Machine Learning-Based Risk Score development and Cut-off Determination of Regional Adiposity for Early Detection of Metabolic Syndrome in young adult.

This is a preprint and has not been peer reviewed. Data may be preliminary. Machine Learning-Based Risk Score development and Cut-off Determination of Regional Adiposity for Early Detection of Metabolic Syndrome in young adult. Abstract Background: Early identification of metabolic syndrome (MetS) in young adults is important to preventing future cardiovascular and metabolic diseases. South Asians are particularly vulnerable due to disproportionate visceral adiposity at lower body mass indices, this phenomenon making traditional BMI-centric screening insufficient. Methods: A cross-sectional study among Indian young adults assessed regional adiposity. Logistic regression identified independent adiposity predictors, and optimal cut-offs were established via receiver operating characteristic (ROC) curve analysis and the Youden Index. A machine learning–based risk score model was developed using significant predictors. Results: BF%, TAF, IAAT, and SCAT demonstrated strong associations with MetS components (p0.91). The final risk score model achieved an AUC of 0.946, offering excellent predictive ability for early MetS detection. Conclusion: Regional adiposity phenotyping combined with machine learning–based risk prediction enables early, precise identification of MetS risk among young adults. Information & Authors Information Version history Copyright This work is licensed under a Non Exclusive No Reuse License. Authors Metrics & Citations Metrics Article Usage 128views 116downloads Citations Download citation Shipra Das, Sanjay Kumar, Anil Baran Choudhury. Machine Learning-Based Risk Score development and Cut-off Determination of Regional Adiposity for Early Detection of Metabolic Syndrome in young adult.. Authorea. 26 May 2025. DOI: https://doi.org/10.22541/au.174823397.74969876/v1 DOI: https://doi.org/10.22541/au.174823397.74969876/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu.