Design should help use of patients' data

Checklists and other tools help doctors to use published evidence in clinical practice. Two other important sources of evidence, however, are the patient and his or her medical record. This series aims to advance the practice of evidence-based medicine by helping in redesign of medical records, drawing on insights from psychology, information design, and medical informatics; and by promoting changes analogous to those occurring in the medical literature. The four papers look at: the uses of medical records and importance of organising them so doctors can use the data they contain; different methods doctors use to search for data and how design of records can help or hinder these approaches; how we interpret data once found, and how record formatting assists this process; and the issues raised by computerisation of records.     

Transition to a computer-based record using scannable, structured encounter forms

OBJECTIVE: To evaluate the quality of documentation and user satisfaction with a structured documentation system for pediatric health maintenance encounters, using scanned paper-based forms to generate an electronic medical record. DESIGN: (1) A retrospective medical record review comparing 16 structured (ST) records with 16 contemporaneously created unstructured records, (2) a questionnaire evaluation of user satisfaction, and (3) an electronic records review of patients seen 1 year following the full implementation of the system to evaluate persistence of the effect. SETTING: The Yale-New Haven Hospital Pediatric Primary Care Center, New Haven, Conn, an inner-city clinic in an academic center. PARTICIPANTS: (1) A random sample of 16 health maintenance records completed by first- and second-year residents in February 1996 matched for patient's age and provider training level with 16 contemporaneously documented visits, (2) 16 of 18 pediatric level 1 residents and 14 of 16 pediatric level 2 residents who completed questionnaires, and (3) all electronic records of health maintenance visits during February 1997. MAIN OUTCOME MEASURES: The number of data elements documented and the percentage of records that record specific components of the health maintenance encounter. User satisfaction was specified on a Likert scale. RESULTS: Overall, residents in the ST records group documented more data elements per visit than did those in the unstructured records group. The number of developmental items documented was 11.5 per visit in the ST records group and 4.8 per visit in the unstructured records group (P = .004). Likewise, anticipatory guidance was more thoroughly documented in the ST records group--8.3 items per visit vs 2.5 items per visit (P < .001). Ninety percent of the users preferred the ST records. One year after the adoption of the ST recording system, high levels of thoroughness persisted. CONCLUSIONS: Structured, scannable encounter forms can facilitate documentation of patient care and are well accepted by users. They can provide an effective mechanism to ease the transition to a computer-based patient record.     

Methodology to Assess Building Designs for Protection against Internal Chemical and Biological Threats

Recent world events involving chemical and biological (CB) attacks within critical infrastructure have highlighted a potential threat to buildings and their occupants. As a result, protecting buildings from CB attacks has become an important design consideration. A methodology has been developed to provide decision makers with the ability to assess multiple building designs for protection against an internal CB release. This methodology includes modeling and simulation of CB contaminant dispersion, a quantitative means to calculate a building’s protection level, and a weighted sum, multiple objective optimization for design selection. This paper outlines the phases in the methodology, and focuses on the application of multizone modeling and optimization techniques to compare design alternatives. The assessment of design options for CB protection in a hospital emergency room is used as an illustrative example. Optimal design options are determined based on the weighted combination functions for the building’s protection level, initial capital costs, and ongoing operations and maintenance costs.     

Agreement between administrative files and written medical records: a case of the Department of Veterans Affairs

OBJECTIVES: This study examined the reliability of Department of Veterans Affairs' health information databases concerning patient demographics, use of care, and diagnoses. METHODS: The Department of Veterans Affairs' Patient Treatment files for Main, Bed-section (PTF) and Outpatient Care (OCF) were compared with medical charts and administrative records (MR) for a random national sample of 1,356 outpatient visits and 414 inpatient discharges to Department of Veterans Affairs' facilities between July 1 and September 30, 1995. Records were uniformly abstracted by a focus group of utilization review nurses and medical record coders blinded to administrative file entries. RESULTS: Reliability was adequate for demographics (kappa approximately 0.92), length of stay (agreement=98%), and selected diagnoses (kappa ranged 0.39 to 1.0). Reliability was generally inadequate to identify the treating bedsection or clinic (kappa approximately 0.5). Compared with medical charts, Patient Treatment Files/Outpatient Care Files reported an additional diagnosis per discharge and 0.8 clinic stops per outpatient visit, resulting in higher estimates of disease prevalence (+39% heart disease, +19% diabetes) and outpatient costs (+36% per unique outpatient per quarter). CONCLUSIONS: In the absence of pilot work validating key data elements, investigators are advised to construct health and utilization data from multiple sources. Further validation studies of administrative files should focus on the relation between process of data capture and data validity.     

