Use of machine learning models to predict in‐hospital mortality in patients with acute coronary syndrome

BackgroundCardiovascular diseases are a significant health burden with the prevalence increasing worldwide. Thus, a highly accurate assessment and prediction of death risk are crucial to meet the clinical demand. This study sought to develop and validate a model to predict in‐hospital mortality among patients with the acute coronary syndrome (ACS) using nonlinear algorithms.MethodsA total of 2414 ACS patients were enrolled in this study. All samples were divided into five groups for cross‐validation. The logistic regression (LR) model and XGboost model were applied to predict in‐hospital mortality. The results of two models were compared between the variable set by the global registry of acute coronary events (GRACE) score and the selected variable set.ResultsThe in‐hospital mortality rate was 3.5% in the dataset. Model performance on the selected variable set was better than that on GRACE variables: a 3% increase in area under the receiver operating characteristic (ROC) curve (AUC) for LR and 1.3% for XGBoost. The AUC of XGBoost is 0.913 (95% confidence interval [CI]: 0.910–0.916), demonstrating a better discrimination ability than LR (AUC = 0.904, 95% CI: 0.902–0.905) on the selected variable set. Almost perfect calibration was found in XGBoost (slope of predicted to observed events, 1.08; intercept, −0.103; p < .001).ConclusionsXGboost modeling, an advanced machine learning algorithm, identifies new variables and provides high accuracy for the prediction of in‐hospital mortality in ACS patients.     

自我干预强化点检表对前列腺手术患者自护能力与心理韧性及并发症的影响

目的：自我干预强化点检表对前列腺手术患者自护能力与心理韧性及并发症的影响。方法：选取2019年5月～2021年6月在我院126例前列腺手术患者作为研究对象,按照随机数字表法分为对照组(予以常规护理干预)与观察组(在常规护理干预的基础上予以自我干预强化点检表),各63例,对比自我护理能力测定量表(ESCA)、心理韧性量表;观察并发症(尿路感染、尿道狭窄、尿潴留、尿失禁、尿频)。结果：入院时,两组患者 ESCA评分、心理韧性评分(坚韧、乐观、自强)比较差异无统计学意义;出院后3个月,观察组的ESCA评分、心理韧性评分(坚韧、乐观、自强)高于对照组。观察组患者的并发症总发生率低于对照组。结论：自我干预强化点检表有利于提高前列腺手术患者的自护能力与心理韧性,以及降低并发症发生率。     

Accelerated-strategy renal replacement therapy for critically ill patients: A systematic review and meta-analysis

Background:The aim of this study was to investigate the clinical effect and safety of accelerated-strategy initiation of renal replacement therapy (RRT) in critically ill patients.Methods:PubMed, Embase, OVID, EBSCO, and the Cochrane Library databases were searched for relevant articles from inception to December 30, 2020. Only RCTs that compared the clinical efficacy and safety between accelerated-strategy RRT and standard-strategy RRT among critically ill adult patients with acute kidney injury (AKI) were included. The primary outcome was 28-day mortality.Results:A total of 5279 patients in 12 RCTs were included in this meta-analysis. The 28-day mortality rates of patients treated with accelerated and standard RRT were 37.3% (969/2596) and 37.9% (976/2573), respectively. No significant difference was observed between the groups (OR, 0.92; 95% CI, 0.70–1.12; I² = 60%). The recovery rates of renal function were 54.5% and 52.5% in the accelerated- and standard-RRT groups, respectively, with no significant difference (OR, 1.03; 95% CI, 0.89–1.19; I² = 56%). The rate of RRT dependency was similar in the accelerated- and standard-RRT strategies (6.7% vs 5.0%; OR, 1.11; 95% CI, 0.71–1.72; I² = 20%). The accelerated-RRT group displayed higher risks of hypotension, catheter-related infection, and hypophosphatemia than the standard-RRT group (hypotension: OR, 1.26; 95% CI, 1.10–1.45; I² = 36%; catheter-related infection: OR, 1.90; 95% CI, 1.17–3.09; I² = 0%; hypophosphatemia: OR, 2.11; 95% CI, 1.43–3.15; I² = 67%).Conclusions:Accelerated RRT does not reduce the risk of death and does not improve the recovery of kidney function among critically ill patients with AKI. In contrast, an increased risk of adverse events was observed in patients receiving accelerated RRT. However, these findings were based on low quality of evidence. Further large-scale RCTs is warranted.     

