Department of Applied Science and Technology, Politecnico Di Torino, C.so Duca degli Abruzzi 24, 10129, Turin, Italy.
Clinical Epidemiology and Pathophysiology of Renal Diseases and Hypertension, CNR-IFC, Nefrologia-Ospedali Riuniti, 89100, Reggio Calabria, Italy.
J Nephrol. 2021 Dec;34(6):1875-1886. doi: 10.1007/s40620-021-01046-6. Epub 2021 Apr 26.
Acute Kidney Injury (AKI), a frequent complication of pateints in the Intensive Care Unit (ICU), is associated with a high mortality rate. Early prediction of AKI is essential in order to trigger the use of preventive care actions.
The aim of this study was to ascertain the accuracy of two mathematical analysis models in obtaining a predictive score for AKI development. A deep learning model based on a urine output trends was compared with a logistic regression analysis for AKI prediction in stages 2 and 3 (defined as the simultaneous increase of serum creatinine and decrease of urine output, according to the Acute Kidney Injury Network (AKIN) guidelines). Two retrospective datasets including 35,573 ICU patients were analyzed. Urine output data were used to train and test the logistic regression and the deep learning model.
The deep learning model defined an area under the curve (AUC) of 0.89 (± 0.01), sensitivity = 0.8 and specificity = 0.84, which was higher than the logistic regression analysis. The deep learning model was able to predict 88% of AKI cases more than 12 h before their onset: for every 6 patients identified as being at risk of AKI by the deep learning model, 5 experienced the event. On the contrary, for every 12 patients not considered to be at risk by the model, 2 developed AKI.
In conclusion, by using urine output trends, deep learning analysis was able to predict AKI episodes more than 12 h in advance, and with a higher accuracy than the classical urine output thresholds. We suggest that this algorithm could be integrated in the ICU setting to better manage, and potentially prevent, AKI episodes.
急性肾损伤（AKI）是重症监护病房（ICU）患者常见的并发症，与高死亡率相关。早期预测 AKI 对于触发预防性护理措施至关重要。
本研究旨在确定两种数学分析模型在获得 AKI 发展预测评分方面的准确性。比较了一种基于尿量趋势的深度学习模型和逻辑回归分析，用于预测 AKIN 指南定义的 2 期和 3 期 AKI（即血清肌酐同时升高和尿量减少）。分析了两个包含 35573 例 ICU 患者的回顾性数据集。使用尿量数据来训练和测试逻辑回归和深度学习模型。
深度学习模型定义的曲线下面积（AUC）为 0.89（±0.01），灵敏度为 0.8，特异性为 0.84，高于逻辑回归分析。深度学习模型能够在 AKI 发作前 12 小时以上预测 88%的 AKI 病例：深度学习模型识别为有 AKI 风险的 6 名患者中，有 5 名患者发生了该事件。相反，对于每 12 名未被模型认为有风险的患者，有 2 名患者发生了 AKI。
总之，通过使用尿量趋势，深度学习分析能够提前 12 小时以上预测 AKI 发作，并且准确性高于经典的尿量阈值。我们建议该算法可以整合到 ICU 环境中，以更好地管理和潜在地预防 AKI 发作。
