AIMS:To replicate the European subtypes of type 2 diabetes mellitus (T2DM) in the Chinese diabetes population and investigate the risk of complications in different subtypes. METHODS:A diabetes cohort using real-world patient data was constructed, and clustering was employed to subgroup the T2DM patients. Kaplan-Meier analysis and the Cox models were used to analyze the association between diabetes subtypes and the risk of complications. RESULTS:A total of 2,652 T2DM patients with complete clustering data were extracted. Among them, 466 (17.57 %) were classified as severe insulin-deficient diabetes (SIDD), 502 (18.93 %) as severe insulin-resistant diabetes (SIRD), 672 (25.34 %) as mild obesity-related diabetes (MOD), and 1,012 (38.16 %) as mild age-related diabetes (MARD). The risk of chronic kidney disease (CKD) and diabetic retinopathy (DR) were different in the four subtypes. Compared with MARD, SIRD had a higher risk of CKD (HR 2.40 [1.16, 4.96]), and SIDD had a higher risk of DR (HR 2.16 [1.11, 4.20]). The risk of stroke and coronary events had no difference. CONCLUSIONS:The European T2DM subtypes can be replicated in the Chinese diabetes population. The risk of CKD and DR varied among different subtypes, indicating that proper interventions can be taken to prevent specific complications in different subtypes.

目的 构建信息化军队药物警戒系统,强化药物安全数据的挖掘利用,促进临床安全合理用药.方法 利用数据抽取、触发器及文本分类技术逐步研发相关软件,构建起自发报告、自动监测、信息交互3个平台,并在实践应用中相辅相成、不断完善.结果 由3个平台、6个软件组成的信息化军队药物警戒系统,实现了基于军综网/互联网/局域网三网系多途径、多方式的药品不良反应数据引接、汇聚、反馈与在线查询共享,实现了相关数据来之于军、服务于军的理念;用于开展基于医院信息系统数据的临床用药风险监测评估与预警,高效快捷、精准经济.结论 基于信息化及人工智能技术支持的药物警戒系统,能够为各级药事监管决策快捷提供精准的参考数据,也是实施药物警戒制、强化药品全生命周期管理,开展大样本真实世界药物风险评价研究的高效支撑工具.

Classical B-splines based on deBoor-Cox algorithm is widely used, but its recursive calculation is time-consuming and its shape control capability still needs to be improved. To address the problem, by incorporated both core functions and Toeplitz matrix theory into the deBoor-Cox recursive formula, a novel set of basis matrix formula to calculate generalized B-splines of arbitrary order is proposed to realize the general matrix representation of three types of curves, including non-uniform generalized B-splines,uniform generalized B-splines and generalized piecewise Bézier. Furthermore, based on this general matrix, we developed the shape-controllable algorithms for curve generation and curve/surface interpolation. Experiments show that our basis matrix method outperforms classical method in terms of computational time and shape controllability for curve and surface modeling. Therefore, this novel method can further enrich the B-splines modeling theory and has good application potential.

近年来,各行各业掀起了数字化转型的浪潮.传统的信息化建设已不能满足医院高质量发展的要求,需要数字化转型为医院提供有力支撑,以驱动业务模式创新,助力医院高质量发展.本研究从定义与内涵、差异、联系等方面对医院数字化转型与信息化建设的关系进行辨析与探讨.信息化建设和数字化转型不是割裂的、对立的,而是联系的、发展的.信息化建设是数字化转型的基础,数字化转型是信息化建设的高级阶段.

BACKGROUND:Given its narrow treatment window, high toxicity, adverse effects, and individual differences in its use, we collected and sorted data on tacrolimus use by real patients with kidney diseases. We then used machine learning technology to predict tacrolimus blood concentration in order to provide a basis for tacrolimus dose adjustment and ensure patient safety.METHODS:This study involved 913 hospitalized patients with nephrotic syndrome and membranous nephropathy treated with tacrolimus. We evaluated data related to patient demographics, laboratory tests, and combined medication. After data cleaning and feature engineering, six machine learning models were constructed, and the predictive performance of each model was evaluated via external verification.RESULTS:The XGBoost model outperformed other investigated models, with a prediction accuracy of 73.33%, F-beta of 91.24%, and AUC of 0.5531.CONCLUSIONS:Through this exploratory study, we could determine the ability of machine learning to predict TAC blood concentration. Although the results prove the predictive potential of machine learning to some extent, in-depth research is still needed to resolve the XGBoost model's bias towards positive class and thereby facilitate its use in real-world settings.