Study of Recent Building Failures in the United States

A total of 225 building failures in the United States from 1989 to 2000 were recorded in this study. The result shows that failures of low-rise buildings constitute about 63% of all cases, followed by multistory buildings as a distant second. In terms of their functions, apartments are the most frequent to fail. External events and construction and maintenance deficiencies have been identified as the most frequent principal causes. External events include rain, wind, snow, vehicular impact, and collision. Construction deficiencies encompass improper renovation, unplanned demolition, poor workmanship, and unsafe excavation operations. Maintenance deficiencies are associated with building deterioration that was overlooked and improperly maintained. A comparative analysis conducted between this study and two previous studies indicates an inclined trend of relative failure occurrences of low-rise and multistory buildings. The study also suggests that, despite the recent enhancement of information technology, current sources of information are still incomplete. The creation of new complete databases, further improvement of information sources, and their dissemination through the Internet are deemed essential to prevent building failures from recurring.     

Facility Maintenance Performance Perspective to Target Strategic Organizational Objectives

While facility design is increasingly playing a role addressing strategic organizational objectives, issues pertaining to facility maintenance have typically been left out of the decision-making process. Reasons include the traditional disconnection between facility design and facility maintenance, mainly originating from the lack of a modality to meaningfully represent facility maintenance information during design decision making. This paper discusses two sets of facility maintenance indicators that have the potential to bridge this traditional divide. The objective of this paper is threefold: (1) to illustrate how maintenance performance indicators can support higher-level decision making; (2) to explain how the methodology could be mapped across building sectors; and (3) to show how facility maintenance could play a crucial role in informing strategic decision making. Two types of indicators are introduced based on: (1) normative models in biophysics and physiology and (2) empiricist models of environment-behavior studies. Using examples from hospital, courthouse, and office building design, the paper articulates the manner in which facility performance indicators could be developed and used to support organizational strategic decision making. The paper demonstrates that facility maintenance indicators could be developed for all types of buildings and could be meaningfully represented for consideration during strategic decision making. Moreover, using an example of a healthcare setting, the paper emphasizes how facility maintenance strategies have an impact on higher-level organizational objectives, and vice versa, thereby underscoring the importance to consider maintenance performance during strategic decision making. The paper shows how the two sets of key performance indicators—the hard and the soft—are designed to address different scales of decision making, thereby allowing facility maintenance performance to be considered at all phases of a procurement cycle.     

融合多特征嵌入与注意力机制的中文电子病历命名实体识别

中文电子病历文本包含大量嵌套实体、句子语法结构复杂、句式偏短。为有效识别其医疗实体,提出一种融合多特征嵌入与注意力机制的命名实体识别算法,在输入表示层融合字符、单词、字形三个粒度的特征,并在双向长短期记忆网络的隐含层引入注意力机制,使算法在捕获特征时更加关注于医疗实体相关的字符,最终实现对中文电子病历中疾病、身体部位、症状、药物、操作五类实体的最优标注。面向开源和自建糖尿病数据集的实验结果中所提算法的实体识别准确率、召回率和F1值都达到97%以上,表明其可以更加有效地识别中文电子病历中各类实体。      

Requests for complete record release: A three-step response protocol.

