مدلهای یادگیری ماشینی برای پیشبینی مالاریا با استفاده از دادههای بالینی: مروری سیستماتیک
کد: G-1122
نویسندگان: Yasamin Ahmadi ℗, Ali Jamshidi ©, Marziye Doraghi, Amir Mohammad Chekeni
زمان بندی: زمان بندی نشده!
دانلود: دانلود پوستر
خلاصه مقاله:
خلاصه مقاله
Introduction: As one of the most essential infectious diseases in tropical and subtropical areas, malaria is still a primary project for global health. Early diagnosis and prediction of this ailment can assist enhance remedy control and decrease mortality. In current years, machine gaining knowledge of fashions have received attention as a brand new technique in predicting sicknesses together with malaria because of their correct and speedy prediction competencies. The goal of this evaluation is to systematically examine current research on the use of system getting to know models to expect malaria the usage of clinical records. Method: A systematic review was performed independently by two people based on the PICO criteria and aligned to the research objective and based on the PRISMA checklist and using PubMed, Medline, Cochrane, Sciencedirect, SID databases Google Scholar search engine, and Boolean operators. The time limit between 2019 and 2024 was determined using the MESH keywords " Machine Learning”, “Malaria “ and “Prediction”. After checking the entry and exit criteria and critically evaluating the quality of the selected articles, a total of 8 articles were included in the study. Results: inspecting the effects of studies indicates that machine getting to know fashions, particularly algorithms based on deep mastering, have considerable overall performance in as it should be predicting malaria. Extra complicated algorithms, together with deep and reinforcement neural networks, had been able to extract complex capabilities from medical statistics and feature furnished widespread development in prediction accuracy as compared to less complicated models along with decision trees. But, some boundaries, such as the shortage of general statistics and obstacles inside the generalizability of the results to special populations, have nevertheless created demanding situations. Conclusion: This study suggests the importance of the use of machine getting to know inside the prognosis and prediction of malaria and indicates that destiny research have to develop models that, similarly to excessive accuracy, also can be generalized to exclusive geographic areas and populations. Also, the need for extremely good and standardized scientific information is felt to improve the performance of predictive fashions on a worldwide scale.
کلمات کلیدی
Machine Learning ,Machine Learning , Prediction
