The Role of Machine Learning Algorithms in Sepsis Diagnosis: A Retrospective Overview using Bibliometric Analysis

Machine learning has great potential to extract meaningful information from large data sets and build powerful predictive models for disease diagnosis. The aim of this study is to conduct a comprehensive review of the role of machine learning algorithms in sepsis diagnosis. The research was conducted using the bibliometric analysis method. Within the scope of the research, an advanced search query was created in the Web of Science (WoS) Core Collection database and WoS index Science Citation Index Expanded (SCI-Exp), publication type article, publication language English, open access publications published between 2000 and 2024 were included. In the WoS database, 277 publications were accessed using an advanced search query created with the relevant keywords on 05.07.2024. After excluding 87 non-English publications that did not include sepsis and machine learning, 190 publications were analyzed. In the treemap obtained in bibliometric analysis, the first five keywords include sepsis, machine learning, intensive care units, mortality, and artificial intelligence, respectively. China led in publication count, whereas the USA boasted the most cited publications. "Frontiers in Medicine" featured the highest number of articles, while "Critical Care Medicine" contained the most cited ones. According to the analysis of articles published, the use of artificial intelligence and machine learning in sepsis diagnosis has significant potential, especially in intensive care units. These technologies show promise in early diagnosis, disease classification, and prognosis prediction. Expanding research collaborations and a growing publication focus on key themes suggest continued growth in this research area.