Clients seen by therapists sometimes request the release of complete copies of their records to assist them with a variety of problems ranging from personal injury lawsuits, child custody litigation, criminal defense, and other issues. Because clients frequently do not know the contents of their records, release of complete mental health records often creates special problems for therapists and, potentially, for clients alike. This multiple-case study describes the impact of therapist-supervised client chart review, education about client rights, and potential consequences of complete record release on client decisions to maintain or rescind consent to release entire chart records. Participants were 27 current or former clients who submitted requests for release of a complete mental health record. A three part protocol designed to authenticate the request, discuss potential benefits and costs of record release, and read the mental health record was implemented. Subsequent decisions to release or rescind the request were documented. Sixteen of 27 requests were rescinded (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Violence in a violent society

This article presents the methods and results of two surveys aiming to contribute to the development of partnerships between doctors and teachers in primary school. The first study, carried out with a sample of elementary school teachers, shows the interest they have in health promotion at school, their desire to see national education doctors become involved in health education, and their misunderstanding of the role of national education doctors and nurses, especially in training and participation in school projects. The second study, carried out among a sample of national education doctors, shows their felt sense of "friction" between the individual medical approach within which they were trained and for which they are known and solicited, and the public health approach that they would like to develop. To ameliorate the partnership, the inspector of national education, as the responsible party for educational policies within his district, is the necessary "link" between doctors, school directors and teachers.     

Contemporary Design-Bid-Build Model

Empirical research was performed into the hypothesis that a substantial number of building performance engineering tasks on design-bid-build projects are typically provided by entities associated with the construction phase, not with the architect-engineer (AE) of record. This hypothesis is contrary to the traditional understanding of design-bid-build and is theorized to result from increased time pressures on AEs, decreased AE profit margins, AEs’ attempts to minimize liability, increased design and construction specialization, and increased prefabrication. Project technical specifications were analyzed for 20 $5–45M building construction projects and 16 individuals directly associated with these projects were interviewed. It was found that 35 building performance engineering tasks were required by the project specifications to be performed by entities associated with the construction of the buildings. This large number of delegated design tasks suggests the conventional understanding of the design-bid-build process is not accurate. The increasing fragmentation of the design and construction process may have implications for the efficiency of communication on design-bid-build projects, lean construction processes, and constructability.     

A case of Rathke''s cleft cyst with apoplexy

OBJECTIVE: To develop and evaluate a model of integrated primary dental and medical care. DESIGN: 3-year prospective study. SETTING: A general dental practice and a general medical practice occupying the same building in Glasgow. INTERVENTION: Regular staff meetings, joint use of patient records systems and information derived from patient questionnaires. Dentistry was included in established screening programmes such as child health surveillance and care of elderly. Staff were encouraged to participate in joint work practices and joint consultations were carried out. MAIN OUTCOME MEASURES: Patient registration, avoidance of discrepancies in information, reduction of secondary referrals, joint work practices. RESULTS: The number of registered joint patients attending both medical and dental practices increased by 90%. The joint use of patient record systems avoided discrepancies in patient information which would have affected the quality of patient care. Including dentistry in child health surveillance and care of elderly screening programmes resulted in an increase in 0-5 year olds registering with dentists from 36% to 68% (P < 0.001) and with > 75 year olds from 47% to 71% (P < 0.001). Joint consultations reduced the need for secondary referrals. CONCLUSIONS: This model of health care demonstrated the potential for coordination and integration of functions between the dental team and the primary care team. Integrated primary dental and medical care requires attitudinal change in health care professionals and requires greater emphasis in education and training of health care professionals in the future.     

Obstetrician-gynecologists are primary physicians to women. I. Practice patterns of Michigan obstetrician-gynecologists

Michigan obstetrician-gynecologists were asked to complete questionnaires designed to determine what kinds of medical services they provide their patients. The questionnaires completed by 369 doctors, who had graduated from medical school between 1930 and 1964 and who are in active practice, form the basis of this report. More than 50% treat common non-obstetric-gynecologic disorders in their own patients and smaller numbers treat more serious medical conditions. This study confirms a previous one, derived from information obtained from patients, that obstetricians-gynecologists serve as primary physicians to women, not exclusively as specialist-consultants.     

Number of diagnoses in the final report and in the medical record

One hundred patient records of an internistic outpatient clinic were evaluated retrospectively for differences regarding the number of diagnoses in the documentation and the final report. Whereas the final or interim reports on the average contained 2.8 clinically relevant diagnoses, screening of the total documentation let the number rise to 3.5. Mainly the reports qualified as qualitatively poor led to overlooked or neglected relevant findings. Our results underline the importance of a meticulously kept medical record for a medical practice of high standards and responsibility.     

