基于多通道的ICU脑血管疾病死亡风险预测模型

死亡风险预测指根据病人临床体征监测数据来预测未来一段时间的死亡风险。对于ICU病患，通过死亡风险预测可以有针对性地对病人做出临床诊断，以及合理安排有限的医疗资源。基于临床使用的MEWS和Glasgow昏迷评分量表，针对ICU病人临床监测的17项生理参数，提出一种基于多通道的ICU脑血管疾病死亡风险预测模型。引入多通道概念应用于BiLSTM模型，用于突出每个生理参数对死亡风险预测的作用。采用Attention机制用于提高模型预测精度。实验数据来自MIMIC [Ⅲ]数据库，从中提取3?080位脑血管疾病患者的16?260条记录用于此次研究，除了六组超参数实验之外，将所提模型与LSTM、Multichannel-BiLSTM、逻辑回归（logistic regression）和支持向量机（support vector machine, SVM）四种模型进行了对比分析，准确率Accuracy、灵敏度Sensitive、特异性Specificity、AUC-ROC和AUC-PRC作为评价指标，实验结果表明，所提模型性能优于其他模型，AUC值达到94.3%。     

干扰抵消型多用户检测器性能分析

用模块化的方法描述了 ＳＩＣ、ＭＳＳＩＣ、ＰＩＣ和ＰＳＩＣ干扰抵消多用户检测算法，给出算法的实现结构图，并且在渐近有效性、抗远近效应、系统容量和实现复杂度诸方面进行了性能比较分析。分析表明需要进行功率排序的ＭＳＳＩＣ、ＰＳＩＣ和ＳＩＣ算法比ＰＩＣ算法具有更好的抗远近效应的性能，ＭＳＳＩＣ和 ＰＳＩＣ算法在渐近有效性和系统容量方面要显著强于ＳＩＣ和ＰＩＣ算法。     

重症监护病房紧急状况预警算法

重症监护病房中的病人身体状况通常很不稳定,常出现各种需要医护人员介入治疗的紧急状况。由于医疗资源有限,医护人员可能无法及时发现并处理这些紧急状况,给病人的存活率带来严重的负面影响。如果可以预测这些紧急状况的发生,并及时通知相关医护人员,将大大提高病人的存活率。常见重症监护病房紧急状况包括突然死亡、败血症、肺部感染、急性低血压、以及器官衰竭等。紧急状况预警建模主要采用病人的长时间生命体征监测数据,预测在一定时间之后发生某种紧急状况的可能性。预警模型所采用的监测数据分为静态数据、事件数据和时间序列数据等三类。静态数据具有容易采集、但预测准确性偏低的特点。事件数据或时间序列数据、以及多种类型数据的混合数据对于紧急状况预警模型的预测性能的提高有重要作用,将会获得更广泛的应用。     

ICU无线输液与监护系统的ZigBee网络

无线输液监护网络方便医生对重症病人实施各种诊疗操作,而且可以实时根据病情变化来及时调整输液治疗方案.本文构建了基于ZigBee的ICU无线输液监护系统,包括集成生理参数检测及无线收发功能的微型化传感器通信模块、星型躯域传感网、床边输液监护基站、护士中央服务器.临床实验时多个病人的心电、脉搏、血氧、呼吸四个生理参数进行连续24小时无线监护并反馈输液控制.结果表明,该网络具有稳定性高、抗干扰能力强、功耗低等特点.该研究创造性地利用ZigBee无线通信技术构建输液监护系统,打破传统的ICU诊疗模式,提高了医疗水平及对重症病人的诊疗质量.     

基于USB接口的医院ICU病房音乐治疗控制系统设计

本文阐述了目前ICU(IntensiveCareUnit)病房音乐治疗控制系统设计存在的不足,提出如何利用计算机新的USB接口技术和MP3音乐解码电路组成的多路音乐点播控制系统,具体包括该音乐治疗系统组成设计、接口电路硬件设计、驱动程序设计、MP3音乐解码电路设计和应用程序设计。     

Neutrophil to Lymphocyte Ratio: An Emerging Marker of the Relationships between the Immune System and Diseases

Over the last 10 years, the evaluation of the neutrophil-to-lymphocyte ratio (NLR) as an emerging marker of diseases has become a compelling field of bio-medical research. Although a precise and unique cut-off value has not been yet found, its role as a flag of immune system homeostasis is well established. NLR has a well-known prognostic value and independently correlates with mortality in the general population and in several specific subsets of disease (sepsis, pneumonia, COVID-19, cancer, etc.). Moreover, NLR was recently considered as part of the decision-making processes concerning the admission/recovery of patients with COVID-19 pneumonia. This review aims to provide an overview of the main use of this biomarker, focusing on the pathophysiology and the molecular basis underlying its central role as a reliable mirror of inflammatory status and adaptive immunity.     

基于表格驱动的XML配置文件解析与生成技术

XML文件作为配置文件是很多系统的首选,但是目前针对XML文件的配置信息提取与配置文件的构造技术都缺乏通用性,效率较低,扩展性很差。针对这一问题,论文提出了一种通用的基于表格驱动的XML配置文件解析与构造技术。该技术具有如下几个特征:第一,采用表格驱动,用表格来表示XML的结构信息,可实现配置信息更加严格的验证;第二,利用表格中的槽(slot)结合函数回调来提取配置信息和生成配置文件,使数据和对数据的操作分开,降低了与配置文件的耦合性,同时也使解析和构造统一化,具有高效性。第三,采用基于插件的开放式架构,通过扩展插件可以解析、生成任何复杂的配置文件,具有易扩展性;实际应用表明,论文提出的XML配置文件解析与构造技术具有通用性、易扩展性和高效性。     

一种ICU护理专家系统的设计

目的:改进ICU临床护理带教模式,以全面提高ICU护理质量。方法:以ICU护理理论、护理技能为基础,运用VB以及数据库技术,设计实现了ICU护理专家系统。结果:该系统把ICU护理中的常用理论和技能与临床护理带教有机地结合起来,ICU临床护理及带教质量得以提高。结论:现代信息技术的引入提高了护生的学习积极性,具有很好的临床应用价值,值得在ICU临床护理带教中加以推广。     

Context related artefact detection in prolonged EEG recordings

The need for reliable detection of artefacts in raw and processed EEG is widely acknowledged. Although different EEG analysis systems have been described, only few general applicable artefact recognition techniques have emerged. This paper tackles the problem of artefact detection in seven 24 h EEG recordings in the intensive care unit. ICU recordings have received less attention than, e.g. epilepsy monitoring, although recordings in this environment present an interesting application area. The EEG data used here was recorded during the difficult circumstances of an explorative ICU study. The data set includes a diverse set of EEG patterns, as well as EEG artefacts. The study investigates objective artefact detection methods based on statistical differences between signal parameters, using time-varying autoregressive modelling (AR) and Slope detection. In addition to matching the performance of artefact detection against two human observers, the study focuses on the optimal settings for context incorporation by testing the algorithms for different time windows and epoch lengths. Results indicate that a relatively short period (20–40 s) provides sufficient context information for the methods used. The combined AR and Slope detection parameters yielded good performance, detecting approximately 90% of the artefacts as indicated by the consensus score of the human observers.