Using artificial intelligence-based models to predict the risk of mucormycosis among COVID-19 survivors: An experience from a public hospital in India

dc.contributor.author Syed-Abdul, Shabbir
dc.contributor.author Babu, A. Shoban
dc.contributor.author Bellamkonda, Raja Shekhar
dc.contributor.author Itumalla, Ramaiah
dc.contributor.author Acharyulu, G. V.R.K.
dc.contributor.author Krishnamurthy, Surya
dc.contributor.author Ramana, Y. Venkat Santosh
dc.contributor.author Mogilicharla, Naresh
dc.contributor.author Malwade, Shwetambara
dc.contributor.author Li, Yu Chuan Jack
dc.date.accessioned 2022-03-27T02:12:25Z
dc.date.available 2022-03-27T02:12:25Z
dc.date.issued 2022-03-01
dc.description.abstract Introduction: India reported a severe public health challenge not only due to the COVID-19 outbreak but also the increasing number of associated mucormycosis cases since 2021.This study aimed at developing artificial intelligence based models to predict the risk of mucormycosis among the patients at the time of discharge from hospital. Methods: The dataset included of 1229 COVID-19 positive patients, and additional 214 inpatients, COVID-19 positive as well as infected with mucormycosis. We used logistic regression, decision tree and random forest and the extreme gradient boosting algorithm. All our models were evaluated with 5-fold validation to derive a reliable estimate of the model error. Results: The logistic regression, XGBoost and random forest performed equally well with AUROC 95.0, 94.0, and 94.0 respectively. The best accuracy and precision (PPV) were 0.91 ± 0.026 and 0.67 ± 0.0526, respectively achieved by XGBoost, followed by logistic regression. This study also determined top five variables namely obesity, anosmia, de novo diabetes, myalgia, and nasal discharge, which showed positive impact towards the risk of mucormycosis. Conclusion: The developed model has the potential to predict the patients at high risk and thus, consequently initiating preventive care or aiding in early detection of mucormycosis infection. Thus, this study, holds potential for early treatment and better management of patients suffering from COVID-19 associated mucormycosis.
dc.identifier.citation Journal of Infection. v.84(3)
dc.identifier.issn 01634453
dc.identifier.uri 10.1016/j.jinf.2021.12.016
dc.identifier.uri https://www.sciencedirect.com/science/article/abs/pii/S0163445321006393
dc.identifier.uri https://dspace.uohyd.ac.in/handle/1/4997
dc.subject Artificial intelligence
dc.subject Coronavirus
dc.subject COVID-19
dc.subject Fungal infection
dc.subject India
dc.subject Mucormycosis
dc.title Using artificial intelligence-based models to predict the risk of mucormycosis among COVID-19 survivors: An experience from a public hospital in India
dc.type Journal. Article
dspace.entity.type
Files
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: