Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, New York.
Department of Computer Science, Stony Brook University, Stony Brook, New York.
Kidney360. 2021 Nov 29;3(2):242-257. doi: 10.34067/KID.0005342021. eCollection 2022 Feb 24.
Severe AKI is strongly associated with poor outcomes in coronavirus disease 2019 (COVID-19), but data on renal recovery are lacking.
We retrospectively analyzed these associations in 3299 hospitalized patients (1338 with COVID-19 and 1961 with acute respiratory illness but who tested negative for COVID-19). Uni- and multivariable analyses were used to study mortality and recovery after Kidney Disease Improving Global Outcomes Stages 2 and 3 AKI (AKI-2/3), and Machine Learning was used to predict AKI and recovery using admission data. Long-term renal function and other outcomes were studied in a subgroup of AKI-2/3 survivors.
Among the 172 COVID-19-negative patients with AKI-2/3, 74% had partial and 44% complete renal recovery, whereas 12% died. Among 255 COVID-19 positive patients with AKI-2/3, lower recovery and higher mortality were noted (51% partial renal recovery, 25% complete renal recovery, 24% died). On multivariable analysis, intensive care unit admission and acute respiratory distress syndrome were associated with nonrecovery, and recovery was significantly associated with survival in COVID-19-positive patients. With Machine Learning, we were able to predict recovery from COVID-19-associated AKI-2/3 with an average precision of 0.62, and the strongest predictors of recovery were initial arterial partial pressure of oxygen and carbon dioxide, serum creatinine, potassium, lymphocyte count, and creatine phosphokinase. At 12-month follow-up, among 52 survivors with AKI-2/3, 26% COVID-19-positive and 24% COVID-19-negative patients had incident or progressive CKD.
Recovery from COVID-19-associated moderate/severe AKI can be predicted using admission data and is associated with severity of respiratory disease and in-hospital death. The risk of CKD might be similar between COVID-19-positive and -negative patients.
严重急性肾损伤(AKI)与 2019 年冠状病毒病(COVID-19)的不良结局密切相关,但缺乏关于肾脏恢复的数据。
我们回顾性分析了 3299 例住院患者(1338 例 COVID-19 和 1961 例急性呼吸道疾病但 COVID-19 检测阴性)的这些关联。采用单变量和多变量分析研究了 COVID-19 阴性患者的 AKI 改善全球肾脏病预后组织(KDIGO)分期 2 和 3 AKI(AKI-2/3)的死亡率和恢复情况,使用入院数据采用机器学习预测 AKI 和恢复情况。在 AKI-2/3 幸存者亚组中研究了长期肾功能和其他结局。
在 172 例 COVID-19 阴性 AKI-2/3 患者中,74%有部分恢复,44%完全恢复,而 12%死亡。在 255 例 COVID-19 阳性 AKI-2/3 患者中,部分和完全恢复的比例较低,死亡率较高(51%部分恢复,25%完全恢复,24%死亡)。多变量分析显示,入住重症监护病房和急性呼吸窘迫综合征与未恢复相关,而恢复与 COVID-19 阳性患者的存活显著相关。使用机器学习,我们能够以平均精度为 0.62 预测 COVID-19 相关 AKI-2/3 的恢复,恢复的最强预测因素是初始动脉血氧分压和二氧化碳分压、血清肌酐、钾、淋巴细胞计数和肌酸磷酸激酶。在 12 个月的随访中,在 52 例 AKI-2/3 幸存者中,26%COVID-19 阳性和 24%COVID-19 阴性患者发生或进展为慢性肾脏病。
使用入院数据可以预测 COVID-19 相关中度/重度 AKI 的恢复,并且与呼吸疾病的严重程度和住院死亡率相关。COVID-19 阳性和阴性患者的慢性肾脏病风险可能相似。