Constructing a Model-Based Software Monitor for the Insulin Pump Behavior

Modern medical systems undertaking the task of surveillance of patients are safety-critical systems steered by software. Such systems will bring man’s life into hazard if they fail to meet patients’ requirements; so, adequate reliability of the algorithms and computations used by software of such systems is a matter of concern. The environment of a medical safety-critical system consisting of a patient has safety requirements that should be satisfied by the system. A safety requirement is the one that if it is violated, the system environment will be subject to severe risk. An effective method to verify the algorithms and computations used by software of such systems against safety requirements is to keep the software under surveillance at run-time. This paper aims to present a model-based method to construct a run-time monitor for a safety-critical medical system called Continuous Infusion Insulin Pump (CIIP).     

Using Machine Learning Classifiers to Assist Healthcare-Related Decisions: Classification of Electronic Patient Records

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.     

UML视图的一种形式化模型及其分析

UML是一种得到广泛应用的系统建模语言，但是由于它缺乏形式化语义和严格的推理机制，从而影响了系统建模的准确性和开发效率。TCOZ是一种将Object—Z和TCSP相结合的形式化语言，具有丰富的建模能力。基于TCOZ，本文建立了UML视图的一种形式化模型，对类图和协作图等提出了转换规则，使得TCOZ中的推理可用于分析UML视图。通过某学校信息系统的实例，阐述了UML视图的形式化建模方法和分析技术。     

A user-oriented computer interface for health professionals

One of the characteristics of medical information systems, which have been most successful in being integrated into the patient care process, is a cordial type of human interface that embodies a form of input/output generator software coupled with a terminal device that facilitates the selection of input data elements from lists or “menus.” This paper reviews the nature of this involvement in patient care and describes this interface in greater detail, illustrating its intrinsic value as an appropriate human-computer interface for use by medical professionals. As with any successful management information system, a medical information system's use will ultimately be a function of the ease with which it can be incorporated into the decision-maker's (manager's) daily activity. Watson has shown that physicians, after a long orientation period, are willing to use a CRT device that presents information in a convenient manner and allows the input of new data by means of selections from tree-structured lists instead of typing. A technique more natural than the use of a light pen is to simply touch a selection with one's finger. For this reason, our hardware terminal device consists of a 15-inch diagonal CRT with 24 80-character lines activated by the touch of a finger, which passes a direct digital signal to the controlling software for appropriate action. The accompanying software described is best characterized as a nonprocedural “higher level language,” or a “meta language”, designed specifically to process frames of CRT information in such a way as to eliminate much of the inevitable programming modification process. Such a capability takes on the characteristics of a “tool” by which the non-computer-oriented professional actually creates application programs that best serve his own needs. The user is able to concentrate on thewhat of using the computer rather than thehow. The software automatically determines thehow. Its use is not limited to just the presentation of the frames but also involves a method of allowing the user to link these with each other, and with parameter tables in a user-logical fashion. In addition, the frames can be readily modified. The selected parameter becomes data that the application program processes. By means of such an optimum combination of software and hardware, the user exerts significant control over that portion of the system that he interfaces with most directly. This approach also offers considerable flexibility in the design of a system so that it can be changed as the user's needs and expectations grow. The need to reflect the user's requirements in input sequence and method of presentation has been shown to be of particular importance in the design of systems that are expected to be used by health professionals. The details of the software supporting such a technique have been described.     

A Novel User Authentication and Key Agreement Protocol for Accessing Multi-Medical Server Usable in TMIS

Telecare Medical Information System (TMIS) makes an efficient and convenient connection between patient(s)/user(s) at home and doctor(s) at a clinical center. To ensure secure connection between the two entities (patient(s)/user(s), doctor(s)), user authentication is enormously important for the medical server. In this regard, many authentication protocols have been proposed in the literature only for accessing single medical server. In order to fix the drawbacks of the single medical server, we have primarily developed a novel architecture for accessing several medical services of the multi-medical server, where a user can directly communicate with the doctor of the medical server securely. Thereafter, we have developed a smart card based user authentication and key agreement security protocol usable for TMIS system using cryptographic one-way hash function. We have analyzed the security of our proposed authentication scheme through both formal and informal security analysis. Furthermore, we have simulated the proposed scheme for the formal security verification using the widely-accepted AVISPA (Automated Validation of Internet Security Protocols and Applications) tool and showed that the scheme is secure against the replay and man-in-the-middle attacks. The informal security analysis is also presented which confirms that the protocol has well security protection on the relevant security attacks. The security and performance comparison analysis confirm that the proposed protocol not only provides security protection on the above mentioned attacks, but it also achieves better complexities along with efficient login and password change phase.     

Improving the Reliability of Medical Software by Predicting the Dangerous Software Modules

Software reliability analysis is inevitable for modern medical systems, since a large amount of medical system functionality is now dependent on software, and software does contribute to system failures. Most software reliability models are based on software failure data collected from the project. This creates a problem for the designers since, during the early stage, software failure data are not available. However, a valuable knowledge can be learned from the analysis of previous projects and applied to the new ones. This paper presents the approach that predicts the potentially dangerous software modules under development based on the analysis of the already finished modules using the machine-learning techniques. On the basis of the prediction given by our method software designers are able to devote more testing effort to the dangerous parts of the system, which results in a more reliable medical software system.     