表里双解法对急性湿疹患者血清IgE的影响

目的通过采用表里双解法对急性湿疹患者的治疗,以及对治疗前后血清IgE变化的观察,探讨刘完素六气怫郁化热理论在急性湿疹治疗中的运用。方法采用随机数字表法和相互对照设计方法,选取急性湿疹患者分成观察组和对照组各80例。观察组采用表里双解法治疗,方选防风通圣丸口服;对照组以3%硼酸溶液湿敷、炉甘石洗剂外搽以及安抚类乳剂外用治疗两周。两组患者治疗前及治疗1个疗程后分别取静脉血5ml,采用酶联免疫吸附法作血清IgE含量测定。结果观察组77例、对照组58例完成观察与随访过程。总有效率观察组为84.42%;对照组为51.72%。血清IgE治疗前观察组与对照组无明显差异(P>0.05),治疗后观察组明显较对照组低(P<0.05);治疗后对照组与治疗前无明显差异(P>0.05),观察组明显较治疗前低(P<0.05)。结论表里双解治疗急性湿疹可能与调节机体免疫功能有关;将刘氏的表里双解法运用于急性湿疹可以体“现火郁发之”法对“湿疮”的辨证论治的重要意义。     

TIPS术治疗的肝硬化并发EVB患者医院内死亡风险预测模型的构建与应用

目的 构建肝硬化门静脉高压症并发食管胃底静脉曲张破裂出血(EVB)患者医院内死亡的风险预测模型。方法 2018年6月～2020年6月我院收治的107例肝硬化门静脉高压症并发EVB患者,均接受经颈静脉肝内门体静脉分流术(TIPS)治疗。应用Logistic回归分析影响患者死亡的危险因素,基于独立影响因素构建医院内死亡的风险预测模型,应用Bootstrap法对预测模型进行内部验证,应用受试者工作特征曲线(ROC)下面积(AUC)评估预测模型的预测效能。结果 本组患者医院内死亡25例(23.4%),生存82例;单因素分析显示,死亡患者Child-Pugh分级、出血部位、门静脉内径、肝性脑病和失血性休克发生率等与生存患者比,均存在显著性差异(P<0.05),多因素Logistic回归分析显示,门静脉内径(OR=2.201,95%CI:1.544～3.139)、肝性脑病(OR=3.093,95%CI:1.731～5.524)和失血性休克(OR=1.101,95%CI:1.040～1.165)是影响患者医院内死亡的独立危险因素(P<0.05);对所构建的列线图预测模型,经内部验证,其C...     

急性早幼粒细胞白血病疗效随访(附78例报告)

目的评估应用不同治疗方案治疗急性早幼粒细胞白血病(APL)的近、远期疗效。方法回顾性分析78例APL患者的诱导缓解及缓解后治疗,并作5年随访分析。结果75例(96．2％)患者获得完全缓解(CR),全反式维甲酸(ATRA)治疗组(49例)和ATRA 化疗治疗组(24例)的CR率分别为95．9％和95．8％,两组间的差异无统计学意义(P>0．05)。75例达CR的患者进入缓解后治疗,应用ATRA 化疗(18例)、单用化疗序贯(48例)及大剂量阿糖胞苷(HDAE),7例)的复发率分别为66．7％、35．4％和85．7％,3组间的差异有统计学意义(P值均<0．05)。75例CR患者的1、3、5年总生存率分别为81．5％、61．8％和49．1％,无病生存期分别为78．2％、59．0％和49．1％。中位生存期为86．7个月(95％CI为66．7～106．8个月)。结论APL,诱导缓解率高,远期随访中缓解后应用化疗序贯的复发率较低。     

欧盟医疗器械上市后风险趋势分析方法研究

目的研究医疗器械上市后风险评估的统计学方法,提高风险管理的科学水平。方法参考欧盟医疗器械新法规中即将实施的趋势报告要求,探索趋势分析方法在医疗器械上市后风险评估中的实践运用,举例说明通过历史数据确定控制限和持续趋势监测的过程,讨论实践中面临的问题。结果趋势分析是科学评估医疗器械上市后风险的方法之一,适于在国内推行。结论企业可运用真实世界风险数据开展趋势分析,提升上市后风险预警能力。     

糖脂代谢紊乱相关疾病患者生活方式管理现状和研究进展

<正>近年来,国内经济生活水平逐渐提高,科学技术不断发展,带给人民富足和便捷的生活方式,导致了不健康的饮食结构和生活习惯流行,从而引起糖脂代谢紊乱相关疾病发病率增加。糖脂代谢紊乱是引起心脑血管疾病和各种代谢性疾病的危险因素。与糖脂代谢紊乱关系最为密切的糖尿病和心脑血管疾病是目前慢性非传染性疾病致死率最高的疾病[1]。其他非传染性疾病,如癌症[2],以及传染性疾病,如新型冠状病毒肺炎[3, 4]等的发生发展也受糖脂代谢紊乱的影响。     

基于治未病论治桥本病亚临床期的理论与实践

从治未病理论出发探讨"阴阳失衡"和"正虚外侵"与桥本甲状腺炎亚临床期的关系.该病亚临床期多以肝郁脾虚或兼肾虚为其病机关键,临床常伴有颈部不适感、周身乏力、情绪不宁或兼有腰膝酸软等症状.围绕既病防变的治疗理念,中医针对桥本病亚临床期进行药物干预具有独特的治疗优势.根据患者亚临床期的症状及病情转归,予疏肝健脾、补肾软坚功效...