematic Review and Meta-Analysis

## TL;DR

This study reviews and evaluates prediction models for coronary heart disease in patients with type 2 diabetes, finding moderate accuracy but significant variability.

## Contribution

The paper systematically reviews and meta-analyzes prognostic models for CHD in T2DM, highlighting variability and suggesting directions for future model development.

## Key findings

- Pooled AUC of 0.69 with high heterogeneity (I² = 97.4%) indicates moderate discrimination but significant variability across models.
- Machine learning and imaging models showed higher AUC but faced limitations like small sample sizes and poor calibration reporting.
- Applicability issues were common in models requiring advanced imaging or molecular platforms.

## Abstract

Background: Individuals with type 2 diabetes mellitus (T2DM) are at markedly increased risk of developing coronary heart disease (CHD); however, the generalizability and transportability of existing prediction models remain uncertain. Objective: To identify and evaluate multivariable prognostic models developed to predict CHD in adults with T2DM. Methods: We conducted a PRISMA-guided systematic review and meta-analysis of multivariable prognostic models predicting CHD in T2DM populations. Model characteristics and performance metrics were extracted following the CHARMS and TRIPOD-SRMA frameworks, and pooled discrimination was estimated on the logit-transformed AUC scale using a random-effects model (REML, Hartung–Knapp adjustment). Between-study heterogeneity and 95% prediction intervals were quantified, while risk of bias and applicability were assessed using the PROBAST tool. Results: Thirteen studies encompassing clinical, imaging-based, and omics-augmented models met the inclusion criteria. The pooled AUC was 0.69 (95% CI: 0.66–0.71), with high heterogeneity (I2 = 97.4%; τ2 = 0.0979) and a wide 95% prediction interval (0.54–0.81). Classical regression-based models demonstrated modest discrimination, whereas machine learning, imaging, and proteomic approaches achieved higher AUC estimates but were frequently constrained by small sample sizes, internal-only validation, and poor calibration reporting. The analysis domain emerged as the principal source of bias in PROBAST evaluations, and applicability issues were most frequent in models requiring advanced imaging or molecular platforms. Conclusions: Prognostic models for CHD in T2DM demonstrate moderate-to-good discrimination but substantial heterogeneity and frequent miscalibration across studies. Their clinical utility depends on rigorous external validation and local recalibration, particularly when incorporating imaging or molecular predictors. Future research should prioritize standardized CHD outcomes, consistent calibration reporting, decision-analytic assessments, and the development of transportable multimodal prediction models across diverse populations.