Shashikumar Supreeth P, Wardi Gabriel, Paul Paulina, Carlile Morgan, Brenner Laura N, Hibbert Kathryn A, North Crystal M, Mukerji Shibani, Robbins Gregory, Shao Yu-Ping, Malhotra Atul, Westover Brandon, Nemati Shamim
medRxiv. 2020 Jun 3:2020.05.30.20118109. doi: 10.1101/2020.05.30.20118109.
Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation is of great importance and may aid in delivering timely treatment.
To develop, externally validate and prospectively test a transparent deep learning algorithm for predicting 24 hours in advance the need for mechanical ventilation in hospitalized patients and those with COVID-19.
Observational cohort study SETTING: Two academic medical centers from January 01, 2016 to December 31, 2019 (Retrospective cohorts) and February 10, 2020 to May 4, 2020 (Prospective cohorts).
Over 31,000 admissions to the intensive care units (ICUs) at two hospitals. Additionally, 777 patients with COVID-19 patients were used for prospective validation. Patients who were placed on mechanical ventilation within four hours of their admission were excluded. MAIN OUTCOME(S) and MEASURE(S): Electronic health record (EHR) data were extracted on an hourly basis, and a set of 40 features were calculated and passed to an interpretable deep-learning algorithm to predict the future need for mechanical ventilation 24 hours in advance. Additionally, commonly used clinical criteria (based on heart rate, oxygen saturation, respiratory rate, FiO2 and pH) was used to assess future need for mechanical ventilation. Performance of the algorithms were evaluated using the area under receiver-operating characteristic curve (AUC), sensitivity, specificity and positive predictive value.
After applying exclusion criteria, the external validation cohort included 3,888 general ICU and 402 COVID-19 patients. The performance of the model (AUC) with a 24-hour prediction horizon at the validation site was 0.882 for the general ICU population and 0.918 for patients with COVID-19. In comparison, commonly used clinical criteria and the ROX score achieved AUCs in the range of 0.773 - 0.782 and 0.768 - 0.810 for the general ICU population and patients with COVID-19, respectively.
A generalizable and transparent deep-learning algorithm improves on traditional clinical criteria to predict the need for mechanical ventilation in hospitalized patients, including those with COVID-19. Such an algorithm may help clinicians with optimizing timing of tracheal intubation, better allocation of mechanical ventilation resources and staff, and improve patient care.
客观且早期识别住院患者，尤其是那些可能需要机械通气的2019冠状病毒病（COVID-19）患者，非常重要，可能有助于及时提供治疗。
开发、外部验证并前瞻性测试一种透明的深度学习算法，用于提前24小时预测住院患者及COVID-19患者对机械通气的需求。
观察性队列研究
两个学术医疗中心，时间跨度为2016年1月1日至2019年12月31日（回顾性队列）以及2020年2月10日至2020年5月4日（前瞻性队列）。
两家医院重症监护病房（ICU）超过31000例入院患者。此外，777例COVID-19患者用于前瞻性验证。入院后4小时内接受机械通气的患者被排除。
每小时提取电子健康记录（EHR）数据，计算一组40个特征并传递给可解释的深度学习算法，以提前24小时预测未来对机械通气的需求。此外，使用常用的临床标准（基于心率、血氧饱和度、呼吸频率、吸入氧分数和pH值）评估未来对机械通气的需求。使用受试者操作特征曲线下面积（AUC）、敏感性、特异性和阳性预测值评估算法的性能。
应用排除标准后，外部验证队列包括3888例普通ICU患者和402例COVID-19患者。在验证地点，预测期为24小时的模型性能（AUC），普通ICU人群为0.882，COVID-19患者为0.918。相比之下，常用的临床标准和ROX评分在普通ICU人群和COVID-19患者中的AUC分别在0.773 - 0.782和0.768 - 0.810范围内。
一种可推广且透明的深度学习算法在预测住院患者（包括COVID-19患者）对机械通气的需求方面优于传统临床标准。这样的算法可能有助于临床医生优化气管插管时机，更好地分配机械通气资源和人员，并改善患者护理。
