Integrating Artificial Intelligence in the Diagnosis and Management of Metabolic Syndrome: A Comprehensive Review

Background: Metabolic syndrome (MetS) is a progressive chronic pathophysiological state characterised by abdominal obesity, hypertension, hyperglycaemia, and dyslipidaemia. It is recognised as one of the major clinical syndromes affecting human health, with approximately one-quarter of the global population impacted. MetS increases the risk of developing cardiovascular diseases (CVDs), stroke, type 2 diabetes mellitus (T2DM), and diverse metabolic diseases. Early diagnosis of MetS could potentially reduce the prevalence of these diseases. However, care for the MetS population faces significant challenges due to (i) a lack of comprehensive understanding of the full spectrum of associated diseases, stemming from unclear pathophysiological mechanisms and (ii) frequent underdiagnosis or misdiagnosis of MetS in clinical settings due to inconsistent screening guidelines, limited medical resources, time constraints in clinical practice, and insufficient awareness and training. The increasing availability of healthcare and medical data presents opportunities to apply and innovate with artificial intelligence (AI) in addressing these challenges. This review aims to (i) summarise the spectrum of diseases associated with MetS and (ii) review the diverse AI models applied to MetS and metabolic syndrome-related diseases (MetSRD), where MetSRD collectively refers to diseases and conditions directly associated with MetS. Methods: Our review consists of two phases. Initially, we conducted a literature review on MetS to narrow down the spectrum of MetSRD based on the strength of clinical evidence. We then used the terms 'Metabolic Syndrome' and 'Machine Learning' in combination with the identified MetSRD for further refinement. In total, we identified 52 related diseases in the first phase and 36 articles in the second phase. Results: We identified a total of 52 MetSRD after the first phase, with T2DM, CVDs, and cancer being the top three. Among the 36 articles obtained in the second phase, we observed the following: (i) The criteria for MetS were inconsistent across the studies. (ii) The primary purpose of AI applications was to identify risk factors for diseases, thereby improving predictions for MetS or MetSRD. Traditional machine learning models, such as Random Forest and Logistic Regression, were found to be the most effective. (iii) In addition to the MetS criteria, AI models explored other factors, including demographic and physiological variables, dietary influences, lipidomic and proteomic indicators, and more. Conclusion: This review underscores the significant link between MetS and a spectrum of diseases, with a particular focus on underreported conditions such as non-alcoholic fatty liver disease and stroke. Through the analysis of data from diverse sources, AI models, and MetS diagnostic criteria, additional indicators beyond traditional measures have been identified, emphasising the importance of combining both traditional and non-traditional markers to enhance the diagnostic and predictive capabilities for MetS and MetSRD. AI shows great potential in MetS research, particularly through the integration of multi-source data, including clinical metrics, genetic information, and omics data. The amalgamation of traditional machine learning and modern machine learning models is particularly promising, offering a balanced approach to model performance and data complexity. While international definitions provide global applicability, they may not be suitable for all populations and scenarios, necessitating flexible diagnostic criteria and adaptive, explainable algorithms. Ultimately, these will enable personalised diagnostics and targeted interventions.