Characterizing the temporal changes in association between modifiable risk factors and acute kidney injury with multi-view analysis
Characterizing the temporal changes in association between modifiable risk factors and acute kidney injury with multi-view analysis
复制标题
DOI：
10.1016/j.ijmedinf.2022.104785
复制
发表时间：
2022-04
影响因子：
4.9
通讯作者：
Kang Liu;Borong Yuan;Xiangzhou Zhang;Weiqi Chen;L. Patel;Yong Hu;Mei Liu
中科院分区：
文献类型：
--
作者：
Kang Liu;Borong Yuan;Xiangzhou Zhang;Weiqi Chen;L. Patel;Yong Hu;Mei Liu
背景急性肾损伤（AKI）是住院患者常见的危及生命的临床综合征。机器学习的进步已经证明了使用电子健康记录（EHRs）进行AKI风险预测的成功。然而，为了预防AKI，确定临床可改变的因素并了解它们在不同预防窗口期的影响是至关重要的。方法从144,084例符合条件的住院患者的电子病历中提取4129个临床变量，包括人口统计学、社会历史、既往诊断、手术、实验室、药物、生命体征。我们为XGBoost （MV-XGB）开发了一个多视图学习框架，以增强算法对可修改因素的关注。为了研究不同时间点可变因素的影响，我们分别在AKI发病前24小时、48小时、72小时建立AKI预测模型。为了表征可修改因素对AKI影响的时间变化，我们基于SHAP值导出了两个指标，类别间评分差和暴露评分差，以比较不同窗口的可修改因素的影响。结果tmv - xgb有效地增加了对可修改因素的关注（解释了92.4%-94.1%的类间评分差异，即AKI与非AKI样本之间的预测差异），同时保持了良好的预测性能（24-48-72 h AKI预测模型的auroc分别为0.854、0.798和0.765）。我们观察到，AKI和非AKI患者在24小时内预测的比值比差异中，62%可以用24 - 72小时之间发生的因素来解释。在重要的可改变因素中，电解质平衡解释了24 - 72小时之间类别间评分差异增加的38.3%，其次是高危药物（13.7%）、护理策略（12.1%）、血压（10%）、感染（7.8%）和贫血（5.4%）。心脏手术或病情、呼吸通气和贫血的影响持续时间超过72 h。结论更好地了解临床可改变的因素对AKI的预防具有重要意义。提出的多视角学习方法改进了AKI可改变因素的识别，并允许表征其在干预中潜在益处的时间动态。
BackgroundAcute kidney injury (AKI) is a common life-threatening clinical syndrome in hospitalized patients. Advances in machine learning has demonstrated success in AKI risk prediction using electronic health records (EHRs). However, to prevent AKI, it is critical to identify clinically modifiable factors and understand their impact at different prevention windows.MethodWe extracted 4129 clinical variables including demographics, social history, past diagnoses, procedures, labs, medications, vitals from EHRs for a cohort of 144,084 eligible inpatient encounters. We developed a multi-view learning framework for XGBoost (MV-XGB) to enhance algorithm attention on modifiable factors. To study effects of modifiable factors at different time points, we built AKI prediction models at 24-hours, 48-hours, 72-hours before AKI onset. To characterize the temporal changes in effect of modifiable factors on AKI, we derived two indicators, inter-class score-difference and exposed-score-difference, based on SHAP values to compare effects of modifiable factors in different windows.ResultMV-XGB effectively increased attention on modifiable factors (explained 92.4%-94.1% inter-class score-difference, i.e., predictive difference between AKI and non-AKI samples) while maintaining good predictive performance (AUROCs were 0.854, 0.798, 0.765 in models for 24–48-72 h AKI prediction respectively). We observed that 62% of predicted odds-ratio difference between AKI and non-AKI patients in 24 h can be explained by factors occurring between 24 and 72 h. Among the important modifiable factors, electrolyte balance explained 38.3% of the inter-class score difference increase between 24 h and 72 h, followed by high-risk medications (13.7%), care strategy (12.1%), blood pressure (10%), infection (7.8%), and anemia (5.4%). Effects of cardiac surgery or condition, respiratory ventilation, and anemia remained important longer than 72 h.ConclusionBetter understanding of the clinically modifiable factors is important to AKI prevention. The proposed multi-view learning approach improved the identification of modifiable factors of AKI and allowed characterization of the temporal dynamics of their potential benefit in intervention.