Key result
Novel ML tools double cardiovascular risk prediction sensitivity in systemic lupus erythematosus over standard equations.
Why the study?
SLE is associated with markedly elevated CVD morbidity and mortality influenced by social determinants of health and lifestyle factors. Given the rapid expansion of AI in rheumatology and the urgency of addressing cardiovascular health inequities in SLE, an equity-centered synthesis of SDOH, lifestyle factors, and AI applications in CVD risk prediction was needed.
Does integrating social determinants of health, lifestyle factors, and artificial intelligence improve cardiovascular risk stratification and management in adults with systemic lupus erythematosus?
Does integrating social determinants of health, lifestyle factors, and artificial intelligence improve cardiovascular risk stratification and management in adults with systemic lupus erythematosus?
This narrative review highlights the necessity of integrating social determinants of health, lifestyle interventions, and equity-focused machine learning tools to improve cardiovascular risk stratification and mitigate disparities in patients with systemic lupus erythematosus.
Answers are grounded in this paper and cite their sources.
SLE CVD risk stratification requires socioeconomic integration; leaves open prospective validation of ML tools before adoption.
Systemic lupus erythematosus (SLE) is a chronic autoimmune condition associated with markedly elevated cardiovascular disease (CVD) morbidity and mortality. Both disproportionately affect women and racial and ethnic minority populations, highlighting the profound influence of social determinants of health (SDOH) on disease trajectories. This narrative review synthesizes evidence on socioeconomic determinants and lifestyle factors that contribute to CVD among individuals with SLE and evaluates emerging applications of artificial intelligence (AI) and machine learning (ML) in CVD risk prediction and management. A comprehensive search (PubMed/MEDLINE, CINAHL, Scopus, Web of Science; 2012–2026) identified original research, systematic reviews, meta-analyses, and guidelines reporting CVD-related outcomes in SLE. Evidence demonstrates strong associations between low socioeconomic status, limited healthcare access, and educational inequities with heightened CVD risk. Black, Hispanic, and Latin American individuals experience disproportionate CVD burden due to intersecting structural, social, and clinical barriers. Modifiable lifestyle factors, including physical inactivity, tobacco use, and suboptimal dietary patterns, further exacerbate risk. Emerging ML-based studies suggest improved individualized CVD risk stratification in SLE compared with traditional general-population risk calculators, highlighting the potential for precision-focused approaches. Equity-centered strategies integrating clinical care with SDOH are essential. AI-enabled tools offer promising avenues for personalized risk prediction and resource optimization; however, rigorous attention to algorithmic fairness, transparency, and health equity is essential to ensure responsible implementation. This is the first review to synthesize SDOH, lifestyle factors, and AI in an equity-centered SLE-CVD framework, given AI’s rapid expansion in rheumatology and the urgency of addressing cardiovascular health inequities in SLE.
No takes yet. Share an insight, caveat, or question.
Choupani et al. (2026) conducted a review in Systemic lupus erythematosus (SLE) and cardiovascular disease (CVD). Social determinants of health, modifiable lifestyle factors, and AI/machine learning risk prediction models (e.g., SLECRISK) vs. Traditional general-population cardiovascular risk calculators (e.g., ACC/AHA Pooled Cohort Equations) was evaluated on Cardiovascular disease risk and individualized CVD risk stratification in systemic lupus erythematosus. Socioeconomic disadvantage and lifestyle factors elevate CVD risk in SLE (2- to 3-fold vs controls), while ML tools like SLECRISK improve risk sensitivity.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: