Development of a machine learning model to predict risk of development of COVID-19-associated mucormycosis
Abstract
Aim: The study aimed to identify quantitative parameters that increase the risk of rhino-orbito-cerebral mucormycosis, and subsequently developed a machine learning model that can anticipate susceptibility to developing this condition. Methods: Clinicopathological data from 124 patients were used to quantify their association with COVID-19-associated mucormycosis (CAM) and subsequently develop a machine learning model to predict its likelihood. Results: Diabetes mellitus, noninvasive ventilation and hypertension were found to have statistically significant associations with radiologically confirmed CAM cases. Conclusion: Machine learning models can be used to accurately predict the likelihood of development of CAM, and this methodology can be used in creating prediction algorithms of a wide variety of infections and complications.
Plain language summary
Fungal infections caused by the Mucorales order of fungi usually target patients with a weakened immune system. They are usually also associated with abnormal blood sugar states, such as in diabetic patients. Recent work during the COVID-19 outbreak suggested that excessive steroid use and diabetes may be behind the rise in fungal infections caused by Mucorales, known as mucormycosis, in India, but little work has been done to see whether we can predict the risk of mucormycosis. This study found that these fungal infections need not necessarily be caused by Mucorales' species, but by a wide variety of fungi that target patients with weak immune systems. Secondly, we found that diabetes, breathing-assisting devices and high blood pressure states had associations with COVID-19-associated fungal infections. Finally, we were able to develop a machine learning model that showed high accuracy when predicting the risk of development of these fungal infections.
Papers of special note have been highlighted as: • of interest; •• of considerable interest
References
- 1. . Global epidemiology of mucormycosis. J. Fungi 5(1), 26 (2019). •• A brief history of mucormycosis cases globally.
- 2. . Diabetes care in India. Ann. Glob. Health 81(6), 830–838 (2015).
- 3. Mucormycosis: battle with the deadly enemy over a five-year period in India. J. Fungi 4(2), 46 (2018).
- 4. A multicentre observational study on the epidemiology, risk factors, management and outcomes of mucormycosis in India. Clin. Microbiol. Infect. 26(7), 944.e9–944.e15 (2020).
- 5. . Mucormycosis in COVID-19: a systematic review of cases reported worldwide and in India. Diabetes Metab. Syndr. 15(4), 102146 (2021). • A compilation of COVID-19-associated mucormycosis cases.
- 6. . Extreme gradient boosting as a method for quantitative structure–activity relationships. J. Chem. Inf. Model. 56(12), 2353–2360 (2016).
- 7. . Mucorales in human disease. Clin. Microbiol. Rev. 13, 236–301 (2000).
- 8. . Epidemiology and clinical manifestations of mucormycosis. Clin. Infect. Dis. 54(Suppl. 1), S23–S34 (2012).
- 9. . Mucormycosis in children: review and recommendations for management. J. Pediatric Infect. Dis. Soc. 7(2), 159–164 (2018).
- 10. Epidemiology and outcome of zygomycosis: a review of 929 reported cases. Clin. Infect. Dis. 41(5), 634–653 (2005).
- 11. Mucormycosis in renal transplant recipients: review of 174 reported cases. BMC Infect. Dis. 17(1), 283 (2017).
- 12. . Bacterial and fungal infections in COVID-19 patients: a matter of concern. Infect. Control Hosp. Epidemiol. 41(9), 1124–1125 (2020).
- 13. Rare and fatal gastrointestinal mucormycosis (zygomycosis) in a COVID-19 patient: a case report. Clinical Endosc. 53(6), 746–749 (2020).
- 14. . Rhino-orbital mucormycosis associated with COVID-19. Cureus 12(9), e10726 (2020).
- 15. . COVID-19 associated mucormycosis (CAM) in India: a formidable challenge. Br. J. Oral Maxillofac. Surg. 59(9), 1095–1098 (2021).
- 16. Mucormycosis and COVID-19: an epidemic within a pandemic in India. Mycoses 64(10), 1253–1260 (2021).
- 17. Updated insights into the T cell-mediated immune response against SARS-CoV-2: a step towards efficient and reliable vaccines. Vaccines 11(1), 101 (2023).
- 18. The double-edged sword of systemic corticosteroid therapy in viral pneumonia: a case report and comparative review of influenza-associated mucormycosis versus COVID-19 associated mucormycosis. Mycoses 64(8), 798–808 (2021).
- 19. . The recent mucormycosis storm over Indian sky. Indian J. Med. Microbiol. 39(3), 269 (2021). •• A succinct report of the COVID-19-associated mucormycosis epidemic during the COVID-19 pandemic.
- 20. Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nat. Med. 28(7), 1455–1460 (2022).
