Dataset Information

A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients.

ABSTRACT: Patients with influenza and SARS-CoV2/Coronavirus disease 2019 (COVID-19) infections have a different clinical course and outcomes. We developed and validated a supervised machine learning pipeline to distinguish the two viral infections using the available vital signs and demographic dataset from the first hospital/emergency room encounters of 3883 patients who had confirmed diagnoses of influenza A/B, COVID-19 or negative laboratory test results. The models were able to achieve an area under the receiver operating characteristic curve (ROC AUC) of at least 97% using our multiclass classifier. The predictive models were externally validated on 15,697 encounters in 3125 patients available on TrinetX database that contains patient-level data from different healthcare organizations. The influenza vs COVID-19-positive model had an AUC of 98.8%, and 92.8% on the internal and external test sets, respectively. Our study illustrates the potentials of machine-learning models for accurately distinguishing the two viral infections. The code is made available at https://github.com/ynaveena/COVID-19-vs-Influenza and may have utility as a frontline diagnostic tool to aid healthcare workers in triaging patients once the two viral infections start cocirculating in the communities.

SUBMITTER: Yanamala N

PROVIDER: S-EPMC8178379 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients.

Yanamala Naveena N Krishna Nanda H NH Hathaway Quincy A QA Radhakrishnan Aditya A Sunkara Srinidhi S Patel Heenaben H Farjo Peter P Patel Brijesh B Sengupta Partho P PP

NPJ digital medicine 20210604 1

Patients with influenza and SARS-CoV2/Coronavirus disease 2019 (COVID-19) infections have a different clinical course and outcomes. We developed and validated a supervised machine learning pipeline to distinguish the two viral infections using the available vital signs and demographic dataset from the first hospital/emergency room encounters of 3883 patients who had confirmed diagnoses of influenza A/B, COVID-19 or negative laboratory test results. The models were able to achieve an area under t ...[more]

PMID: 34088961

Similar Datasets

Project description:This study aimed to analyze vital sign characteristics of adult patients admitted at the Tertiary Hospital, and to define fever threshold and average body temperature by examining the tympanic temperatures of all patients. Retrospective medical data were extracted from 9195 patients aged > 21 years admitted to a tertiary hospital for elective surgeries between 2016 and 2020. Data regarding the patients' vital signs during their hospital stay, including tympanic body temperature, heart rate, and respiratory rate, were analyzed according to age, sex, and circadian rhythm. A normal-distribution graph was obtained when all the body temperature results were aligned. The average body temperature measured was 36.91 ± 0.45 °C (average ± standard deviation), indicating a potential fever threshold of 37.81 °C. When the participants were divided into age groups, the average temperature, heart rate, and respiratory rate exhibited parabolic trends. Patients in their 60s exhibited the lowest average temperature (36.88 °C), whereas those in their 50s had the lowest average heart rate (75.82/min) and lowest respiratory rate (19.08/min). Heart rate and respiratory rate tended to increase in elderly people older than 81 years. The average body temperature was greater in women than in men (36.94 ± 0.42 °C vs. 36.89 ± 0.47 °C), while the average heart (75.53 ± 10.04/min vs. 77.31 ± 11.52/min) and respiratory rates (19.13 ± 1.39/min vs. 19.29 ± 2.24/min) were lower in women than in men respectively. According to the time of measurement, the average temperature and heart rate appeared to follow a sinusoidal pattern, suggesting that the circadian rhythm was highest at 1 a.m. and lowest at 8 a.m. Tympanic temperature is a convenient measurement method preferred in hospital settings because it is noninvasive and easier to measure compared to other body parts. To develop an improved device and measurement method in the future, it is necessary to analyze tympanic temperature big data and compare it with past vital sign data or biometric information from other body parts.

Dataset Information

A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients.

Publications

A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets