Predicting the necessity of oxygen therapy in the early stage of COVID-19 using machine learning

Abstract

Medical oxygen is a critical element in the treatment process of COVID-19 patients which its shortage impacts the treatment process adversely. This study aims to apply machine learning (ML) to predict the requirement for oxygen-based treatment for hospitalized COVID-19 patients. In the first phase, demographic information, symptoms, and patient's background were extracted from the databases of two local hospitals in Iran, and preprocessing actions were applied. In the second step, the related features were selected. Lastly, five ML models including logistic regression (LR), random forest (RF), XGBoost, C5.0, and neural networks (NNs) were implemented and compared based on their accuracy and capability. Among the variables related to the patient's background, consuming opium due to the high rate of opium users in Iran was considered in the models. Of the 398 patients included in the study, 112 (28.14%) received oxygen-based treatment. Shortness of breath (71.42%), fever (62.5%), and cough (59.82%) had the highest frequency in patients with oxygen requirements. The most important variables for prediction were shortness of breath, cough, age, and fever. For opioid-addicted patients, in addition to the high mortality rate (23.07%), the rate of oxygen-based treatment was twice as high as non-addicted patients. XGBoost and LR obtained the highest area under the curve with values of 88.7% and 88.3%, respectively. For accuracy, LR and NNs achieved the best and same accuracy (86.42%). This approach provides a tool that accurately predicts the need for oxygen in the treatment process of COVID-19 patients and helps hospital resource management.

Mortality Analysis of Patients with COVID-19 in Mexico Based on Risk Factors Applying Machine Learning Techniques

“…We can find research around the world about this topic employing IA techniques such as random forest models [ 17 , 42 , 43 , 44 , 45 ], deep learning [ 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 ], decision trees [ 43 , 54 ], support vector machine (SVM) [ 49 , 55 ] and logistic regression procedures [ 49 , 56 ]; which are intended to predict the health status (mortality risk or disease severity) of a COVID-19 infected patient employing factors such as the patients age, weight, gender, physiological conditions, demographic data, travel data, computed tomography, vital signs, symptoms, smoking history, radiological features, clinical features, genetic variants, platelets, laboratory test, D-dimer test, chronic comorbidities and general health information. Meantime, other studies [ 57 ] create models using data analysis techniques with the aim of predicting the need of oxygen therapy in a timely manner in COVID-19 patients; which employed variables like shortness of breath, cough, age and fever. We can also find related works intended to design CNN-based models with the purpose of detecting positive cases of COVID-19 using chest X-ray images [ 58 ].…”

A Machine Learning Approach to Predict the Rehabilitation Outcome in Convalescent COVID-19 Patients

“…This model exhibited a similar performance in both internal (AUROC: 86.0%) and external validation (AUROC: 86.0%) [ 34 ]. Several other studies used ML to predict mortality [ 35 ] but also to evaluate the necessity of oxygen supplementation [ 36 ], to monitor pandemic-related psychopathology [ 37 ], to identify vaccine-related adverse events from Twitter data [ 38 ], and even to diagnose COVID-19 from cough audio signals [ 39 ]. However, to the best of our knowledge, no previous study used ML to predict the rehabilitation outcome in the post-acute phase of COVID-19.…”

Biotechnological Perspectives to Combat the COVID-19 Pandemic: Precise Diagnostics and Inevitable Vaccine Paradigms

“…Currently, AI is used to predict the patient’s need for oxygen therapy andasymptomatic people’s tendency to develop ARDS. This can be ruled out, which is a key clinical symptom representing the severity of COVID-19 infection [ 191 ]. Now a day’s deep learning model called COVID-19 detection neural network (CovNet) is used to distinguish between COVID-19 and community-acquired pneumonia.…”