Department of Endocrinology and Metabolism, Fujita Health University, Toyoake, Aichi, Japan.
IBM Research, Tokyo, Japan.
Sci Rep. 2019 Aug 14;9(1):11862. doi: 10.1038/s41598-019-48263-5.
Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.
人工智能（AI）有望辅助医学临床决策。我们利用 AI 技术，通过大数据机器学习处理自然语言和纵向数据，基于 64059 例糖尿病患者的电子病历（EMR），构建了一个用于预测糖尿病肾脏疾病（DKD）的新模型。AI 从前 6 个月中提取原始特征作为参考期，并选择 24 个因素，使用卷积自动编码器寻找与 6 个月 DKD 加重相关的时间序列模式。AI 使用逻辑回归分析构建了包含时间序列数据的 3073 个特征的预测模型。AI 对 DKD 加重的预测准确率为 71%。此外，在 10 年的时间里，DKD 加重组比非加重组接受血液透析的比例明显更高（N=2900）。AI 的新预测模型可以检测 DKD 的进展，有助于更有效地、更准确地采取干预措施，减少血液透析的需求。
