Background and aims: The use of artificial intelligence in medicine has grown significantly inthe past decades. Machine learning (ML) is a branch of artificial intelligence that can improve theefficiency and quality of health care by helping to improve the prognosis and diagnosis of diseases.Meningitis is an inflammatory disease that is one of the world’s major health problems, andthe mortality rate caused by this disease is always high. This systematic review aimed to evaluateML algorithms in the prediction, diagnosis, and prevalence of meningitis.Method: This systematic review was conducted by searching keywords in the authoritative scientificdatabases PubMed, Scopus, EMBASE, and Web of Science on November ۱۲, ۲۰۲۲. We followedthe Preferred Reporting for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.English-language studies that used ML to predict, estimate prevalence, and diagnose meningitiswere considered to meet inclusion criteria. Titles and abstracts were independently screened basedon the eligibility criteria. Afterward, complete texts were retrieved and independently screenedbased on the eligibility criteria. The same form was used to extract the following data: the titleof the study, the year of publication, the country, the number of participants, ML algorithms, thetype of meningitis considered in the study, the objectives of the study, and the main findings ofthe study.Results: In total, ۱۶ studies met the inclusion criteria and were included in this systematic review.Studies on the application of ML algorithms in the three categories of disease diagnosis ability(۸/۱۶), disease prevalence investigation (۱/۱۶), and disease prediction ability (including casesrelated to identifying patients (۳/۱۶), risk of death in patients (۲/۱۶), the consequences of the diseasein childhood (۱/۱۶), and its etiology (۱/۱۶)) were placed. Among the ML algorithms used inthis study, the random forest approach (۳/۱۶, ۱۹%) and artificial neural network (۳/۱۶, ۱۹%) werethe most used. All the included studies indicated improvements in the processes of diagnosis,prediction, and disease outbreak with the help of ML algorithms.Conclusion: The results of the present systematic review showed that in all studies, ML techniqueswere an effective approach to facilitate diagnosis, predict outcomes for risk classification,and improve resource utilization by predicting the volume of patients or services as wellas discovering risk factors; The role of ML algorithms in improving disease diagnosis was moresignificant than disease prediction and prevalence. Meanwhile, the use of combined methods canoptimize differential diagnoses and facilitate the decision-making process for doctors.