Dataset Information

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

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.

SUBMITTER: Bhatia S

PROVIDER: S-EPMC9931227 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Bhatia Samarth S Makhija Yukti Y Jayaswal Sneha S Singh Shalendra S Malik Prabhat Singh PS Venigalla Sri Krishna SK Gupta Pallavi P Samaga Shreyas N SN Hota Rabi Narayan RN Gupta Ishaan I

PLOS digital health 20220309 3

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 cl ...[more]

PMID: 36812530

Similar Datasets

Project description:Abstract Epidemiological data across the United States of America illustrate health disparities in COVID-19 infection, hospitalization, and mortality by race/ethnicity. However, limited information is available from prospective observational studies in hospitalized patients, particularly for American Indian or Alaska Native (AI/AN) populations. Here, we present risk factors associated with severe COVID-19 and mortality in patients (4/2020–12/2021, n = 475) at the University of New Mexico Hospital. Data were collected on patient demographics, infection duration, laboratory measures, comorbidities, treatment(s), major clinical events, and in-hospital mortality. Severe disease was defined by COVID-related intensive care unit requirements and/or death. The cohort was stratified by self-reported race/ethnicity: AI/AN (30.7%), Hispanic (47.0%), non-Hispanic White (NHW, 18.5%), and Other (4.0%, not included in statistical comparisons). Despite similar timing of infection and comparable comorbidities, admission characteristics for AI/AN patients included younger age (P = 0.02), higher invasive mechanical ventilation requirements (P = 0.0001), and laboratory values indicative of more severe disease. Throughout hospitalization, the AI/AN group also experienced elevated invasive mechanical ventilation (P < 0.0001), shock (P = 0.01), encephalopathy (P = 0.02), and severe COVID-19 (P = 0.0002), consistent with longer hospitalization (P < 0.0001). Self-reported AI/AN race/ethnicity emerged as the highest risk factor for severe COVID-19 (OR = 3.19; 95% CI = 1.70–6.01; P = 0.0003) and was a predictor of in-hospital mortality (OR = 2.35; 95% CI = 1.12–4.92; P = 0.02). Results from this study highlight the disproportionate impact of COVID-19 on hospitalized AI/AN patients, who experienced more severe illness and associated mortality, compared to Hispanic and NHW patients, even when accounting for symptom onset and comorbid conditions. These findings underscore the need for interventions and resources to address health disparities in the COVID-19 pandemic.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets