Multi-Modal, Machine Learning-Driven Framework Integrating Multi-Omics for Personalized Chronic Kidney Disease...

Chronic kidney disease (CKD) has become a global health issue, affecting up to 14% of the population worldwide. Between 1990 and 2021, the number of patients grew from 351 million to almost 674 million, with projections warning that CKD may rank as the fifth leading cause of death globally by 2040. Clinically, CKD stems from a complex mix of etiologies, including lifestyle-driven civilization diseases, such as diabetes, hypertension, or obesity, immune-mediated glomerulonephritides (such as IgA, membranous nephropathy or focal segmental glomerulosclerosis), genetic (such as autosomal-dominant polycystic kidney disease, Fabry disease) and tubulointerstitial diseases, or causes of undetermined etiology. Time to diagnosis and the diagnosis of CKD before end-stage organ failure are crucial; therefore, new methods are actively being developed for early detection of kidney disease. Physicians emphasize the need to evaluate markers of kidney dysfunction faster and more accurately. Modern nephrology relies on multi-omics profiling, encompassing genomics, transcriptomics, proteomics, and metabolomics. Applying these technologies to identify molecular drivers of the disease can yield specific signatures that help clinicians stratify patients and decide on a treatment and follow-up plan. Our review addresses a fundamental transformation reshaping nephrology: the transition from a traditional to precision medicine approach.