In Nutrition, metabolism, and cardiovascular diseases : NMCD
BACKGROUND AND AIMS : Metabolic syndrome (MetS) definitions in adolescents based on the percentiles of its components are rather complicated to use in clinical practice. The aim of this study was to test the validity of artificial intelligence (AI)-based scores (AI_METS) that do not use these percentiles for MetS screening for adolescents.
METHODS AND RESULTS : This study included 1086 adolescents aged 12 to 18. The cohort underwent anthropometric measurements and blood tests. Mean blood pressure (MBP), and triglyceride glucose index (TyG) were calculated. Explainable AI methods are used to extract the learned function. Gini importance techniques were tested and used to build new scores for the screening of MetS. IDF, Cook, De Ferranti, Viner, and Weiss definitions of MetS were used to test the validity of these scores. MetS prevalence was 0.4%-4.7% according to these definitions. AI_METS used age, waist circumference, MBP, and TyG index. They offer area under the curves (AUCs) 0.91, 0.93, 0.89, 0.93, and 0.98; specificity 81%, 75%, 72%, 80%, and 97%; and sensitivity 90%, 100%, 90%, 100%, and 100%, respectively, for the detection of MetS according to these definitions. Considering only MBP offers a better specificity and sensitivity to detect MetS than considering only TyG index. MBP offers slightly lower performance than AI_METS.
CONCLUSION : AI techniques have proven their ability to extract knowledge from data. They allowed us to generate new scores for MetS detection in adolescents without using specific percentiles for each component. Although these scores are less intuitive than the percentile-based definition, their accuracy is rather effective for the detection of MetS.
Benmohammed Karima, Valensi Paul, Omri Nabil, Al Masry Zeina, Zerhouni Noureddine
Adolescent, Artificial intelligence, Cardiometabolic risk factors, Metabolic syndrome