摘要目的 探索一种应用大数据算法筛选急救数据库中能够用于评估急诊致命性消化道院内再出血的核心指标.方法 基于解放军总医院急救数据库,应用数据检索技术,以库中明确诊断消化道出血的647例次成人患者为研究对象〔除外入院首次血红蛋白(Hb)＜90 g/L或未进行Hb化验者〕.根据入科12 h内是否输血将患者分为再出血组(存在院内致命性再出血,313例次)和未再出血组(不存在院内致命性再出血,334例次).收集患者的一般资料,包括性别、年龄、体征、血气、化验指标集合数据以及消化道再出血发病标识,综合使用粗糙集算法、遗传算法以及元胞自动机算法的融合算法,计算出影响消化道再出血的关键指标.根据筛选结果将关键指标分为生命体征关键指标、血气关键指标、血常规关键指标、凝血关键指标和生化关键指标.结果 对499项指标进行了机器融合算法计算,反复筛选5次后,共筛选出24项关键指标,其中生命体征关键指标3项,包括收缩压(SBP)、舒张压(DBP)、体温(T);血常规关键指标7项,包括白细胞计数(WBC)、嗜酸粒细胞(EOS)、单核细胞(MONO)、Hb、血细胞比容(HCT)、红细胞体积分布宽度(RDW)、平均红细胞血红蛋白量(MCH);凝血关键指标3项,包括凝血酶原时间(PT)、血浆纤维蛋白原(FIB)、血浆活化部分凝血活酶时间(APTT);生化关键指标5项,包括肌红蛋白(MYO)、氯化物(chloride)、葡萄糖(GLU)、血清白蛋白(ALB)、总胆红素(TBil);血气关键指标6项,包括pH值、乳酸(Lac)、氧饱和度(SO2)、剩余碱(BE)、碳酸氢盐(HCO3-)、动脉血二氧化碳分压(PaCO2).结论 运用大数据技术可从急救数据库中筛选出24项用于评估急诊致命性消化道院内再出血的核心指标,为临床诊断该病提供了新的思路和方法.

abstractsObjective To explore a method of screening the core indicators in the emergency database that can be used to evaluate the in-hospital fatal gastrointestinal rebleeding by using the big data algorithm. Methods Based on the emergency database of the Chinese PLA General Hospital, through the big data retrieval technology, all the 647 patients diagnosed as gastrointestinal bleeding in the emergency database were enrolled, except those who were admitted to the hospital for the first time and whose hemoglobin (Hb) was less than 90 g/L or did not undergo Hb test. Among them, there were 313 in the rebleeding group (fatal rebleeding in the hospital) and 334 in the non-rebleeding group (no fatal rebleeding in the hospital). General data of patients were collected, including gender, age, physical signs, blood gas, test index collection data, and the identification of gastrointestinal rebleeding. The fusion algorithm of rough set algorithm, genetic algorithm, and cellular automaton algorithm were used to calculate the key indicators that affect gastrointestinal rebleeding. Results A total of 499 indicators were calculated by machine fusion algorithm, after screening 5 times repeatedly, 24 key indicators were screened out, 3 of which were vital signs, including systolic blood pressure (SBP), diastolic blood pressure (DBP), temperature (T); 7 key indicators of blood routine, including white blood cell count (WBC), eosinophil (EOS), monocyte (MONO), Hb, hematocrit (HCT), red cell distribution width (RDW), mean corpuscular hemoglobin (MCH); 3 key indicators of coagulation, including prothrombin time (PT), plasma fibrinogen (FIB), activated partial thromboplastin time (APTT); 5 key indicators of biochemical, including myoglobin (MYO), chloride, glucose (GLU), serum albumin (ALB), total bilirubin (TBil); and 6 key indicators of blood gas, including pH, lactate (Lac), oxygen saturation (SO2), base excess (BE), bicarbonate (HCO3-), partial pressure of carbon dioxide (PaCO2). Conclusions Using big data technology, 24 core indicators for evaluating the fatal gastrointestinal rebleeding in hospitals can be screened out from the emergency database, providing new ideas and methods for clinical diagnosis of the disease.