. Raoof Nopour; . Mostafa Shanbezadeh; . Hadi Kazemi-Arpanahi
Volume 13, Issue 1 , January 2023, , Pages 1-8
Abstract
BACKGROUND: Accurately predicting the intubation risk in COVID‑19 patients at the admissiontime is critical to optimal use of limited hospital resources, providing customized and ...
Read More
BACKGROUND: Accurately predicting the intubation risk in COVID‑19 patients at the admissiontime is critical to optimal use of limited hospital resources, providing customized and evidence‑basedtreatments, and improving the quality of delivered medical care services. This study aimed to designa statistical algorithm to select the best features influencing intubation prediction in coronavirusdisease 2019 (COVID‑19) hospitalized patients. Then, using selected features, multiple artificialneural network (ANN) configurations were developed to predict intubation risk.MATERIAL AND METHODS: In this retrospective single‑center study, a dataset containing 482COVID‑19 patients who were hospitalized between February 9, 2020 and July 20, 2021 was used. First,the Phi correlation coefficient method was performed for selecting the most important features affectingCOVID‑19 patients’ intubation. Then, the different configurations of ANN were developed. Finally,the performance of ANN configurations was assessed using several evaluation metrics, and the beststructure was determined for predicting intubation requirements among hospitalized COVID‑19 patients.RESULTS: The ANN models were developed based on 18 validated features. The results indicatedthat the best performance belongs to the 18‑20‑1 ANN configuration with positive predictive value(PPV) = 0.907, negative predictive value (NPV) = 0.941, sensitivity = 0.898, specificity = 0.951, andarea under curve (AUC) = 0.906.CONCLUSIONS: The results demonstrate the effectiveness of the ANN models for timely and reliableprediction of intubation risk in COVID‑19 hospitalized patients. Our models can inform clinicians andthose involved in policymaking and decision making for prioritizing restricted mechanical ventilationand other related resources for critically COVID‑19 patients.
