Genetic biomarkers and machine learning techniques for predicting diabetes: systematic review

Abstract Diabetes mellitus is a long-term metabolic condition marked by high blood sugar levels due to issues with insulin production, insulin effectiveness, or a combination of both. It stands as one of the fastest-growing diseases worldwide, projected to afflict 693 million adults by 2045. The escalating prevalence of diabetes and associated health complications (kidney disease, retinopathy, and neuropathy) underscore the imperative to devise predictive models for early diagnosis and intervention. These complications contribute to increased mortality rates, blindness, kidney failure, and an overall diminished quality of life in individuals living with diabetes. While clinical risk factors and glycemic control provide valuable insights, they alone cannot reliably predict the onset of vascular complications. Genetic biomarkers and machine learning techniques have emerged as promising tools for predicting diabetes development risk and associated complications. Despite the emergence of numerous smart AI models for diabetes prediction, there is still a need for a thorough review outlining their progress and challenges. To address this gap, this paper offers a systematic review of the literature on AI-based models for diabetes identification, following the PRISMA extension for scoping reviews guidelines. Our review revealed that multimodal diabetes prediction models outperformed unimodal models. Most studies focused on classical machine learning models, with SNPs being the most used data type, followed by gene expression profiles, while lipidomic and metabolomic data were the least utilized. Moreover, some studies focused on identifying genetic determinants of diabetes complications relied on familial linkage analysis, tailored for robust effect loci. However, these approaches had limitations, including susceptibility to false positives in candidate gene studies and underpowered AI models capabilities due to sample size constraints. The landscape shifted dramatically with the proliferation of genomic datasets, fueled by the emergence of biobanks and the amalgamation of global cohorts. This surge has led to a more than twofold increase in genetic discoveries related to both diabetes and its complications using AI. Our focus here is on these genetic breakthroughs, particularly those empowered by AI models. However, we also highlight the existing gaps in research and underscore the need for further advancements to propel genomic discovery to the next level.