Supplementary Material for: Comparison of Approaches for Prediction of Renal Replacement Therapy-Free Survival in Patients with Acute Kidney Injury

Background/Aims: Acute kidney injury (AKI) in critically ill patients is common, and continuous renal replacement therapy (CRRT) is a preferred mode of renal replacement therapy (RRT) in hemodynamically unstable patients. Prediction of clinical outcomes in patients on CRRT is challenging. We utilized several approaches to predict RRT-free survival (RRTFS) in critically ill patients with AKI requiring CRRT. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify patients ≥18 years old with AKI on CRRT, after excluding patients who had ESRD on chronic dialysis, and kidney transplantation. We defined RRTFS as patients who were discharged alive and did not require RRT ≥7 days prior to hospital discharge. We utilized all available biomedical data up to CRRT initiation. We evaluated 7 approaches, including logistic regression (LR), random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), and MLP with long short-term memory (MLP + LSTM). We evaluated model performance by using area under the receiver operating characteristic (AUROC) curves. Results: Out of 684 patients with AKI on CRRT, 205 (30%) patients had RRTFS. The median age of patients was 63 years and their median Simplified Acute Physiology Score (SAPS) II was 67 (interquartile range 52–84). The MLP + LSTM showed the highest AUROC (95% CI) of 0.70 (0.67–0.73), followed by MLP 0.59 (0.54–0.64), LR 0.57 (0.52–0.62), SVM 0.51 (0.46–0.56), AdaBoost 0.51 (0.46–0.55), RF 0.44 (0.39–0.48), and XGBoost 0.43 (CI 0.38–0.47). Conclusions: A MLP + LSTM model outperformed other approaches for predicting RRTFS. Performance could be further improved by incorporating other data types.

研究背景与目的：重症患者并发急性肾损伤（Acute Kidney Injury，AKI）较为常见，连续肾脏替代治疗（Continuous Renal Replacement Therapy，CRRT）是血流动力学不稳定患者首选的肾脏替代治疗（Renal Replacement Therapy，RRT）方式。针对接受CRRT治疗的患者开展临床结局预测颇具挑战，本研究采用多种方法对需接受CRRT治疗的AKI重症患者的无肾脏替代治疗生存（RRT-free Survival，RRTFS）进行预测。
方法：本研究使用重症监护医学信息数据库（Medical Information Mart for Intensive Care，MIMIC-III）筛选年龄≥18岁的AKI并行CRRT治疗的患者，排除接受慢性透析的终末期肾病（End-Stage Renal Disease，ESRD）患者及肾移植受者。本研究将无肾脏替代治疗生存定义为：患者出院时仍存活，且在出院前7天及以上无需接受RRT治疗。本研究利用CRRT启动前的所有可用生物医学数据，评估了7种建模方法，包括逻辑回归（Logistic Regression，LR）、随机森林（Random Forest，RF）、支持向量机（Support Vector Machine，SVM）、自适应提升（Adaptive Boosting，AdaBoost）、极端梯度提升（Extreme Gradient Boosting，XGBoost）、多层感知机（Multilayer Perceptron，MLP）以及融合长短期记忆网络的多层感知机（MLP + Long Short-Term Memory，MLP+LSTM）。本研究采用受试者工作特征曲线下面积（Area Under the Receiver Operating Characteristic Curve，AUROC）评估模型性能。
结果：本研究共纳入684例接受CRRT治疗的AKI患者，其中205例（30%）达到无肾脏替代治疗生存。患者的中位年龄为63岁，简化急性生理学评分II（Simplified Acute Physiology Score II，SAPS II）的中位值为67（四分位间距52~84）。MLP+LSTM模型的AUROC最高，为0.70（95%置信区间：0.67~0.73），其次依次为MLP（0.59，95%CI：0.54~0.64）、LR（0.57，95%CI：0.52~0.62）、SVM（0.51，95%CI：0.46~0.56）、AdaBoost（0.51，95%CI：0.46~0.55）、RF（0.44，95%CI：0.39~0.48）以及XGBoost（0.43，95%CI：0.38~0.47）。
结论：MLP+LSTM模型在预测无肾脏替代治疗生存方面优于其他建模方法，未来可通过纳入其他类型的数据进一步提升模型性能。