Department of Nephrology, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
Teaching Center for Preventive Medicine, School of Public Health, Anhui Medical University, Hefei, China.
BMC Med Inform Decis Mak. 2024 May 31;24(1):148. doi: 10.1186/s12911-024-02537-9.
This study aimed to create a method for promptly predicting acute kidney injury (AKI) in intensive care patients by applying interpretable, explainable artificial intelligence techniques.
Population data regarding intensive care patients were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. Machine learning (ML) techniques with six methods were created to construct the predicted models for AKI. The performance of each ML model was evaluated by comparing the areas under the curve (AUC). Local Interpretable Model-Agnostic Explanations (LIME) method and Shapley Additive exPlanation values were used to decipher the best model.
According to inclusion and exclusion criteria, 53,150 severely sick individuals were included in the present study, of which 42,520 (80%) were assigned to the training group, and 10,630 (20%) were allocated to the validation group. Compared to the other five ML models, the eXtreme Gradient Boosting (XGBoost) model greatly predicted AKI following ICU admission, with an AUC of 0.816. The top four contributing variables of the XGBoost model were SOFA score, weight, mechanical ventilation, and the Simplified Acute Physiology Score II. An AKI and Non-AKI cases were predicted separately using the LIME algorithm.
Overall, the constructed clinical feature-based ML models are excellent in predicting AKI in intensive care patients. It would be constructive for physicians to provide early support and timely intervention measures to intensive care patients at risk of AKI.
本研究旨在通过应用可解释、可解释的人工智能技术，为重症监护患者创建一种快速预测急性肾损伤（AKI）的方法。
从 2008 年至 2019 年的医疗信息集市重症监护 IV 数据库中获取重症监护患者的人群数据。使用六种方法创建机器学习（ML）技术来构建 AKI 的预测模型。通过比较曲线下面积（AUC）来评估每个 ML 模型的性能。使用局部可解释模型不可知解释（LIME）方法和 Shapley Additive exPlanation 值来解析最佳模型。
根据纳入和排除标准，本研究共纳入 53150 名重病患者，其中 42520 名（80%）被分配到训练组，10630 名（20%）被分配到验证组。与其他五种 ML 模型相比，极端梯度提升（XGBoost）模型在 ICU 入院后对 AKI 的预测效果更好，AUC 为 0.816。XGBoost 模型的前四个贡献变量为 SOFA 评分、体重、机械通气和简化急性生理学评分 II。使用 LIME 算法分别预测 AKI 和非 AKI 病例。
总体而言，基于临床特征构建的 ML 模型在预测重症监护患者的 AKI 方面表现出色。这将有助于医生为有 AKI 风险的重症监护患者提供早期支持和及时的干预措施。
