Machine learning (ML) has been employed by researchers from the University of Queensland, Australia, to assist in predicting the likelihood of subsequent bacterial infections in hospitalized Covid-19 patients. The machine learning technique can assist in determining whether the administration of antibiotics is necessary for patients with these diseases, according to a study published in the journal The Lancet Microbe.
According to Dr. Kirsty Short, an associate professor at the University of Queensland, “estimates of the incidents of secondary bacterial infections in Covid-19 patients are broad, but in some studies, 100% of fatal cases have suffered a bacterial co-infection.” “To reduce the risk of bacterial co-infections, it would be theoretically possible to just treat all Covid-19 patients with antibiotics,” she stated.
But Short pointed out that there’s a chance that overusing antibiotics could result in antibiotic resistance and the emergence of superbugs in bacteria. “We’ve helped develop a robust predictive model to determine the risk of bacterial infections in Covid-19 patients, facilitating a careful use of antibiotics,” she stated. The “least absolute shrinkage and selection operator,” or LASSO, is the method’s name.
Blood samples from six different countries with Covid-19 patients were evaluated using LASSO. According to the study, seven genes’ expression in a Covid-19 patient can predict the patient’s probability of contracting a subsequent respiratory bacterial infection within 24 hours of hospital admission. Dr. Meagan Carney, a lecturer at the University of Queensland, said, “This data raises the exciting possibility that gene transcription and analysis at the time of clinical presentation at a hospital, together with machine learning, can change the game for antibiotic prescription.” She also mentioned how LASSO is less complicated than the sophisticated machine learning techniques being spoken about in the media in relation to artificial intelligence.