The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.

目的:解决银联、微信、支付宝等第三方支付平台与医院信息系统之间自动化对账的问题.方法:分析了几种常见的对账方式,并介绍了解放军总医院对账系统的设计与实现,以及接入"军卫一号"医院信息系统的方案.结果:该对账系统在使用过程中得到不断改进优化,实现了一方面能够兼容多种支付平台,另一方面能够嵌入会计业务流程的目的.结论:对账业务作为承载支付与结算的关键环节,能够保证医院资金安全,必须在整个支付流程设计之初就得到充分的重视.

以解放军总医院为例,从网络架构、整体架构、业务流程3方面阐述医院公众号系统设计与实现,介绍系统运行情况,指出该系统有助于减少患者等候时间,优化就医流程,改善患者就医体验.

目的 探索医疗大数据时代围术期麻醉专科方向数据库的建设及应用.方法 基于本院基础医疗业务系统,利用Greenplum大数据解决方案,建立围术期麻醉专科数据库,并采用临床数据交换标准协会(Clinical Data Interchange Standards Consortium,CDISC)数据标准,实现数据标准化.结果 围术期麻醉专科数据库实现了围术期患者数据整合、治理和质量控制;并完成了专科大数据应用平台的建设.结论 围术期麻醉专科数据库将汇集多家医院的围术期医疗数据,有利于促进围术期患者信息资源的分析研究和沟通交流,在科研上发挥出1+1大于2的数据价值效应.

目的:了解我国医疗健康信息产品选型现状,发现当前行业选型的难点和需求,为推动行业发展提供依据.方法:通过网络问卷调查方式,对全国672名医疗机构信息人员进行调查,对调查数据进行统计分析.结果:目前医疗机构对于信息产品供应商和在用系统的整体满意度一般;选型时主要考虑系统稳定、功能全面以及供应商对客户的重视程度;医疗机构对于医疗健康信息产品测评机构和第三方信息发布平台的态度比较积极;行业协会的测评更受到医疗机构信赖.结论:供需双方在医疗健康信息产品选型方面均有很大的提升空间,建立科学的选型管理模式、构建专业的市场引导机制对于医疗信息化行业的健康发展十分必要.

目的:紧急实施一系列建设与保障举措,应对新冠肺炎疫情防控对医院信息化的新挑战、新要求.方法:通过通信链路、信息系统、硬件设备、安全防护的改造与升级,以及5G远程医疗新技术应用,探索形成应急综合信息保障能力.结果:综合技术手段多措并举实现了疫情防控所需的快速、高效、安全的信息保障,为临床有效救治赢得时间与效率.结论:疫情防控推动信息保障模式转变,信息化能够快速响应疫情防控变化需求,信息系统、技术与人员是医院疫情防控的重要支撑要素.

The invention discloses a method for labeling a region of interest in an ultrasonic multi-frame image, which comprises the following steps of: obtaining the ultrasonic multi-frame image which comprises a first frame image, a second frame image and a third frame image; manually generating a first annotation curve for the region of interest in the first frame image; generating a second annotation curve in the second frame image based on the translation amount of the second frame image relative to the first frame image and the first annotation curve, and in the third frame of image, if the translation amount of the third frame of image relative to the second frame of image is greater than a predetermined threshold, generating a third annotation curve based on the translation amount of the third frame of image relative to the second frame of image, the translation amount of the third frame of image relative to the first frame of image and the second annotation curve. The invention furtherprovides a device and a computer readable storage medium.

The invention discloses an anomaly positioning method, device and equipment for an image archiving communication system and a medium. The image archiving communication system is a PACS system composedof a plurality of image archiving communication PACS server sides. The method comprises the steps of: receiving medical digital imaging and communication DICOM log files from the image archiving communication PACS server sides respectively; calling a pre-constructed log information model in parallel, and processing the DICOM log file; writing the processed DICOM log file into a log database; andanalyzing based on the log database to obtain the exception analysis result of the PACS system of the multi-server architecture. According to the technical scheme provided by the embodiment of the invention, the DICOM log is subjected to parallel processing according to the log information model, so that the exception positioning efficiency of the PACS system of the multi-PACS server architectureis effectively improved.

目的:解决移动应用接入传统医院信息系统的问题.方法:设计基于医院信息系统的组件化移动应用架构,并实现了基于该架构的移动服务系统.结果:该应用架构支持多平台移动应用接入医院信息系统.结论:移动应用架构具备较高的兼容性和可扩展性,对于医院移动应用的建设具有一定借鉴意义.

目的:解放军总医院在国内大型医院中较早开展互联网服务,医院官方微信公众号是其中一个典型互联网+医疗健康应用。方法:提供了统一的互联网服务入口,建立了安全可信的网络链路,制定了标准的对外服务接口。结果:经过不断技术积累和业务实践,形成了一套独立的解决方案。结论:整个技术方案由医院自主定制和研发,信息流程制定合理,身份认证方式严谨,互联网用户和医疗数据统一可控。

目的:研究利用深度学习技术辅助门诊发药的技术可行性,利用计算机视觉技术实现药品类别和数量的自动识别.方法:采集药品外包装图像,利用预处理技术生成训练图像集,建立7层(3C3P1F)卷积神经网络模型进行训练,部署RESTful接口规范的药品图像识别服务.药师利用嵌入药品外包装识别模块的处方发药程序采集药品图像,将其传送至药品图像识别服务,将返回的药品分类与数量结果与HIS中电子处方比对,若发现信息不一致,系统向药师提示报警.结果:通过对56种药品约47万张图像进行3 000次迭代训练,训练时长12小时,预测分类准确率达到95.6％.结论:利用深度学习技术,门诊药师可借助药品外包装特征识别技术快速区分易混淆药品,及时发现药品和数量的错误信息,对降低药品错发率具有实际意义.

目的:实现解放军总医院微信公众号在应用过程中对患者进行消息推送的功能,优化患者体验,提升医院的服务水平.方法:通过分析向患者推送消息的不同场景,实现不同业务场景下的消息生成功能,布署RabbitMQ服务及消息推送服务.以医保预约取号为例介绍RabbitMQ的应用.结果:实现了不同业务场景下向不同平台的患者推送消息.结论:消息队列的应用为医院与不同平台的消息交互提供了方便,优化了患者体验,使公众号功能更加完善.

木马病毒是目前感染计算机最严重的病毒,也是黑客进行网络攻击的重要工具.木马的危害性极大,窃取用户私密信息,威胁人民财产安全.通过分析木马的攻击原理,详细阐述木马的多种隐藏方式及发现技术,采用软件Autoruns、狙剑及Fport进行木马发现仿真实验,实验表明该软件可以成功检测出自启动运行的木马,修改系统服务描述符表的木马和修改动态链接库文件的木马,为进一步清除计算机中的木马病毒奠定基础.

目的:在门诊药房发药流程中应用深度学习技术,讨论构建深度学习系统相关平台的模式与技术方案.方法:阐述药品包装识别系统工作原理,以及由训练、推理、开发管理三类平台构建深度学习系统的相关技术.结果:应用深度学习技术的药品包装识别系统现已取得初步成果,已完成对500种药品的分类识别,训练时验证准确度为96.4％.结论:深度学习平台在本系统中应用的相关技术与方法,对其他深度学习模型在医疗领域的应用有一定参考价值.

目的 从医院纷繁复杂的信息工作中厘清数据管理的具体内容,提升医院数据管理能力和管理质量.方法 结合医院数据管理实际场景,总结数据管理的任务和内容.结果 通过分析梳理医院数据管理面临的问题和实际需求,将医院数据管理分为6大任务:数据的权益管理、数据利用的技术服务与过程监管、数据的组织管理、数据的质量管理、数据的共享和价值管理,以及数据的安全管理.结论 6个数据管理任务囊括医院数据管理工作的方方面面,但面对不同的数据管理目标,不同的医院又各有侧重.