一种实用的中医知识表达语言TCMKRL及专家系统生成环境TCM-ES-GE

介绍一种新型的中医知识表达语言TCMKRL.这种语言将有利于中医专家系统知识获取这一瓶颈问题的解决,而且能够被中医师掌握和运用。所开发的专家系统生成母机是按计算机辅助软件工程原则设计的强有力的软件工具,使专家系统批量化生产成为可能.     

Runtime Verification of Pacemaker Functionality Using Hierarchical Fuzzy Colored Petri-nets

Today, implanted medical devices are increasingly used for many patients and in case of diverse health problems. However, several runtime problems and errors are reported by the relevant organizations, even resulting in patient death. One of those devices is the pacemaker. The pacemaker is a device helping the patient to regulate the heartbeat by connecting to the cardiac vessels. This device is directed by its software, so any failure in this software causes a serious malfunction. Therefore, this study aims to a better way to monitor the device’s software behavior to decrease the failure risk. Accordingly, we supervise the runtime function and status of the software. The software verification means examining limitations and needs of the system users by the system running software. In this paper, a method to verify the pacemaker software, based on the fuzzy function of the device, is presented. So, the function limitations of the device are identified and presented as fuzzy rules and then the device is verified based on the hierarchical Fuzzy Colored Petri-net (FCPN), which is formed considering the software limits. Regarding the experiences of using: 1) Fuzzy Petri-nets (FPN) to verify insulin pumps, 2) Colored Petri-nets (CPN) to verify the pacemaker and 3) To verify the pacemaker by a software agent with Petri-network based knowledge, which we gained during the previous studies, the runtime behavior of the pacemaker software is examined by HFCPN, in this paper. This is considered a developing step compared to the earlier work. HFCPN in this paper, compared to the FPN and CPN used in our previous studies reduces the complexity. By presenting the Petri-net (PN) in a hierarchical form, the verification runtime, decreased as 90.61% compared to the verification runtime in the earlier work. Since we need an inference engine in the runtime verification, we used the HFCPN to enhance the performance of the inference engine.     

基于TCOZ的UML用例图的形式化模型

基于TCOZ，本文建立了UML视图的一种形式化模型，不仅为UML提供了一种精确的数学描述，也为其正确性分析和验证奠定了基础。     

LEMMA: A Language for Easy Medical Models Analysis

The quality of health care systems and processes is becoming a prominent problem and more and more efforts are devoted to define methodologies and tools to measure and assure quality of care. New methods are required to optimize health care processes to guarantee high quality standards within (limited) available resources. Resource optimizations able to preserve the quality of treatments require good models of medical processes. This paper presents LEMMA, a new notation to model medical processes. LEMMA provides physicians with intuitive graphical elements to design their models. At the same time a high level timed Petri net corresponding to the designed model is built automatically. In this way, LEMMA models are ascribed formal semantics and can be executed and analyzed automatically. The dual language approach followed in this paper allows physicians to gain all the benefits of formal methods without being proficient in them. Medical users manage simple graphical elements, while Petri nets ensure formality and validation capabilities. In this way LEMMA mixes formal and informal notations, overcoming the problems of both the approaches. The definition of the notation has been supported by the development of an environment to design LEMMA models. The environment, besides letting us experiment with the notation, has been employed to define and analyze real case studies.     

Recognizing Obesity and Comorbidities in Sparse Data

In order to survey, facilitate, and evaluate studies of medical language processing on clinical narratives, i2b2 (Informatics for Integrating Biology to the Bedside) organized its second challenge and workshop. This challenge focused on automatically extracting information on obesity and fifteen of its most common comorbidities from patient discharge summaries. For each patient, obesity and any of the comorbidities could be Present, Absent, or Questionable (i.e., possible) in the patient, or Unmentioned in the discharge summary of the patient. i2b2 provided data for, and invited the development of, automated systems that can classify obesity and its comorbidities into these four classes based on individual discharge summaries. This article refers to obesity and comorbidities as diseases. It refers to the categories Present, Absent, Questionable, and Unmentioned as classes. The task of classifying obesity and its comorbidities is called the Obesity Challenge.The data released by i2b2 was annotated for textual judgments reflecting the explicitly reported information on diseases, and intuitive judgments reflecting medical professionals' reading of the information presented in discharge summaries. There were very few examples of some disease classes in the data. The Obesity Challenge paid particular attention to the performance of systems on these less well-represented classes.A total of 30 teams participated in the Obesity Challenge. Each team was allowed to submit two sets of up to three system runs for evaluation, resulting in a total of 136 submissions. The submissions represented a combination of rule-based and machine learning approaches.Evaluation of system runs shows that the best predictions of textual judgments come from systems that filter the potentially noisy portions of the narratives, project dictionaries of disease names onto the remaining text, apply negation extraction, and process the text through rules. Information on disease-related concepts, such as symptoms and medications, and general medical knowledge help systems infer intuitive judgments on the diseases.     

