An artificial intelligence approach for predicting death or organ failure after hospitalization for COVID-19: development of a novel risk prediction tool and comparisons with ISARIC-4C, CURB-65, qSOFA, and MEWS scoring systems

Abstract

Background We applied machine learning (ML) algorithms to generate a risk prediction tool [Collaboration for Risk Evaluation in COVID-19 (CORE-COVID-19)] for predicting the composite of 30-day endotracheal intubation, intravenous administration of vasopressors, or death after COVID-19 hospitalization and compared it with the existing risk scores. Methods This is a retrospective study of adults hospitalized with COVID-19 from March 2020 to February 2021. Patients, each with 92 variables, and one composite outcome underwent feature selection process to identify the most predictive variables. Selected variables were modeled to build four ML algorithms (artificial neural network, support vector machine, gradient boosting machine, and Logistic regression) and an ensemble model to generate a CORE-COVID-19 model to predict the composite outcome and compared with existing risk prediction scores. The net benefit for clinical use of each model was assessed by decision curve analysis. Results Of 1796 patients, 278 (15%) patients reached primary outcome. Six most predictive features were identified. Four ML algorithms achieved comparable discrimination (P > 0.827) with c-statistics ranged 0.849–0.856, calibration slopes 0.911–1.173, and Hosmer–Lemeshow P > 0.141 in validation dataset. These 6-variable fitted CORE-COVID-19 model revealed a c-statistic of 0.880, which was significantly (P < 0.04) higher than ISARIC-4C (0.751), CURB-65 (0.735), qSOFA (0.676), and MEWS (0.674) for outcome prediction. The net benefit of the CORE-COVID-19 model was greater than that of the existing risk scores. Conclusion The CORE-COVID-19 model accurately assigned 88% of patients who potentially progressed to 30-day composite events and revealed improved performance over existing risk scores, indicating its potential utility in clinical practice.

Machine learning–aided algorithm design for prediction of severity from clinical, demographic, biochemical and immunological parameters: Our COVID-19 experience from the pandemic

“…Previous studies with ML models in cases of COVID 19 are usually prone to the problem of not being able to be translated into healthcare system because they often provide mixed results. [ 22 ] However, the advantage our study has over these concerns is that, compared with the earlier studies that were analysed in the early stages of the pandemic, our study was done at a later stage. [ 23 24 25 26 ] This provided us with an ample insight into the clinical scenario, and data mining of records was thus worked efficiently to provide as much relevant data as required to the ML models.…”

Rural-urban Differences in Long-term Mortality and Readmission Following COVID-19 Hospitalization, 2020 to 2023

“…In this retrospective study, we analyzed data from COVID-19 patients hospitalized at 17 hospitals in Arizona, Florida, Minnesota, and Wisconsin, from 1 March 2020, to 22 July 2022, with follow-up until 23 May 2023. Data abstraction has been previously described [ 11 ]. The data were abstracted using the International Classification of Disease Clinical Modification Tenth Revision (ICD-10-CM) code U07.1 for COVID-19.…”

“…The underlying comorbidities with potential impact on COVID-19 outcomes were a priori selection based on previous outcome studies by the study investigators [ 11 ], review of published literature, expert opinion, and conditions specified by the Department of Health and Human Services [ 13 ]. Supplementary Table 2 summarizes individual chronic conditions and their respective ICD-10-CM codes.…”

A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

“…It has been extensively used in different clinical applications, e.g., for general risk assessments in the emergency department, 22 , 23 , 35 , 36 and for prediction of disease-specific outcomes in specific patient cohorts. 24 , 25 , 26 , 37 , 38 , 39 , 40 , 41 …”