Systematic Review of Artificial Intelligence Implementations in Central Nervous System Infections

Introduction: Despite the increasing use of machine learning (ML) in the early diagnosis and determining risk factors of various infections, a few studies investigate using ML in central nervous system infections (CNSI).Materials and Methods: A literature search was performed with using the keywords ``Artificial intelligence" OR "Machine learning" OR "Deep learning" AND "Central nervous system infection" OR "Encephalitis" OR "Meningitis" in Scopus, Web of Science, PubMed via Ovid electronic databases.The last update was performed on July 20, 2022.Studies have been selected according to the Population, Intervention, Comparator, Outcome(s) of interest, and Study design (PICOS).For quality control of studies, the Joanna Briggs Institute (JBI) Cohort Studies and Case Control Research Checklist were used.The study population was defined as adolescent and adult patients with a diagnosis of CNSI confirmed by cerebrospinal fluid testing or other laboratory examination and imaging methods.Results: Five of the 731 determined articles were included.The studies have focused on the role of ML in the following issues; risk factors for healthcareassociated ventriculitis/meningitis, assessing treatment failure in spinal epidural abscess (SEA) patients who were treated with medical treatment without surgery, prediction of mortality in the SEA, differential diagnosis of meningitis, comparison of ML methods and clinician's decisions in the differential diagnosis.Conclusions: Based on the current literature, although more studies are needed in this area, ML can be used effectively soon in CNSI.It is essential to determine the best ML model for each issue.AI applications offer great potential to contribute to rapid diagnosis and effective early treatment.