نقش الگوریتم های یادگیری ماشین برای پیش بینی پنومونی وابسته به ونتیلاتور: بررسی سیستماتیک
کد: G-1594
نویسندگان: Kimia Abrishamifar ℗, Farid Zand, Naeimehossadat Asmarian, Somayyeh Zakerabasali *
زمان بندی: زمان بندی نشده!
برچسب: پردازش سیگنال های پزشکی
دانلود: دانلود پوستر
خلاصه مقاله:
خلاصه مقاله
Background: Ventilator-associated pneumonia (VAP) is a type of pneumonia that develops 48 hours or more after endotracheal intubation. In recent years, with a better understanding of the pathophysiology of the disease, as well as technological advances such as artificial intelligence, we have had new strategies and approaches in the prediction of VAP. The purpose of this study is to review articles about Machine learning algorithms that were applied to predict VAP. Methods: The study protocol adopted the PRISMA guidelines. A systematic review was performed using PubMed, Scopus and Web Of Science to identify articles using machine learning in English literature and published from August 2021 to December 2023. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles. Data extraction was performed independently by all investigators and included algorithms, sample size, evaluation index and features. Results: We retrieved 219 potential articles were from the 3 databases. After 2 levels of screening, only 10 articles that met our inclusion criteria were identified. The findings indicate that the most common machine learning model used was random forest algorithm (70%), which is a classification approach achieved through supervised learning. XGBoost and Logistic Regression algorithm each used in 40% of studies. The most used features for prediction are related to respiratory characteristics and laboratory results. Conclusions: ICU public datasets need to be constructed and data standardization is necessary for clinical application of machine learning in VAP prediction.
کلمات کلیدی
ArtificialIntelligence, Machinelearning, SupervisedLearning,Ventilator-associated pneumonia, VAP
