Unraveling complex relationships between COVID-19 risk factors using machine learning based models for predicting mortality of hospitalized patients and identification of high-risk group: a large retrospective study

Abstract

BackgroundAt the end of 2019, the coronavirus disease 2019 (COVID-19) pandemic increased the hospital burden of COVID-19 caused by the SARS-Cov-2 and became the most significant health challenge for nations worldwide. The severity and high mortality of COVID-19 have been correlated with various demographic characteristics and clinical manifestations. Prediction of mortality rate, identification of risk factors, and classification of patients played a crucial role in managing COVID-19 patients. Our purpose was to develop machine learning (ML)-based models for the prediction of mortality and severity among patients with COVID-19. Identifying the most important predictors and unraveling their relationships by classification of patients to the low-, moderate- and high-risk groups might guide prioritizing treatment decisions and a better understanding of interactions between factors. A detailed evaluation of patient data is believed to be important since COVID-19 resurgence is underway in many countries.ResultsThe findings of this study revealed that the ML-based statistically inspired modification of the partial least square (SIMPLS) method could predict the in-hospital mortality among COVID-19 patients. The prediction model was developed using 19 predictors including clinical variables, comorbidities, and blood markers with moderate predictability (Q2 = 0.24) to separate survivors and non-survivors. Oxygen saturation level, loss of consciousness, and chronic kidney disease (CKD) were the top mortality predictors. Correlation analysis showed different correlation patterns among predictors for each non-survivor and survivor cohort separately. The main prediction model was verified using other ML-based analyses with a high area under the curve (AUC) (0.81−0.93) and specificity (0.94−0.99). The obtained data revealed that the mortality prediction model can be different for males and females with diverse predictors. Patients were classified into four clusters of mortality risk and identified the patients at the highest risk of mortality, which accentuated the most significant predictors correlating with mortality.ConclusionAn ML model for predicting mortality among hospitalized COVID-19 patients was developed considering the interactions between factors that may reduce the complexity of clinical decision-making processes. The most predictive factors related to patient mortality were identified by assessing and classifying patients into different groups based on their sex and mortality risk (low-, moderate-, and high-risk groups).

Personalized Assessment of Mortality Risk and Hospital Stay Duration in Hospitalized Patients with COVID-19 Treated with Remdesivir: A Machine Learning Approach

“…Most current studies using ML techniques confirm that respiratory parameters like SpO 2 and the need for invasive ventilatory support are considered the most important predictors for mortality in hospitalized COVID-19 patients treated with remdesivir. While hypertension and worsening renal function are also considered mortality predictors in these studies, they did not hold enough significance in our research [81,82]. Kuno T et al developed a predictive model for in-hospital mortality using ML methods in COVID-19 patients treated with steroids and remdesivir.…”

Approaching Personalized Medicine: The Use of Machine Learning to Determine Predictors of Mortality in a Population with SARS-CoV-2 Infection

“…Some of them agree that advanced age is a high-risk factor for mortality [19][20][21]. Banoei et al determined that saturation level and loss of consciousness were also risk factors [22]; Kumaran et al indicated that it was respiratory difficulties [19]; Nieto-Codesido et al concluded that acute phase reactants had a high level of importance in poor prognoses [20]; and Izquierdo et al reported that fever was the second most important predictor after age [23]. These studies, like others, may differ in various aspects such as the ML model used, the time interval analyzed, and/or the variables studied.…”

Multi-Level Training and Testing of CNN Models in Diagnosing Multi-Center COVID-19 and Pneumonia X-ray Images

“…Most proposed models or systems have not been tested on other datasets. It is also noted that even though the COVID-19 datasets have become more available, most have not been validated and can be subject to mislabeling, noise, incompleteness, corruption, or low quality [46][47][48][49]. One relevant question is how these models or systems that have been trained on one training database will perform on other datasets that inevitably have certain disparities.…”