624-P: Bridging Psychiatric Interventions and Glycemic Control in Children with Type 2 Diabetes Mellitus Based on Machine Lea

초록

Introduction and Objective: The impact of psychiatric interventions on glycemic control in pediatric and adolescent patients with type 2 diabetes mellitus (T2DM) has not been assessed using machine learning methods. We investigated the integration of psychiatric interventions in the management of T2DM, emphasizing the need for psychosocial support, as recommended by the 2024 American Diabetes Association and 2022 International Society for Pediatric and Adolescent Diabetes guidelines. Methods: We applied machine learning on a dataset from Inha University Hospital, Korea, involving 111 pediatric patients with T2DM to predict the optimal timing for psychiatric intervention to enhance glycemic control. Results: The analysis revealed that early psychiatric interventions contributed to more stable glycemic control with a slight improvement in HbA1c levels, indicating the effectiveness of these interventions. Advanced analytical techniques identified patient subgroups that benefited from early intervention, although age did not significantly affect the outcomes. Conclusion: This study serves as a foundation for future research utilizing datasets in the field of medicine, emphasizing the role of machine learning in predicting disease prognosis and adopting a multifaceted approach to analyze factors influencing disease outcomes. It advocates a shift towards leveraging comprehensive data analysis to enhance our understanding of diseases, thereby fostering more informed, predictive, and personalized disease management strategies. This aspiration pioneered the application of machine learning to explore the breadth of data to advance patient c