AI for risk and treatment prediction of COVID-19 in inpatient settings

In collaboration with Memorial Healthcare System, researchers at Florida Atlantic University’s Christine E. Lynn College of Nursing and College of Engineering and Computer Science have developed an artificial intelligence (AI)- and machine learning (ML)-based decision support system. This system identifies critical characteristics influencing the severity of disease outcomes for patients hospitalized with Coronavirus. The researchers analysed electronic health record (eHR) data from 5,371 patients admitted to a South Florida hospital with the virus between March 2020 and January 2021, using 24 variables including sociodemographics, comorbidities, and medications. The results of the study, published in Diagnostics, show that patterns of admission to the Intensive Care Unit (ICU), ICU with mechanical ventilation, and the Intermediate Care Unit (IMCU) identified overlapping factors such as age, race, sex, body mass index (BMI), diarrhoea, diabetes, hypertension, early renal disease, and pneumonia as the most significant predictors of the three outcomes. This new approach stands out for its use of easily accessible eHR data and the combination of ML interpretability techniques with traditional statistical methods. This study highlights the potential of using AI and ML in healthcare to facilitate the development of targeted interventions by health authorities, thereby helping to mitigate epidemics and improve healthcare delivery.