Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, United States.
Department of Electrical Engineering and Computer Science, Cleveland State University, Cleveland, OH 44115, United States.
J Am Med Inform Assoc. 2024 May 20;31(6):1227-1238. doi: 10.1093/jamia/ocae049.
Metabolic disease in children is increasing worldwide and predisposes a wide array of chronic comorbid conditions with severe impacts on quality of life. Tools for early detection are needed to promptly intervene to prevent or slow the development of these long-term complications.
No clinically available tools are currently in widespread use that can predict the onset of metabolic diseases in pediatric patients. Here, we use interpretable deep learning, leveraging longitudinal clinical measurements, demographical data, and diagnosis codes from electronic health record data from a large integrated health system to predict the onset of prediabetes, type 2 diabetes (T2D), and metabolic syndrome in pediatric cohorts.
The cohort included 49 517 children with overweight or obesity aged 2-18 (54.9% male, 73% Caucasian), with a median follow-up time of 7.5 years and mean body mass index (BMI) percentile of 88.6%. Our model demonstrated area under receiver operating characteristic curve (AUC) accuracies up to 0.87, 0.79, and 0.79 for predicting T2D, metabolic syndrome, and prediabetes, respectively. Whereas most risk calculators use only recently available data, incorporating longitudinal data improved AUCs by 13.04%, 11.48%, and 11.67% for T2D, syndrome, and prediabetes, respectively, versus models using the most recent BMI (P < 2.2 × 10-16).
Despite most risk calculators using only the most recent data, incorporating longitudinal data improved the model accuracies because utilizing trajectories provides a more comprehensive characterization of the patient's health history. Our interpretable model indicated that BMI trajectories were consistently identified as one of the most influential features for prediction, highlighting the advantages of incorporating longitudinal data when available.
儿童代谢疾病在全球范围内呈上升趋势，使多种慢性合并症的发病风险增加，严重影响生活质量。需要使用代谢疾病的早期检测工具，以便及时进行干预，预防或延缓这些长期并发症的发生。
目前，尚无广泛使用的临床可用工具可预测儿科患者代谢疾病的发病。在这里，我们使用可解释的深度学习技术，利用来自大型综合健康系统的电子病历数据中的纵向临床测量、人口统计学数据和诊断代码，预测儿科队列中前驱糖尿病、2 型糖尿病（T2D）和代谢综合征的发病。
该队列纳入了 49517 名超重或肥胖的 2-18 岁儿童（54.9%为男性，73%为白种人），中位随访时间为 7.5 年，平均体重指数（BMI）百分位数为 88.6%。我们的模型在预测 T2D、代谢综合征和前驱糖尿病方面的受试者工作特征曲线下面积（AUC）准确性高达 0.87、0.79 和 0.79。虽然大多数风险计算器仅使用最近可用的数据，但与仅使用最近 BMI 的模型相比，纳入纵向数据可使 T2D、综合征和前驱糖尿病的 AUC 分别提高 13.04%、11.48%和 11.67%（P < 2.2×10-16）。
尽管大多数风险计算器仅使用最近的数据，但纳入纵向数据可提高模型准确性，因为利用轨迹可更全面地描述患者的健康史。我们的可解释模型表明，BMI 轨迹始终被确定为预测的最主要特征之一，突出了在有纵向数据时纳入纵向数据的优势。
