Integrating social and cardiometabolic risk factors in predicting cardiometabolic multimorbidity: a Bayesian model development and internal validation in Swedish middle-aged adults

Cardiometabolic diseases often cluster as multimorbidity, yet current risk prediction models typically focus on a single disease and rarely incorporate social determinants. This study aims to develop a Bayesian risk prediction model for cardiometabolic multimorbidity in middle-aged Swedish adults. This prospective cohort included 11,964 adults without prior cardiometabolic disease from the Swedish CArdioPulmonary bioImage Study (SCAPIS; enrolment 2013–2016). Cardiometabolic disease was defined as incident type 2 diabetes (T2D), ischaemic heart disease/heart failure, or stroke. Regularised Bayesian logistic regression models were developed to predict any cardiometabolic disease (≥ 1 condition) and cardiometabolic multimorbidity (≥ 2 conditions) within 2–5 years. Twenty-two social and cardiometabolic risk predictors were considered. During follow-up, 6.0% of participants developed cardiometabolic disease(s) (5.7% with a single cardiometabolic disease and 0.3% with multimorbidity). The prediction model showed fair discrimination for any cardiometabolic disease (AUC 0.76, 95% CI 0.74–0.78) and good discrimination for multimorbidity (AUC 0.89, 95% CI 0.86–0.93). The highest predicted risks were observed among older foreign-born males with hypertension, low HDL-C, high waist circumference, and current/ex-smoker, with predicted risks of 34.7% (95% CrI 30.3%–39.5%) for any cardiometabolic disease and 4.4% (95% CrI 2.0%–7.9%) for multimorbidity. These findings suggest that social determinants and uncertainty estimates may provide useful information for cardiometabolic disease prediction, though further validation is needed before use in clinical practice.