Abstract
Type 1 Diabetes Mellitus (T1D) can be related to various factors, including neonatal and perinatal conditions. This study investigated the impact of neonatal and perinatal factors-Apgar score, birth weight, feeding type, sex, and delivery type-on the risk of Type 1 Diabetes Mellitus and evaluated predictive models. A cohort of 327 patients was analyzed using correlations, General Linear Model, and artificial neural network. T1D patients showed higher birth weight, lower Apgar score, a predominance of formula feeding, and more cesarean deliveries. Diabetes risk showed a moderate positive correlation with birth weight class and nutrition type (p < 0.05) and a weak negative correlation with Apgar score (p < 0.05), while birth weight, birth weight class, and nutrition type were all weakly positively correlated with each other and with delivery type (p < 0.05). General linear model identified nutrition type, birth weight, and Apgar score as key predictors, with significant interactions among them (R(2) = 0.88). Artificial neural network achieved high accuracy (84.2%), AUC (0.95), sensitivity (89.1%), and specificity (76.7%). ANN successfully modeled the complex non-linear interactions among early-life factors, allowing it to discriminate between high-risk and low-risk cases, as evidenced by the low prediction errors (RMSE 0.31 and MAE 0.09) and strong agreement (Kappa 0.81). The models' strong internal predictive performance points to potential applications in early T1D diagnosis and personalized management, although confirmation in larger and independent datasets is needed.