Search Articles

View query in Help articles search

Search Results (1 to 10 of 56 Results)

Download search results: CSV END BibTex RIS


Large Language Model–Driven Knowledge Graph Construction in Sepsis Care Using Multicenter Clinical Databases: Development and Usability Study

Large Language Model–Driven Knowledge Graph Construction in Sepsis Care Using Multicenter Clinical Databases: Development and Usability Study

In this research, we aim to establish a multicenter sepsis database (MSD), providing a richer and more diverse dataset that is crucial for the in-depth analysis and understanding of sepsis. Using GPT4.0 for entity recognition and relation extraction, we aim to construct a comprehensive sepsis knowledge graph, using real-world databases supplemented by clinical guidelines and relevant public databases.

Hao Yang, Jiaxi Li, Chi Zhang, Alejandro Pazos Sierra, Bairong Shen

J Med Internet Res 2025;27:e65537

GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews

GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews

We conducted a post hoc analysis of our previous study to evaluate the performance of GPT-3.5 Turbo and GPT-4 Turbo in LLM-assisted title and abstract screening, using data from 5 clinical questions (CQs) developed for the Japanese Clinical Practice Guidelines for Management of Sepsis and Septic Shock 2024 [6,10].

Takehiko Oami, Yohei Okada, Taka-aki Nakada

JMIR Med Inform 2025;13:e64682

Investigating the Association Between Mean Arterial Pressure on 28-Day Mortality Risk in Patients With Sepsis: Retrospective Cohort Study Based on the MIMIC-IV Database

Investigating the Association Between Mean Arterial Pressure on 28-Day Mortality Risk in Patients With Sepsis: Retrospective Cohort Study Based on the MIMIC-IV Database

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection [1-3]. While mortality from sepsis has decreased over time after age standardization, it remains high [2-6]. According to the Global Burden of Disease Study, 48.9 million cases of sepsis were reported worldwide in 2017, accounting for 11 million deaths [7].

Qimin Chen, Wei Li, Ying Wang, Xianjun Chen, Dehua He, Ming Liu, Jia Yuan, Chuan Xiao, Qing Li, Lu Chen, Feng Shen

Interact J Med Res 2025;14:e63291

An AI-Based Clinical Decision Support System for Antibiotic Therapy in Sepsis (KINBIOTICS): Use Case Analysis

An AI-Based Clinical Decision Support System for Antibiotic Therapy in Sepsis (KINBIOTICS): Use Case Analysis

Sepsis infections caused by pathogens with antimicrobial resistance (AMR) represent a significant global challenge in health care [1,2]. In 2017, there were 48.9 million new cases of sepsis and 11 million deaths related to sepsis, accounting for 19.7% of all global deaths [3]. In Germany, sepsis incidence increased by an average of 5.7% per year, from 280 cases in 2010 to 370 cases in 2015 per 100,000 individuals [4].

Juliane Andrea Düvel, David Lampe, Maren Kirchner, Svenja Elkenkamp, Philipp Cimiano, Christoph Düsing, Hannah Marchi, Sophie Schmiegel, Christiane Fuchs, Simon Claßen, Kirsten-Laura Meier, Rainer Borgstedt, Sebastian Rehberg, Wolfgang Greiner

JMIR Hum Factors 2025;12:e66699

Complete Blood Count and Monocyte Distribution Width–Based Machine Learning Algorithms for Sepsis Detection: Multicentric Development and External Validation Study

Complete Blood Count and Monocyte Distribution Width–Based Machine Learning Algorithms for Sepsis Detection: Multicentric Development and External Validation Study

In addition, they are usually ordered when sepsis is clinically suspected, leading to a diagnostic delay [7] and making them unsuitable as a screening tool. The ideal biomarker for sepsis screening should have the following characteristics: (1) easy to measure, (2) high sensitivity and negative predictive value for sepsis, (3) low turn-around time, and (4) always available to clinicians, especially when sepsis is not (yet) suspected. Complete blood count (CBC) parameters fulfill all of these features [8].

