Machine-Learning Approaches in COVID-19 Survival Analysis and Discharge-Time Likelihood Prediction Using Clinical Data

Machine-Learning Approaches in COVID-19 Survival Analysis and Discharge-Time Likelihood Prediction Using Clinical Data

Blog Article

Summary: As a highly contagious respiratory disease, COVID-19 has yielded high mortality rates since its emergence in December 2019.As the number of COVID-19 cases soars in epicenters, health officials are warning about the possibility of the designated treatment centers being overwhelmed by coronavirus patients.In this study, several computational techniques are implemented to analyze the survival characteristics of 1,182 patients.The computational results agree with the outcome reported in early clinical reports released for a group of patients from China that confirmed a higher mortality rate in men compared with women and in older age groups.The discharge-time prediction of COVID-19 patients was also evaluated using different machine-learning and statistical analysis methods.

The results indicate Doors that the Gradient Boosting survival model outperforms other models for patient survival prediction in this study.This research study is aimed to help health officials make more educated decisions during the outbreak.The Bigger Picture: A record-breaking pressure has been placed on healthcare systems by the COVID-19 pandemic.As a result of fast-growing requests for Tweed Hats medical care in hospitals, with limited space and number of intensive care units, estimation of the length of stay of patients with COVID-19 in hospitals can provide insightful information to decision makers for efficient allocation of equipment and managing hospital overload in different countries.This work introduces statistical models and machine-learning-based approaches that can be directly applied to real-world COVID-19 data to predict the patient discharge time from hospital and evaluate how the patient clinical information could have an impact on the length of stay in hospital.

While considerable insights have been achieved about the patient recovery times in this paper, applications of these data-driven approaches are expected to gather substantial interest in the near future once more detailed clinical data are available.