Sepsis is a life-threatening condition in the ICU and requires treatment in time. Despite the accuracy of existing sepsis prediction models, insufficient focus on reducing alarms could worsen alarm fatigue and desensitisation in ICUs, potentially compromising patient safety. In this retrospective study, we aim to develop an accurate, robust, and readily deployable method in ICUs, only based on the vital signs and laboratory tests. Our method consists of a customised down-sampling process and a specific dynamic sliding window and XGBoost to offer sepsis prediction. The down-sampling process was applied to the retrospective data for training the XGBoost model. During the testing stage, the dynamic sliding window and the trained XGBoost were used to predict sepsis on the retrospective datasets, PhysioNet and FHC. With the filtered data from PhysioNet, our method achieved 80.74% accuracy (77.90% sensitivity and 84.42% specificity) and 83.95% (84.82% sensitivity and 82.00% specificity) on the test set of PhysioNet-A and PhysioNet-B, respectively. The AUC score was 0.89 for both datasets. On the FHC dataset, our method achieved 92.38% accuracy (88.37% sensitivity and 95.16% specificity) and 0.98 AUC score on the test set of FHC. Our results indicate that the down-sampling process and the dynamic sliding window with XGBoost brought robust and accurate performance to give sepsis prediction under various hospital settings. The localisation and robustness of our method can assist in sepsis diagnosis in different ICU settings.

Qinhao Wu

Fei Ye

Qianqian Gu

Feng Shao

Xi Long

Zhuozhao Zhan

Junjie Zhang

Jun He

Yangzhou Zhang

Quan Xiao

International Journal of Medical Informatics

国际医学信息学杂志为传播有关医学信息学领域的原始结果和解释性评论提供了一个国际媒体。该杂志强调医疗环境中系统的评估。期刊范围涵盖：信息系统，包括国家或国际注册系统、医院信息系统、科室和/或医生办公系统、文件处理系统、电子病历系统、标准化、系统集成等；使用启发式、算法和/或统计方法的计算机辅助医疗决策支持系统，如决策理论、协议开发、人工智能等。与医学信息学或医学有关的基于计算机的教育程序； IT 应用在医疗保健中的组织、经济、社会、临床影响、伦理和成本效益方面。

The International Journal of Medical Informatics serves as an international platform for disseminating original research findings and interpretative reviews in the field of medical informatics. The journal places a strong emphasis on the systematic evaluation of systems within healthcare settings. Its scope includes: information systems such as national or international registries, hospital information systems, departmental and/or physician office systems, document processing systems, electronic medical record systems, standardization, and system integration; computer-aided medical decision support systems utilizing heuristic, algorithmic, and/or statistical methods, including decision theory, protocol development, and artificial intelligence; computer-based educational programs related to medical informatics or medicine; and the organizational, economic, social, clinical impacts, ethics, and cost-effectiveness of IT applications in healthcare.

国际医学信息学杂志是一个国际性媒体，旨在传播医学信息学领域的原创研究成果和解释性评论。该杂志特别强调在医疗环境中对系统的评估。期刊的范围涵盖：信息系统，包括国家或国际注册系统、医院信息系统、科室和/或医生办公系统、文档处理系统、电子病历系统、标准化、系统集成等；使用启发式、算法和/或统计方法的计算机辅助医疗决策支持系统，如决策理论、协议开发、人工智能等；与医学信息学或医学相关的基于计算机的教育项目；以及信息技术在医疗保健中的组织、经济、社会、临床影响、伦理和成本效益方面的应用。

A customised down-sampling machine learning approach for sepsis prediction

The results indicate that the down-sampling process and the dynamic sliding window with XGBoost brought robust and accurate performance to give sepsis prediction under various hospital settings.

Category	Quartile
医学	2
医学, 计算机信息系统	2
医学, 卫生保健与服务	2
医学, 医学信息	3

A customised down-sampling machine learning approach for sepsis prediction

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
MEDICAL INFORMATICS	2