Machine learning algorithms for predicting determinants of COVID-19 mortality in South Africa

Abstract

BackgroundCOVID-19 has strained healthcare resources, necessitating efficient prognostication to triage patients effectively. This study quantified COVID-19 risk factors and predicted COVID-19 intensive care unit (ICU) mortality in South Africa based on machine learning algorithms.MethodsData for this study were obtained from 392 COVID-19 ICU patients enrolled between 26 March 2020 and 10 February 2021. We used an artificial neural network (ANN) and random forest (RF) to predict mortality among ICU patients and a semi-parametric logistic regression with nine covariates, including a grouping variable based on K-means clustering. Further evaluation of the algorithms was performed using sensitivity, accuracy, specificity, and Cohen's K statistics.ResultsFrom the semi-parametric logistic regression and ANN variable importance, age, gender, cluster, presence of severe symptoms, being on the ventilator, and comorbidities of asthma significantly contributed to ICU death. In particular, the odds of mortality were six times higher among asthmatic patients than non-asthmatic patients. In univariable and multivariate regression, advanced age, PF1 and 2, FiO2, severe symptoms, asthma, oxygen saturation, and cluster 4 were strongly predictive of mortality. The RF model revealed that intubation status, age, cluster, diabetes, and hypertension were the top five significant predictors of mortality. The ANN performed well with an accuracy of 71%, a precision of 83%, an F1 score of 100%, Matthew's correlation coefficient (MCC) score of 100%, and a recall of 88%. In addition, Cohen's k-value of 0.75 verified the most extreme discriminative power of the ANN. In comparison, the RF model provided a 76% recall, an 87% precision, and a 65% MCC.ConclusionBased on the findings, we can conclude that both ANN and RF can predict COVID-19 mortality in the ICU with accuracy. The proposed models accurately predict the prognosis of COVID-19 patients after diagnosis. The models can be used to prioritize COVID-19 patients with a high mortality risk in resource-constrained ICUs.

Use of machine learning to identify protective factors for death from COVID-19 in the ICU: a retrospective study

“…This highlights that the choice of variables can significantly impact the variables identified as associated with the outcome. Moreover, their model exhibited different performance metrics compared to ours, achieving a recall of 76% and a precision of 87%, whereas our model achieved a higher recall of 90.1% and precision of 84.9%, indicating that our model correctly identified more true positives ( Chimbunde et al, 2023 ; Hicks et al, 2022 ).…”

“… Chimbunde et al (2023) utilized RF to predict determinants of COVID-19 mortality in South Africa. Surprisingly, their analysis revealed that being female was associated with increased mortality, contrary to findings from our study and others, which suggested that being female was protective ( Elhazmi et al, 2022 ; Kar et al, 2021 ).…”

Unlocking Maternal Outcome Prediction Potential: A Comprehensive Analysis of the ConvXGB Model Integrating XGBoost and Deep Learning” at Evolving Systems.

“…Review of Related Works The computational learning approach has been proven to be a reliable tool in predicting various maternal outcomes, such as full-term delivery (Predicting induced labour outcomes for full-term pregnancies using an Intuitionistic Fuzzy Approach for maternal outcome prediction [12], [13]), miscarriage (proposed early prediction for both miscarriage and threatened miscarriage [3], [14], [15]), mortality (implemented machine learning techniques to forecast in-hospital mortality [16]- [18]),placenta previa, preterm delivery (utilizing machine learning for the early prediction of spontaneous preterm birth [19]- [22]), stillbirth (Data-Driven Stillbirth Prediction in Pregnancy [23]), and Urinary Tract Infection (UTI) exploring machine learning algorithms for predicting UTI [24]- [27]. It is encouraging to see the advancements in this field, which have the potential to improve the health and safety of expectant mothers.…”