FHC dataset underlying the publication: A Customised Down-sampling Machine Learning Approach for Sepsis Prediction

The FHC dataset was collected from patients 18 years or older from the First Hospital of Changsha, China, between 2020 and 2022. The collected data contained laboratory test values and vital signs from adult ICU patients, including 69 sepsis cases and 46 non-septic cardiovascular-disease-only cases. The laboratory tests were conducted following the routine of clinical practice. The laboratory results were collected on a daily basis. The laboratory instruments and measurements are listed in the supplementary material. The items of daily laboratory tests were used as data features. The sepsis label was given by the intensivist's suspicion of onset time following the Sepsis-3 clinical criteria. Features included in the FHC dataset contain 5 vital signs, 31 laboratory values and 4 demographic information. Vital signs collected manually by nurses include temperature (Temp), heart rate (HR), systolic blood pressure (SBP) and diastolic blood pressure (DBP).  <br>The laboratory routine for gathering the measurement is stated as follows: For blood routine examination, the measurement is provided by the fully automatic blood cell analyser, Sysmex XN-2800. Specifically, the colourimetric assay is used to detect haemoglobin. For the electrolyte examination, it is provided by Mindray Global BS-820, which is used to detect the pH value. Specifically, the o-cresolphthalein complexone assay is used to detect the total calcium ions, and the enzymatic assay is used to detect potassium ions.For the liver and coagulation function examination, the enzymatic assay is used to detect bilirubin direct and bilirubin total. For the clotting, chromogenic, and immunologic examinations, STAGO STA-Compact provides the measurement including prothrombin time, activated partial thromboplastin time and Fibrinogen etc. For the blood gas analysis, a blood gas analyser, RAPIDPoint 500 System from Siemens Healthineers, is used to detect partial pressure of oxygen and partial pressure of carbon dioxide etc.<br>This study was conducted in accordance with the principles of the Declaration of Helsinki, and the study protocol was approved by the Ethics Review Committee of the First Hospital of Changsha ((2023) Ethic [Clinical paper] No. 1). Because of the retrospective nature of the study, patient consent for inclusion was waived.

FHC数据集采集自中国长沙市第一医院2020年至2022年间收治的18岁及以上患者。所采集数据涵盖成人重症监护病房（Intensive Care Unit, ICU）患者的实验室检验指标与生命体征，其中包含69例脓毒症病例与46例仅罹患心血管疾病的非脓毒症病例。实验室检验严格遵循临床常规操作流程，检测结果每日采集一次，实验室仪器与检测项目详情参见补充材料。本数据集以每日实验室检验项目作为数据特征。脓毒症标签由重症医师依据Sepsis-3临床标准结合发病时间疑似情况进行判定。FHC数据集共包含三类特征：5项生命体征、31项实验室指标与4项人口统计学信息。护士手动采集的生命体征包括体温（Temp）、心率（HR）、收缩压（SBP）与舒张压（DBP）。
各项检测的常规流程如下：血常规检测采用Sysmex XN-2800全自动血细胞分析仪完成，其中血红蛋白检测采用比色法。电解质检测采用迈瑞（Mindray）BS-820全自动生化分析仪完成，可检测pH值；其中总钙离子采用邻甲酚酞络合酮比色法检测，钾离子采用酶法检测。肝肾功能与凝血功能检测中，直接胆红素与总胆红素采用酶法检测。凝血、显色与免疫学检测采用STAGO STA-Compact全自动凝血分析仪完成，可检测凝血酶原时间、活化部分凝血活酶时间、纤维蛋白原等指标。血气分析采用西门子医疗（Siemens Healthineers）的RAPIDPoint 500 System血气分析仪完成，可检测氧分压、二氧化碳分压等指标。
本研究严格遵循《赫尔辛基宣言》的伦理原则开展，研究方案已通过长沙市第一医院伦理审查委员会批准（(2023) 伦理[临床论文] 第1号）。鉴于本研究为回顾性研究，故豁免患者的纳入知情同意。