Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Abstract Background Machine learning (ML) is increasingly used in many areas of healthcare. Its use in infection management is catching up as identified in a recent review in this journal. We present a complementary review to this work. Objectives To support clinicians and researchers to navigate through the methodological aspects of ML approaches in the field of infection management. Sources A Medline search with the keywords artificial intelligence, machine learning, infection*, and infectious disease* for the years 2014 to 2019 was performed. Studies using routinely available electronic hospital record data from an inpatient setting with a focus on bacterial and fungal infections were included. Content Fifty-two studies were included and divided into six groups based on their focus. These studies covered detection/prediction of sepsis (n=19), hospital-acquired infections (n=11), surgical site infections and other postoperative infections (n=11), microbiological test results (n=4), infections in general (n=2), musculoskeletal infections (n=2), and other topics (urinary tract infections, deep fungal infections, antimicrobial prescriptions; n=1 each). In total, 35 different ML techniques were used. Logistic regression was applied in 18 studies followed by random forest, support vector machines, and artificial neural networks in 18, 12, and 7 studies, respectively. Overall, the studies were very heterogeneous in their approach and their reporting. Detailed information on data handling and software code was often lacking. Validation on new datasets and/or in other institutions was rarely done. Clinical studies on the impact of ML in infection management were lacking. Implications Promising approaches of ML use in infectious diseases were identified. But building trust in these new technologies will require improved reporting. Explainability and interpretability of the used models was rarely addressed and should be further explored. Independent model validation and clinical studies evaluating the added value of ML approaches are needed.