Using Artificial Intelligence-based models to predict the risk of Mucormycosis among COVID-19 Survivors: An Experience from India

• DOI: 10.1101/2021.09.13.21263511
• Publication Date: 2021-09-16T21:55:18Z
• Authors: Shabbir Syed-Abdul; A. Shoban Babu; Raja Shekhar Bell...; Ramaiah Itumalla; GVRK Acharyulu; Surya Krishnamurthy; Y. Venkat Santosh...; Naresh Mogilicharla; Shwetambara Malwade; Yu-Chuan (Jack) Li
• Keywords: Anosmia

Abstract Introduction India reported a severe public health challenge not only due to the COVID-19 outbreak but also increasing number of associated mucormycosis cases since 2021. This study aimed at developing artificial intelligence-based models predict risk among patients time discharge from hospital. Methods The dataset included 1229 positive patients, and additional 214 inpatients, as well infected with mucormycosis. We used logistic regression, decision tree, random forest, extreme gradient boosting algorithm. All our were evaluated 5-fold validation derive reliable estimate model error. Results XGBoost, forest performed equally AUROC 95.0, 94.0, 94.0 respectively. determined top five variables namely obesity, anosmia, de novo diabetes, myalgia, nasal discharge, which showed impact on Conclusion developed has potential high thus, consequently initiating preventive care or aiding in early detection infection. Thus, this holds for treatment better management suffering