Fan Chenyu, Ding Xiu, Song Yanli
Department of Emergency, Tongji Hospital of Tongji University, Shanghai, China.
Ann Palliat Med. 2021 Feb;10(2):1772-1778. doi: 10.21037/apm-20-1117. Epub 2020 Dec 22.
Acute kidney injury is common in patients with sepsis and contributes to poor prognosis and mortality. Early identification of high-risk patients can provide evidence for clinical decision-making.
We developed a prediction model based on a cohort of 15,726 patients with sepsis from the Medical Information Mart for Intensive Care III critical care database. Logistic regression analysis was applied to develop a prediction model incorporating the selected risk factors. Discrimination and calibration of the prediction model were assessed using the C-index and calibration plot.
Risk factors in the prediction model included diabetes mellitus, chronic kidney disease, congestive heart failure, chronic liver disease, hyperbicarbonemia, hyperglycemia, low blood pH, prolonged clotting time, hypotension, and hyperlactatemia. The model showed great discrimination with a C-index of 0.711 (95% CI, 0.702-0.721) and appropriate calibration. A medium C-index value of 0.712 (95% CI, 0.697-0.727) could still be reached in the validation cohort. Negative and positive predictive values for the optimal cutoff value of ≥6 points were 56.8% and 72.3% in the training cohort and 57.3% and 72.6% in the validation cohort, respectively.
This prediction model allows clinicians to quickly assess the risk of sepsis-associated acute kidney injury (SA-AKI) at an early stage. Accordingly, clinicians can implement more medical measures that are considered beneficial to patients with sepsis.
急性肾损伤在脓毒症患者中很常见，会导致预后不良和死亡。早期识别高危患者可为临床决策提供依据。
我们基于重症监护医学信息数据库III中的15726例脓毒症患者队列开发了一个预测模型。应用逻辑回归分析来开发一个纳入选定风险因素的预测模型。使用C指数和校准图评估预测模型的区分度和校准情况。
预测模型中的风险因素包括糖尿病、慢性肾脏病、充血性心力衰竭、慢性肝病、高碳酸氢血症、高血糖、低血pH值、凝血时间延长、低血压和高乳酸血症。该模型显示出良好的区分度，C指数为0.711（95%CI，0.702-0.721），校准情况良好。在验证队列中，C指数的中位数为0.712（95%CI，0.697-0.727）。在训练队列中，≥6分的最佳截断值的阴性和阳性预测值分别为56.8%和72.3%，在验证队列中分别为57.3%和72.6%。
该预测模型使临床医生能够在早期快速评估脓毒症相关急性肾损伤（SA-AKI）的风险。因此，临床医生可以实施更多被认为对脓毒症患者有益的医疗措施。
