Sabetian Golnar, Azimi Aram, Kazemi Azar, Hoseini Benyamin, Asmarian Naeimehossadat, Khaloo Vahid, Zand Farid, Masjedi Mansoor, Shahriarirad Reza, Shahriarirad Sepehr
Shiraz University of Medical Sciences, Anesthesiology and Critical Care Research Center, Shiraz, Iran.
Department of Biomedical Informatics, Mashhad University of Medical Sciences, Mashhad, Iran.
Indian J Crit Care Med. 2022 Jun;26(6):688-695. doi: 10.5005/jp-journals-10071-24226.
Prioritizing the patients requiring intensive care may decrease the fatality of coronavirus disease-2019 (COVID-19).
To develop, validate, and compare two models based on machine-learning methods for predicting patients with COVID-19 requiring intensive care.
In 2021, 506 suspected COVID-19 patients, with clinical presentations along with radiographic findings, were laboratory confirmed and included in the study. The primary end-point was patients with COVID-19 requiring intensive care, defined as actual admission to the intensive care unit (ICU). The data were randomly partitioned into training and testing sets (70% and 30%, respectively) without overlapping. A decision-tree algorithm and multivariate logistic regression were performed to develop the models for predicting the cases based on their first 24 hours data. The predictive performance of the models was compared based on the area under the receiver operating characteristic curve (AUC), sensitivity, and accuracy of the models.
A 10-fold cross-validation decision-tree model predicted cases requiring intensive care with the AUC, accuracy, and sensitivity of 97%, 98%, and 94.74%, respectively. The same values in the machine-learning logistic regression model were 75%, 85.62%, and 55.26%, respectively. Creatinine, smoking, neutrophil/lymphocyte ratio, temperature, respiratory rate, partial thromboplastin time, white blood cell, Glasgow Coma Scale (GCS), dizziness, international normalized ratio, O saturation, C-reactive protein, diastolic blood pressure (DBP), and dry cough were the most important predictors.
In an Iranian population, our decision-based machine-learning method offered an advantage over logistic regression for predicting patients requiring intensive care. This method can support clinicians in decision-making, using patients' early data, particularly in low- and middle-income countries where their resources are as limited as Iran.
Sabetian G, Azimi A, Kazemi A, Hoseini B, Asmarian N, Khaloo V, Prediction of Patients with COVID-19 Requiring Intensive Care: A Cross-sectional Study based on Machine-learning Approach from Iran. Indian J Crit Care Med 2022;26(6):688-695.
This study was approved by the Ethical Committee of Shiraz University of Medical Sciences (IR.SUMS.REC.1399.018).
对需要重症监护的患者进行优先级排序可能会降低2019冠状病毒病（COVID-19）的死亡率。
开发、验证并比较两种基于机器学习方法的模型，用于预测需要重症监护的COVID-19患者。
2021年，506例有临床表现及影像学检查结果的疑似COVID-19患者经实验室确诊并纳入研究。主要终点是需要重症监护的COVID-19患者，定义为实际入住重症监护病房（ICU）。数据被随机分为训练集和测试集（分别为70%和30%），不重叠。采用决策树算法和多因素逻辑回归，根据患者最初24小时的数据建立预测模型。基于受试者工作特征曲线下面积（AUC）、模型的敏感性和准确性比较模型的预测性能。
10倍交叉验证决策树模型预测需要重症监护的病例，其AUC、准确性和敏感性分别为97%、98%和94.74%。机器学习逻辑回归模型中的相同值分别为75%、85.62%和55.26%。肌酐、吸烟、中性粒细胞/淋巴细胞比值、体温、呼吸频率、活化部分凝血活酶时间、白细胞、格拉斯哥昏迷量表（GCS）、头晕、国际标准化比值、血氧饱和度、C反应蛋白、舒张压（DBP）和干咳是最重要的预测因素。
在伊朗人群中，我们基于决策的机器学习方法在预测需要重症监护的患者方面比逻辑回归具有优势。这种方法可以利用患者的早期数据支持临床医生进行决策，特别是在资源与伊朗一样有限的低收入和中等收入国家。
萨贝蒂安G，阿齐米A，卡泽米A，侯赛尼B，阿斯马里安N，哈洛V，《预测需要重症监护的COVID-19患者：基于伊朗机器学习方法的横断面研究》。《印度重症监护医学杂志》2022；26（6）：688 - 695。
本研究经设拉子医科大学伦理委员会批准（IR.SUMS.REC.1399.018）。
