Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Medical Informatics Applications”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,261 records · Page 70Linked to original sources
PubMed1994

Mapping clinically useful terminology to a controlled medical vocabulary.

We have mapped clinically used diagnostic terms from a legacy ambulatory care system to the separate controlled vocabulary of our central clinical information system. The methodology combines elements of lexical and morphologic text matching techniques, followed by manual physician review. Results of the automated matching algorithm before and after partial manual review are presented. The results of this effort will permit the migration of coded clinical data from one system to another. Output from the system after the term review process will be fed back to the target vocabulary via automated and semi-automated means to improve its clinical utility.

Academic Medical Centers↗
PubMed1994

Academic physicians' assessment of the effects of computers on health care.

We assessed the attitudes of academic physicians towards computers in health care at two academic medical centers that are in the early stages of clinical information-system deployment. We distributed a 4-page questionnaire to 470 subjects, and a total of 272 physicians (58%) responded. Our results show that respondents use computers frequently, primarily to perform academic-oriented tasks as opposed to clinical tasks. Overall, respondents viewed computers as being slightly beneficial to health care. They perceive self-education and access to up-to-date information as the most beneficial aspects of computers and are most concerned about privacy issues and the effect of computers on the doctor-patient relationship. Physicians with prior computer training and greater knowledge of informatics concepts had more favorable attitudes towards computers in health care. We suggest that negative attitudes towards computers can be addressed by careful system design as well as targeted educational activities.

Academic Medical Centers↗
PubMedDate not supplied

Cytology requisition log-in with a minimum of keyboard entry.

Virtually every cytology laboratory invests considerable staff time in the entry or log-in of specimens into a laboratory information system. In many cases these systems are not optimized for rapid entry of the data. We describe a combination of two techniques (fastkey/macros and bar code) that has enabled us to reduce the number of keystrokes required for cytologic smear accessioning and to improve the overall efficiency of the requisition entry process by 25%. Similar techniques could be used with a wide variety of information systems.

Cytological Techniques↗
PubMed1994

The need for requirements engineering in the development of clinical decision-support systems: a qualitative study.

Insufficient requirements analysis has recently been suggested as a problem in clinical decision-support systems development. Therefore, to explore knowledge, practices and attitudes, key professionals in the area from four countries were interviewed regarding the early phases in the development process. For data collection, semi-structured interviews were performed and video-taped. As reference, documentation of the Action Design requirements engineering methodology was used. Two separate qualitative analyses of the data were made. The first was to identify central concepts and attitudes related to requirements engineering. In the second analysis, concrete circumstances surrounding decisions to use requirements engineering methods were investigated. This paper reports the results of the analyses and discusses changes in the planning and management of clinical decision-support projects in general, and it comments on development methods, using Action Design as reference. It is concluded that studies are needed to further investigate the problems real decision-support projects have to deal with. This knowledge can then be used to develop methods and tools which support design practices where existing structural, procedural and, building on this, technical obstacles are overcome.

Decision Support Techniques↗
PubMed1993

An evaluation of factors influencing Bayesian learning systems.

This paper examines the influences of situational and model factors upon the accuracy of Bayesian learning systems. In particular, it is concerned with the impact of variations in training sample size, number of attributes, choice of Bayesian model, and criteria for excluding model attributes upon the overall accuracy of the simple and proper Bayes models.

Artificial Intelligence↗
PubMed1993

[Full computerization of a radiology service. A 5 years' experience at a centralized system].

Even though the problem of collecting and processing information is of paramount importance in any radiology department, the choice of the best information system--as for organization and effectiveness--largely depends on specific and different local situations and is therefore still largely debated. In the ULSS 18 in Veneto (Dolo, Venezia), all patients are referred to the only existing hospital radiology. Therefore, a central computer system has been be realized and used also by the radiology department, for completely computed procedures, since January 1, 1988. We describe the computer configuration of both the ULSS and the radiology department and report on our 5-year experience with full computerization within a central information system. As for department organization, any information system--with appropriate hardware and software--can be equivalent to others, since it largely contributes to both management (programming, booking, filing, accounting) and reporting (automatic reporting with memorized texts and/or voice recognition; reprinting; immediate correction at the video-terminal). Thanks to more rational exploitation of human and technological resources, any information system makes a radiology department more functional and efficient. However, some peculiarities of the central computer system must be stressed, as they allow: 1) to use pre-existing and updated patients files (unequivocal identification in the whole ULSS); 2) to gain access to the databanks of different specialties and to patients' clinical histories (complete data collected from many sources); 3) to intervene in booking and ticket collection centers with none of the relative loads; 4) to have no limits of memory, storage or speed for complex programs (automatic reporting also with the recognition of the dictating voice, accounting and statistical analyses, ecc.); 5) to profit by continually updated and fitted hardware and software, with the relative expenses and benefits shared by the whole ULSS. Within the possibilities given by a double role-ruled password, all different menus and programs are accessible from any video-terminal, even while other programs are running, thus allowing cost-effective hardware to be available in the radiology department.

Computers↗
PubMed1993

Automatic knowledge acquisition from MEDLINE.

Construction of medical knowledge bases for use in expert systems is an arduous task. We propose a procedure for obtaining medical knowledge via automated analysis of citations found in the National Library of Medicine's MEDLINE database. In this method, simple pattern of keywords and subheading co-occurrences are detected in the keyword descriptor portion of the citations. Each pattern corresponds to a fact, expressed as a semantic relationship between medical concepts. We have constructed a set of 504 pattern-matching rules and applied it to a set of 673 MEDLINE citations to produce 2,795 such facts. The results are presented of an analysis of the syntactic and semantic features of these facts to understand the kinds of knowledge than can be obtained through our method and speculate on the potential uses and pitfalls for knowledge of this type.

Artificial Intelligence↗
PubMed1993

HEALTH WATCH: health promotion and disease prevention in primary care.

HEALTH WATCH, a longitudinal prospective study of healthy aging, was designed to characterize a healthy population of 2,200 men and women, ages 20-80 years in 1970. Biochemical, hematological, and physiological tests are performed annually over three weekly visits, combined with a self-administered HEALTH WATCH questionnaire to measure health status and behaviors in seven areas (with over 1,330 variables). In 1988, the HEALTH WATCH study was modified to assess characteristics of an oldest old "productive aging" cohort in Kauai, Hawaii. Nutrition, physical activity, extended family, and spirituality were found to be major health determinants. During 1989 to 1991 a controlled intervention study (ten local primary care physicians and their patients, aged 65-89 years) was completed in the Sun Cities, Arizona. These studies provide evidence that primary care physicians can promote positive health outcomes in patients of any chronological age and baseline health status through active healthy aging interventions.

Aged↗