Artificial Intelligence to Predict Outcomes in Patients with Acute Kidney Injury on Continuous Renal Replacement Therapy

人工智能预测急性肾损伤患者连续肾脏替代治疗的结果

• 批准号: 10261059
• 负责人: Girish Nitin Nadkarni
• 金额: $ 10万
• 依托单位: UNIVERSITY OF KENTUCKY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-19 至 2021-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10261059
• 关键词: Acute; Acute Renal Failure with Renal Papillary Necrosis; Affect; Algorithms; Artificial Intelligence; Big Data; Clinical; Clinical Data; Clinical Research; Clinical Trials; Clinical Trials Design; Critical Illness; Data; Data Set; Decision Making; Development; Dialysis procedure; Dose; Electronic Health Record; Event; Excision; Fluid overload; Goals; Hospital Mortality; Hour; Intensive Care Units; Intervention; Intervention Studies; Kidney; Liquid substance; Logistic Regressions; Measurement; Measures; Modality; Modeling; Outcome; Patient-Focused Outcomes; Patients; Performance; Phenotype; Population; Predictive Factor; Recovery; Registries; Renal Replacement Therapy; Reproducibility; Research; Resolution; Risk Factors; Series; Source; Statistical Algorithm; Survivors; Time; Ultrafiltration; Validation; Vulnerable Populations; Weight; clinical decision support; clinical decision-making; computer science; deep learning; electronic data; hemodynamics; improved; individual patient; individual response; innovation; model development; modifiable risk; mortality; mortality risk; multimodal data; multimodality; novel; outcome prediction; patient response; precision medicine; predict clinical outcome; risk prediction model; solute; therapy design; time use

ABSTRACT Acute kidney injury (AKI) affects up to half of critically ill patients admitted to intensive care units (ICU). In patients with AKI and hemodynamic instability, continuous renal replacement therapy (CRRT) is the preferred dialysis modality for solute and volume control. ICU mortality in this vulnerable population is high (~75%) but kidney recovery occurs in up to two-thirds of survivors. Fluid overload is a potentially modifiable risk factor associated with these outcomes. However, there are currently no universally accepted approaches for predicting kidney recovery, survival or individual response to fluid removal during CRRT. Due to recent advances in computer science and widespread big data usage, deep learning (DL) has emerged as a valuable approach. DL allows construction of risk prediction models using time-series data that incorporate thousands of variables and dynamic changes in these variables derived from multi-dimensional sources and not only static values of these variables. We propose to develop and validate innovative DL approaches to dynamically predict these outcomes using multi-modal data from electronic health records and CRRT machines. We demonstrated superiority of DL models without a-priori variable selection compared to optimized logistic regression (C-Statistic of 0.72 vs. 0.62) for prediction of RRT liberation. We also showed that mortality prediction improved by incorporating changes in clinical data within 6-hour intervals after CRRT initiation. In addition, we identified distinctive mortality risk according to quintiles of achieved net ultrafiltration rates, after adjustment by patient’s weight, duration of CRRT, and other clinical parameters: OR 8.0 (95% CI: 2.7-25.1) when the highest quintile (>36 ml/kg/day) was compared to the lowest quintile (<13 ml/kg/day). We hypothesize that innovative DL approaches integrating time- series data will generate accurate and generalizable risk prediction models that can impact CRRT delivery. We will utilize a multi-institutional dataset that encompasses clinical data and CRRT programmatic and therapy data (CRRTnet registry, n=1500 patients) for model development and an independent multi-institutional dataset for validation (n=1500 patients) to: 1) continuously predict short-term (7-day) and medium-term (28-day) liberation from RRT due to kidney recovery; 2) continuously predict 24-hour mortality; and 3) identify and validate sub- phenotypes of patients with AKI on CRRT with differing achieved net ultrafiltration rates. This innovative research will assist 1) the development of novel clinical decision support platforms for guiding informed CRRT delivery and promoting kidney recovery; 2) the identification of sub-phenotypes of patients that can benefit from precision- medicine approaches to fluid removal during CRRT; and 3) the design of interventional studies focusing on fluid removal during CRRT to impact patient-centered outcomes.

摘要 急性肾损伤（AKI）影响了多达一半的重症监护室（ICU）重症患者。患者 对于AKI和血流动力学不稳定，连续性肾脏替代治疗（CRRT）是首选透析 用于溶质和体积控制的模态。该弱势群体的ICU死亡率很高（~75%），但肾脏 多达三分之二的幸存者会康复。体液过多是一个潜在的可改变的风险因素， 这些结果。然而，目前还没有普遍接受的方法来预测肾脏疾病， CRRT期间对液体清除的恢复、生存或个体反应。由于计算机的最新发展， 科学和广泛的大数据使用，深度学习（DL）已经成为一种有价值的方法。DL允许 使用包含数千个变量和动态的时间序列数据构建风险预测模型 这些变量的变化来自多维来源，而不仅仅是这些变量的静态值。 我们建议开发和验证创新的DL方法，以动态预测这些结果， 来自电子健康记录和CRRT机器的多模式数据。我们证明了DL模型的优越性 无先验变量选择与优化logistic回归相比（C-统计量为0.72 vs. 0.62）， RRT释放的预测。我们还表明，通过将以下因素的变化纳入死亡率预测， CRRT开始后6小时内的临床数据。此外，我们确定了独特的死亡风险， 根据达到的净超滤率的五分位数，经患者体重、CRRT持续时间 和其他临床参数：OR 8.0（95% CI：2.7 - 25.1），当最高五分位数（> 36 ml/kg/天）为 与最低五分位数（<13 ml/kg/天）相比。我们假设，创新的DL方法整合了时间- 系列数据将生成可影响CRRT输送的准确和可推广的风险预测模型。我们 将利用包括临床数据和CRRT计划和治疗数据的多机构数据集 （CRRTnet登记研究，n = 1500例患者）用于模型开发，以及一个独立的多机构数据集， 验证（n = 1500例患者）：1）连续预测短期（7天）和中期（28天）释放 2）持续预测24小时死亡率; 3）识别和验证亚 接受CRRT治疗的AKI患者的表型，达到的净超滤率不同。这项创新性的研究 将协助1）开发新的临床决策支持平台，以指导知情CRRT输送 和促进肾脏恢复; 2）识别可以从精确- CRRT期间液体清除的医学方法;以及3）以液体为重点的介入研究的设计 CRRT期间移除，以影响以患者为中心的结局。