Enhance Patient Safety through AI-driven Decision Support Systems for Sepsis Management: A review and future research agenda (Preprint)

Abstract

<sec> <title>BACKGROUND</title> Sepsis is a life-threatening condition where the body's reaction to infection leads to organ dysfunction. It is a significant patient safety concern, requiring prompt diagnosis and treatment to prevent complications or death. For such prevention, an AI-driven Decision Support System (DSS) may play a vital role in managing sepsis through early detection, alerting clinicians to potential cases, and facilitating prompt interventions. </sec> <sec> <title>OBJECTIVE</title> This paper reviews the existing AI-driven DSS applications in sepsis diagnosis and provides initial intervention and suitable treatment recommendations. All original literature (qualitative and quantitative) was reviewed to understand the current scope of DSS for sepsis management and to analyze existing methods used to evaluate and report the systems. </sec> <sec> <title>METHODS</title> A literature review, guided by PRISMA 2020 and supported by bibliometric analysis, was conducted in June 2024. The search utilized two electronic databases, SCOPUS and PubMed, and included articles focused on using DSS for diagnosing and managing sepsis. </sec> <sec> <title>RESULTS</title> The search strategy identified 3,470 articles, with 37 meeting the inclusion criteria. The publications spanned from 2010 to 2024, with 57% conducted in the United States. The studies primarily explored the use of AI-driven DSS for diagnosing sepsis in adults and managing its progression. Various data types, such as electronic health records, expert-derived knowledge, and clinical notes, were utilized to determine risk factors linked to sepsis. </sec> <sec> <title>CONCLUSIONS</title> Current research needs more evidence on the tangible impact of DSS in aiding healthcare providers with sepsis-related decision-making. Additional studies are required to refine the design and implementation of clinical DSS, assess their effects on clinical practices, identify barriers to adoption, and explore innovative strategies for advancing sepsis management. Improving these systems' accuracy, reliability, and usability could enhance sepsis detection, optimize treatment decisions, and ultimately save more lives in combating this deadly condition. </sec>

Ähnliche Arbeiten