Andrea Campagner, Luisa Agnello, Anna Carobene, Andrea Padoan, Fabio Del Ben, Massimo Locatelli, Mario Plebani, Agostino Ognibene, Maria Lorubbio, Elena De Vecchi, Andrea Cortegiani, Elisa Piva, Donatella Poz, Francesco Curcio, Federico Cabitza, Marcello Ciaccio

J Med Internet Res 2025;27:e55492

User-Oriented Requirements for Artificial Intelligence–Based Clinical Decision Support Systems in Sepsis: Protocol for a Multimethod Research Project

User-Oriented Requirements for Artificial Intelligence–Based Clinical Decision Support Systems in Sepsis: Protocol for a Multimethod Research Project

Treatment of the dysregulated immune response as a cause of sepsis has not been successful in large trials and subsequently has therefore not found its way into clinical practice or sepsis guidelines. AI-based CDSS could be particularly useful in sepsis care due to the high heterogeneity and complexity of the disease [10]. Non–knowledge-based respectively data-based CDSS are subject to a trade-off between model complexity and interpretability.

Pascal Raszke, Godwin Denk Giebel, Carina Abels, Jürgen Wasem, Michael Adamzik, Hartmuth Nowak, Lars Palmowski, Philipp Heinz, Silke Mreyen, Nina Timmesfeld, Marianne Tokic, Frank Martin Brunkhorst, Nikola Blase

JMIR Res Protoc 2025;14:e62704

AI-Driven Innovations for Early Sepsis Detection by Combining Predictive Accuracy With Blood Count Analysis in an Emergency Setting: Retrospective Study

AI-Driven Innovations for Early Sepsis Detection by Combining Predictive Accuracy With Blood Count Analysis in an Emergency Setting: Retrospective Study

This confirms the critical role of specific blood parameters in sepsis detection and enhances our model’s interpretability and clinical relevance. Correlation heat map of complete blood count with differential (CBC+DIFF) parameters and sepsis.

Tai-Han Lin, Hsing-Yi Chung, Ming-Jr Jian, Chih-Kai Chang, Hung-Hsin Lin, Chiung-Tzu Yen, Sheng-Hui Tang, Pin-Ching Pan, Cherng-Lih Perng, Feng-Yee Chang, Chien-Wen Chen, Hung-Sheng Shang

J Med Internet Res 2025;27:e56155

Identification of a Susceptible and High-Risk Population for Postoperative Systemic Inflammatory Response Syndrome in Older Adults: Machine Learning–Based Predictive Model

Identification of a Susceptible and High-Risk Population for Postoperative Systemic Inflammatory Response Syndrome in Older Adults: Machine Learning–Based Predictive Model

Recognizing SIRS has been a prerequisite of suspecting potential sepsis and implementing decisions such as sample culturing for the source of infection, escalating antibiotic regimens, and the level of patient monitor and care [2,3].

Haiyan Mai, Yaxin Lu, Yu Fu, Tongsen Luo, Xiaoyue Li, Yihan Zhang, Zifeng Liu, Yuenong Zhang, Shaoli Zhou, Chaojin Chen

J Med Internet Res 2024;26:e57486

The COSMOS Registry of CytoSorb Hemoadsorption Therapy in Critically Ill Patients: Protocol for an International, Prospective Registry

The COSMOS Registry of CytoSorb Hemoadsorption Therapy in Critically Ill Patients: Protocol for an International, Prospective Registry

A recent randomized controlled trial (RCT) in healthy volunteers provided definitive mechanistic evidence of Cyto Sorb’s ability to decrease systemic cytokine levels after intravenous administration of endotoxin in an established sepsis model [11].

Fabio Silvio Taccone, Frank Martin Brunkhorst, Gabriella Bottari, Jorge Hidalgo, Andreas Kribben, Jean-Louis Teboul, Dana Tomescu, Teresa Klaus, Joerg Scheier, Efthymios Deliargyris, Ricard Ferrer

JMIR Res Protoc 2024;13:e55880