@文章{信息:doi/10.2196/16850，作者="Zhang, Lei and Shang, Xianwen and Sreedharan, Subhashaan and Yan, Xixi and Liu, Jianbin and Keel, Stuart and Wu, Jinrong and Peng, Wei and He, Mingguang"，标题="利用机器学习技术预测澳大利亚大型队列中2型糖尿病的发展:纵向调查研究"，期刊="JMIR Med Inform"，年="2020"，月="七月"，日="28"，卷="8"，数="7"，页数="e16850"，关键词="糖尿病;机器学习;风险预测;背景:以前预测糖尿病的传统模型可以通过结合越来越多的可用健康数据和新的风险预测方法进行更新。目的:我们的目标是使用复杂的机器学习算法，在2006-2017年期间纳入研究的超过23万人的大型回顾性人群队列的基础上，开发一个显著改进的糖尿病风险预测模型。方法:我们收集了来自45岁及以上研究的超过236,684名无糖尿病参与者的2型糖尿病(T2DM)的人口统计学、医学、行为和发病率数据。基于三种机器学习方法和传统回归模型，我们预测并比较了这些参与者在3年、5年、7年和10年的糖尿病发病风险。结果:总体而言，6.05{\%}(14,313/236,684)的参与者在平均8.8年的随访期内患上了2型糖尿病。男性10年糖尿病发病率为8.30{%}(8.08{%}-8.49{%})，显著高于女性6.20{%}(6.00{%}-6.40{%})(优势比1.37,95{%}CI 1.32-1.41)。肥胖个体的T2DM发病率翻倍(男性:17.78{\%}[17.05{\%}-18.43{\%}]; women: 14.59{\%} [13.99{\%}-15.17{\%}]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79{\%} in 3-year prediction and 75{\%} in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12{\%}-50{\%} of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3{\%} to 2.8{\%} (P<.001). Conclusions: A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM. ", issn="2291-9694", doi="10.2196/16850", url="https://medinform.www.mybigtv.com/2020/7/e16850", url="https://doi.org/10.2196/16850", url="http://www.ncbi.nlm.nih.gov/pubmed/32720912" }