Random forest approach for determining risk prediction and predictive factors of type 2 diabetes: large-scale health check-up data in Japan.
Random forest approach for determining risk prediction and predictive factors of type 2 diabetes: large-scale health check-up data in Japan.
复制标题
DOI：
10.1136/bmjnph-2020-000200
复制
发表时间：
2021
影响因子：
--
通讯作者：
Yamagata Z
中科院分区：
文献类型：
--
作者：
Ooka T;Johno H;Nakamoto K;Yoda Y;Yokomichi H;Yamagata Z
2型糖尿病的早期干预可以预防胰岛素抵抗的恶化。通过早期准确预测糖化血红蛋白A1c （HbA1c）的变化，可以实施更有效的干预措施。人工智能（AI）已被引入各个医学领域，可能有助于预测HbA1c的变化。然而，在使用领先的人工智能技术深度学习时，无法解释预测因素一直是一个问题。因此，我们将一种高度可解释的人工智能方法——随机森林（RF）应用于大规模健康检查数据，并检验其是否优于传统预测模型。本研究共纳入42,908例未接受HbA1c <6.5%糖尿病治疗的受试者。目标变量为下一年HbA1c的变化。每个预测模型都使用51个运行状况检查项目及其上一年的部分更改值创建。我们使用两种分析方法来比较预测能力：RF作为新模型和多元逻辑回归（MLR）作为传统模型。我们还创建了排除变化值的模型，以确定它是否对预测产生积极影响。此外，在RF分析中计算变量重要性，在MLR分析中计算标准回归系数以识别预测因子。RF模型对HbA1c变化的预测能力高于MLR模型。包含变化值的RF模型预测能力最强。在RF预测模型中，HbA1c、空腹血糖、体重、碱性磷酸酶和血小板计数是预测能力较高的因素。正确使用RF方法可以对HbA1c的变化进行高度准确的风险预测，并可以识别新的糖尿病风险预测因子。
Early intervention in type 2 diabetes can prevent exacerbation of insulin resistance. More effective interventions can be implemented by early and precise prediction of the change in glycated haemoglobin A1c (HbA1c). Artificial intelligence (AI), which has been introduced into various medical fields, may be useful in predicting changes in HbA1c. However, the inability to explain the predictive factors has been a problem in the use of deep learning, the leading AI technology. Therefore, we applied a highly interpretable AI method, random forest (RF), to large-scale health check-up data and examined whether there was an advantage over a conventional prediction model. This study included a cumulative total of 42 908 subjects not receiving treatment for diabetes with an HbA1c <6.5%. The objective variable was the change in HbA1c in the next year. Each prediction model was created with 51 health-check items and part of their change values from the previous year. We used two analytical methods to compare the predictive powers: RF as a new model and multivariate logistic regression (MLR) as a conventional model. We also created models excluding the change values to determine whether it positively affected the predictions. In addition, variable importance was calculated in the RF analysis, and standard regression coefficients were calculated in the MLR analysis to identify the predictors. The RF model showed a higher predictive power for the change in HbA1c than MLR in all models. The RF model including change values showed the highest predictive power. In the RF prediction model, HbA1c, fasting blood glucose, body weight, alkaline phosphatase and platelet count were factors with high predictive power. Correct use of the RF method may enable highly accurate risk prediction for the change in HbA1c and may allow the identification of new diabetes risk predictors.
登录
查看更多内容
影响因子：
3.7
作者：
Nanri A;Nakagawa T;Kuwahara K;Yamamoto S;Honda T;Okazaki H;Uehara A;Yamamoto M;Miyamoto T;Kochi T;Eguchi M;Murakami T;Shimizu C;Shimizu M;Tomita K;Nagahama S;Imai T;Nishihara A;Sasaki N;Hori A;Sakamoto N;Nishiura C;Totsuzaki T;Kato N;Fukasawa K;Huanhuan H;Akter S;Kurotani K;Kabe I;Mizoue T;Sone T;Dohi S;Japan Epidemiology Collaboration on Occupational Health Study Group
通讯作者：
Japan Epidemiology Collaboration on Occupational Health Study Group
影响因子：
29.4
作者：
Chen, Peng-Jen;Lin, Meng-Chiung;Tseng, Vincent S.
通讯作者：
Tseng, Vincent S.
影响因子：
5.8
作者：
Cheung, Ching-Lung;Tan, Kathryn C. B.;Cheung, Bernard M. Y.
通讯作者：
Cheung, Bernard M. Y.
影响因子：
120.7
作者：
Ting, Daniel Shu Wei;Cheung, Carol Yim-Lui;Wong, Tien Yin
通讯作者：
Wong, Tien Yin
影响因子：
1.6
作者：
Hong, Jae W.;Ku, Cheol R.;Kim, Dong-Jun
通讯作者：
Kim, Dong-Jun