新型农村合作医疗跨地区实时结算系统建设实践

由于各个县市新型农村合作医疗信息系统是不同软件公司开发,参保病人在其它地方看病不能跨地区结算。介绍通过系统集成技术、网络技术、软件系统开发,组织完成了新型农村合作医疗9个跨县（市、区）实时结算管理系统的建设。基本解决了临海市新农合参合农民“报销难、报销烦”问题。     

基于Petri网的嵌入式系统失效模型与分析

针对嵌入式系统的特点,提出一种基于Petri网的嵌入式系统失效模型与分析方法。依据嵌入式系统失效需求,采用Petri网建立嵌入式系统的形式化描述语言,并对嵌入式系统中的基本元素,如任务、资源、传感器、执行器等进行描述。构造任务间基本关系、任务与设备间交互的模型,并利用组合规则将这些模型动态地集成为一个完整的嵌入式系统失效模型。基于模型的运行特征和状态空间,分析模型的正确性。最后,应用具体实例模拟嵌入式系统失效模型与分析过程,验证了该方法的有效性。     

民国时期中国高等西医学教育的简要评述

民国时期中国高等西医学教育主要存在有教会、政府和私人三种办学主体。在此期间，西医教育实现了在中国的本土化，我国崖立了现代医学教育体系。该段时期积累的办学经验对当今高等教育有着如下启示：兼容并包，多元办学模式并存；联合办学，平衡教育资源；完善立法，加强监督引导等。我们应借鉴这些宝贵经验，促进我国高等教育的发展并逐步走向辉煌。     

Predicting hospital-associated mortality for Medicare patients. A method for patients with stroke, pneumonia, acute myocardial infarction, and congestive heart failure

We created a microcomputer-based system that uses characteristics of the patient at admission to predict death within 30 days of hospital admission for Medicare patients with stroke, pneumonia, myocardial infarction, and congestive heart failure. These conditions account for 13% of discharges and 31% of 30-day mortality for Medicare patients over 64 years of age. The system was calibrated on a stratified, random sample of 5888 discharges (about 1470 for each condition) from seven states, with stratification by hospital type to make the sample nationally representative. The predictors must be specially abstracted from the medical record. The cross-validated R2 for predictions is 0.14 to 0.25, which is better than the values for other systems for which we have data. Risk-adjusted predicted group mortality rates may be useful in interpreting information on unadjusted mortality rates, and patient-specific predictions may be useful in identifying unexpected deaths for clinical review.     

我国医药代表职业规范化管理的探讨

针对我国医药代表存在的问题,通过比较分析国内外医药代表管理的现状,探讨国内医药代表职业规范化管理存在的问题,并提出深化医改、加强药品流通和使用监管;强化医药代表专业培训,推广医药代表专业认证制度;建立有针对性的法律规章制度,规范医药代表职业行为;拓宽宣传路径,提高医药代表资源利用效率等对策建议。     

Mayo Clinic NLP System for Patient Smoking Status Identification

This article describes our system entry for the 2006 I2B2 contest “Challenges in Natural Language Processing for Clinical Data” for the task of identifying the smoking status of patients. Our system makes the simplifying assumption that patient-level smoking status determination can be achieved by accurately classifying individual sentences from a patient’s record. We created our system with reusable text analysis components built on the Unstructured Information Management Architecture and Weka. This reuse of code minimized the development effort related specifically to our smoking status classifier. We report precision, recall, F-score, and 95% exact confidence intervals for each metric. Recasting the classification task for the sentence level and reusing code from other text analysis projects allowed us to quickly build a classification system that performs with a system F-score of 92.64 based on held-out data tests and of 85.57 on the formal evaluation data. Our general medical natural language engine is easily adaptable to a real-world medical informatics application. Some of the limitations as applied to the use-case are negation detection and temporal resolution.     

医院信息系统中电子病历的建设

电子病历是指计算机化的病历，它建立在医院医疗活动全面信息化的基础上。发展电子病历系统是计算机应用向临床发展的需要。本文通过对软件系统边实施边总结的方法，概述了系统的功能与特点、新旧系统的对比及具体实施要求。     

Healthcare Blockchain System Using Smart Contracts for Secure Automated Remote Patient Monitoring

As Internet of Things (IoT) devices and other remote patient monitoring systems increase in popularity, security concerns about the transfer and logging of data transactions arise. In order to handle the protected health information (PHI) generated by these devices, we propose utilizing blockchain-based smart contracts to facilitate secure analysis and management of medical sensors. Using a private blockchain based on the Ethereum protocol, we created a system where the sensors communicate with a smart device that calls smart contracts and writes records of all events on the blockchain. This smart contract system would support real-time patient monitoring and medical interventions by sending notifications to patients and medical professionals, while also maintaining a secure record of who has initiated these activities. This would resolve many security vulnerabilities associated with remote patient monitoring and automate the delivery of notifications to all involved parties in a HIPAA compliant manner.