Key result
COMPASS-HF proteomic model improves 10-year HF hospitalization prediction over clinical models, reaching AUC ~0.90.
Its licence doesn't allow us to show a copy here.
Why the study?
Heart failure is a severe complication in type 2 diabetes mellitus, but current risk stratification scores have limited predictive accuracy.
Does the COMPASS-HF model integrating clinical and proteomic variables improve the prediction of 10-year incident heart failure hospitalization compared to a clinical model in patients with T2DM?
Cohort (n=2,111)
Does the COMPASS-HF model integrating clinical and proteomic variables improve the prediction of 10-year incident heart failure hospitalization compared to a clinical model in patients with T2DM?
Integrating clinical variables with proteomics using machine learning significantly improves the prediction of 10-year incident heart failure hospitalization in patients with type 2 diabetes.
BACKGROUND AND AIMS: Heart failure (HF) is a severe complication in type 2 diabetes mellitus (T2DM), but current risk stratification scores have limited predictive accuracy. We aimed to develop novel prediction tools integrating clinical variables with proteomics to improve risk stratification of hospitalization for HF in T2DM. METHODS AND RESULTS: In this study, we included 2111 UK Biobank participants with T2DM but no prior HF, and profiled 2920 proteins to predict 10-year incident HF hospitalization. Participants were randomly divided into training (70%), tuning (10%), and validation (20%) sets.Three prediction models were developed: a Clinical model based on demographic characteristics, comorbidities, medication use, and laboratory indices; a Protein model based on 40 proteins selected by the Light Gradient Boosting Machine (LGBM); and the Clinical OMics and Protein ASSessment for Heart Failure (COMPASS-HF) model, which integrated both clinical variables and the LGBM-selected proteins. Models were evaluated for area under the curve (AUC), sensitivity, and specificity. During follow-up, 168 participants (7.96%) developed incident HF. The COMPASS-HF model showed better discrimination than the Clinical model, with an AUC of 0.897 (95% CI: 0.850-0.945) versus 0.790 (95% CI: 0.723-0.856). It also demonstrated higher sensitivity (0.882; 95% CI: 0.725-0.967) and consistent performance in subgroups. COMPASS-HF effectively stratified risk of hospitalization for HF, with cumulative incidence rates of 31.9% in the high-risk group and 1.2% in the low-risk group. CONCLUSIONS: By combining clinical and proteomic variables, we developed a high-performance HF prediction model for T2DM, enabling precise risk stratification and informing early intervention strategies.
No takes yet. Share an insight, caveat, or question.
Shen et al. (2026) conducted a cohort in Type 2 diabetes mellitus without prior heart failure (n=2,111). COMPASS-HF model (clinical variables + proteomics) vs. Clinical model was evaluated on Discrimination for 10-year incident HF hospitalization (AUC) (AUC 0.897, 95% CI 0.850-0.945). The COMPASS-HF model, integrating clinical and proteomic variables, showed better discrimination for 10-year incident HF hospitalization than the Clinical model (AUC 0.897 vs 0.790).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: