Health Center, School of Medicine, Keio University, 35 Shinanomachi, Tokyo 160-8582, Japan.
Comput Biol Med. 2011 Nov;41(11):1051-6. doi: 10.1016/j.compbiomed.2011.09.005. Epub 2011 Oct 13.
This study aimed to predict the 6-year incidence of metabolic syndrome (MetS) using an artificial neural network (ANN) system and multiple logistic regression (MLR) analysis based on clinical factors, including the insulin resistance index calculated by homeostasis model assessment (HOMA-IR).
Subjects were recruited from participants in annual health check-ups in both 2000 and 2006. A total of 410 Japanese male teachers and other workers at Keio University, 30-59 years of age at baseline, participated in this retrospective cohort study.
Clinical parameters were randomly divided into a training dataset and a validation dataset, and the ANN system and MLR analysis were applied to predict individual incidences. The leave some out cross validation method was used for validation.
The sensitivity of the prediction was 0.27 for the MLR model and 0.93 for the ANN system, while specificities were 0.95 and 0.91, respectively. Sensitivity analysis employing the ANN system identified BMI, age, diastolic blood pressure, HDL-cholesterol, LDL-cholesterol and HOMA-IR as important predictors, suggesting these factors to be non-linearly related to the outcome.
We successfully predicted the 6-year incidence of MetS using an ANN system based on clinical data, including HOMA-IR and serum adiponectin, in Japanese male subjects.
本研究旨在基于临床因素（包括通过稳态模型评估计算的胰岛素抵抗指数），利用人工神经网络（ANN）系统和多元逻辑回归（MLR）分析来预测代谢综合征（MetS）的 6 年发病率。
本研究招募了 2000 年和 2006 年参加庆应义塾大学年度健康检查的参与者。共有 410 名年龄在 30-59 岁的日本男性教师和其他工作人员参加了这项回顾性队列研究。
临床参数随机分为训练数据集和验证数据集，然后应用 ANN 系统和 MLR 分析来预测个体的发病情况。采用留一法交叉验证方法进行验证。
MLR 模型的预测敏感性为 0.27，ANN 系统的预测敏感性为 0.93，而特异性分别为 0.95 和 0.91。采用 ANN 系统进行的敏感性分析确定 BMI、年龄、舒张压、HDL-胆固醇、LDL-胆固醇和 HOMA-IR 为重要预测因子，表明这些因素与结果呈非线性相关。
我们成功地使用基于临床数据（包括 HOMA-IR 和血清脂联素）的 ANN 系统预测了日本男性人群中 MetS 的 6 年发病率。