Dynamic Testing of a Masonry Structure on a Passive Isolation System

Lightly reinforced and unreinforced masonry buildings have not performed well in earthquakes. Evaluation of past performance of masonry structures has led to more stringent design and construction requirements in the current building codes, and has raised concerns about the performance of existing lightly reinforced and unreinforced masonry buildings in future earthquakes. Base isolation has been shown to be effective in reducing damage to large building structures, and appears to be particularly effective in protecting stiff masonry structures. Using the base isolation principle, Kansas State University’s stiffness decoupler for the base isolation of structures (SDBIS) was designed to effectively reduce the acceleration and force transferred into a building superstructure during a seismic event. The sliding system uses a passive method to provide damping and to dissipate some of the kinetic energy to reduce relative displacements. In addition, the SDBIS system includes a self-centering element that will recover the majority of the induced displacement and provide resistance to overturning. In order to apply the SDBIS system to the masonry building industry, dynamic testes were performed to evaluate the structural response of a full-size one-story masonry model that was supported by the SDBIS system. Acceleration time-history results are presented for dynamic tests using the July 21, 1952 Kern County earthquake, Station 1095 Taft Lincoln School record, the May 19, 1940 Imperial Valley earthquake, Station 117 El Centro Array #9 record, the February 9, 1971 San Fernando earthquake, Station 279 Pacoima Dam record, and the January 17, 1994 Northridge earthquake, Station 24436 Tarzana Cedar Hill record ground motions. Test results show the system is effective when used with a masonry structure.     

Informatics support to medical diagnosis. General information obtained from a first structured contact with the patient

BACKGROUND: The methods and characteristics of clinical data gathered at the initial steps of development of a computerized system to aid medical diagnosis are reported. The objectives of the study were as follows: to describe the overall method and to set a framework for developing an intellectual model of the medical diagnosis procedure. MATERIAL AND METHODS: A structured medical interview and physical examination using an informatic program on PC compatible portable computers were completed in a sample 1,238 patients attending the outpatient clinics of our institution. Data obtained were compared with information in the patient's medical record taking as reference pattern the record of physicians in charge of the patients. Diagnosis were codified according to WHO International Classification of Diseases (ICD-9-CM). RESULTS: The distribution of symptoms and signs corresponding to the different organs and systems was analyzed. Each subdivision afforded a range of 1.3 to 3.9 abnormal findings per patient. A total of 3,571 diagnoses were codified for the whole group 1,238 patients with a mean (standard deviation) of 3 (2) diagnoses per patient (range 0-12). The distribution of diagnostic groups varied depending on the consideration of the main diagnosis or the concomitant diagnoses that defined the patient's clinical context. The most frequent main diagnoses included tumors, cardiovascular diseases, gastrointestinal disorders, and genitourinary tract diseases. CONCLUSIONS: As shown by results obtained in a sample of 1,238 patients, there is a very complex situation in clinical practice due to the simultaneous occurrence of several clinical patterns. This finding should be taken into account when developing clinical decision making support systems. The use of a structured medical interview or a structured and standard medical visit may be an adequate tool to clarify this matter and to contribute to standardization of clinical concepts and situations.     

基于数据融合的智能医疗辅助诊断方法

医生诊断需要结合临床症状、影像检查等各种数据,基于此,提出了一种可以进行数据融合的医疗辅助诊断方法。将患者的影像信息（如CT图像）和数值数据（如临床诊断信息）相结合,利用结合的信息自动预测患者的病情,进而提出了基于深度学习的医疗辅助诊断模型。模型以卷积神经网络为基础进行搭建,图像和数值数据作为输入,输出病人的患病情况。该医疗辅助诊断方法能够利用更加全面的信息,有助于提高自动诊断准确率、降低诊断误差;另外,仅使用提出的医疗辅助诊断模型就可以一次性处理多种类型的数据,能够在一定程度上节省诊断时间。在两个数据集上验证了所提出方法的有效性,实验结果表明,该方法是有效的,它可以提高辅助诊断的准确性。