AI-based models to predict risk of mucormycosis

Hyderabad: Mucormycosis is a rare but a life-threatening fungal infection. India has been facing a public health challenge from Covid-19 related mucormycosis. A collaborative study aimed at developing artificial intelligence-based models to predict the risk of mucormycosis among the patients at the time of discharge from hospital. The dataset included 1,229 Covid-19 positive patients and 214 inpatients, positive and infected with mucormycosis.

The authors used logistic regression, decision tree, random forest, and the extreme gradient boosting algorithm. All the models were evaluated with 5-fold validation to derive a reliable estimate of the model error.

Prof Raja Shekhar Bellamkonda and Prof GVRK Acharyulu from the School of Management Studies, University of Hyderabad, India; Prof Shabbir Syed Abdul, Prof Jack and Shwetambara from Taipei Medical University, Taiwan; Prof A Shoban Babu, Dr Naresh, and Venkata Ramana from Gandhi Medical College and Hospital, Secunderabad, India; Dr Ramaiah Itumalla (did Ph.D. with Prof Raja Shekhar Bellamkonda and Prof GVRK Acharyulu), University of Hail, Saudi Arabia and Surya, Data Scientist, iQGateway, Bengaluru, Karnataka, have developed Artificial Intelligence-based models to predict the risk of mucormycosis among the patients at the time of discharge from hospital. The study was published in the Journal of Infection (an official journal of the British Infection Association), with a high impact factor of 38.63.

Prof Raja Shekhar, one of the co-authors, said that applying technology and mathematical models will be crucial for the growth of the healthcare sector. Prof Shabbir expresses that the appropriate use of Artificial Intelligence in healthcare can benefit us in this challenging pandemic situation. There is a need for more collaborative research work in the healthcare domain, Prof GVRK Acharyulu (mentor of MBA Healthcare and Hospital Management programme at SMS) added.