There has been a significant influence of AI on chronic disease interventions in a personalized way, especially for diabetes mellitus. AI-managed tools such as wearable devices/smartphone algorithms offer individuals the chance to monitor exercise endurance, blood glucose, daily diet, heart rate, body composition metrics, etc., for the management of this complex metabolic disorder. Unsupervised and supervised machine learning algorithms can analyze enormous amounts of data from genetic, lifestyle factors, cardiovascular biomarkers to quantify the individual risk factors for diabetes-related cardiometabolic outcomes. Novel treatments are being discovered through AI-driven drug discovery and developmental processes. AI is also creating virtual simulations and models of complex biological conditions and pathways, helping researchers in the development of targeted therapies.
AI enhancement for the detection of diabetes-related complications like retinopathy and neuropathy by imaging and clinical data is now proliferating in literature in both research and clinical practice. Machine learning algorithms can analyze medical imaging and clinical data to identify early signs of diseases like fatty liver disease, prediabetes, and diabetes, as well as complications like early retinopathy. This early detection can lead to timely interventions, preventing the progression of these diseases to more severe stages.
In addition to all the above, AI is leading to a very personalized and precision-driven medical approach for the titration of drugs, especially insulin, that incorporates an individual’s race, gender, ethnicity, lifestyle, and genetic makeup into clinical decision-making. AI is particularly suited to the assessment of response to therapy, helping patients and clinicians make informed decisions about the management plan. AI is also recommending personalized diet plans that are more effective in managing weight and preventing negative cardiometabolic outcomes in diabetes. More recently, large language models (LLMs) and other facets of Generative AI are transforming the landscape of healthcare by discovering patterns in diabetes mellitus that were unexplorable or undiscoverable in the past.
In summary, we believe that this topic would be very timely for a review of the current state of the science in this field.
Keywords: AI, Diabetes mellitus, Treatment, Early detection, Diabetes-related complications, Machine learning algorithms
Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.