Severity and mortality prediction models to triage Indian COVID-19 patients

Samarth Bhatia, Yukti Makhija, Sneha Jayaswal, Shalendra Singh, Prabhat Singh Malik, Sri Krishna Venigalla, Pallavi Gupta, Shreyas N Samaga, Rabi Narayan Hota and Ishaan Gupta

PLOS Digital Health, 2022, vol. 1, issue 3, 1-11

Abstract: As the second wave in India mitigates, COVID-19 has now infected about 29 million patients countrywide, leading to more than 350 thousand people dead. As the infections surged, the strain on the medical infrastructure in the country became apparent. While the country vaccinates its population, opening up the economy may lead to an increase in infection rates. In this scenario, it is essential to effectively utilize the limited hospital resources by an informed patient triaging system based on clinical parameters. Here, we present two interpretable machine learning models predicting the clinical outcomes, severity, and mortality, of the patients based on routine non-invasive surveillance of blood parameters from one of the largest cohorts of Indian patients at the day of admission. Patient severity and mortality prediction models achieved 86.3% and 88.06% accuracy, respectively, with an AUC-ROC of 0.91 and 0.92. We have integrated both the models in a user-friendly web app calculator, https://triage-COVID-19.herokuapp.com/, to showcase the potential deployment of such efforts at scale.Author summary: As the medical system in India struggles to cope with more than 1.5 million active cases, with a total number of patients crossing 30 million, it is essential to develop patient triage models for effective utilization of medical resources. Here, we built cross-validated machine learning models using data from one of the largest cohorts of Covid-19 patients from India to categorize patients based on the severity of infection and eventual mortality. Using routine clinical parameters measured from patient blood we were able to predict with about 90% accuracy the progression of disease in an individual at the time of admission. Our model is available as a web application https://triage-covid-19.herokuapp.com/ and is easily accessible and deployable.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000020 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 00020&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0000020

DOI: 10.1371/journal.pdig.0000020

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().