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 775 records · Page 43Linked to original sources
PubMed2001

Medical informatics: reasoning methods.

The progress of medical informatics has been characterized by the development of a wide range of reasoning methods. These reasoning methods are based on organizing principles that make use of the various relations existing in medical domains: associations, probabilities, causality, functional relationships, temporal relations, locality, similarity, and clinical practice. Some, such as those based on associations and probabilities have been developed to the point where there are off-the-shelf tools available for the researcher to develop new decision support tools. Others such as temporal relations require more effort to use effectively. Even so, we have learned the importance of a separate explicit representation of the domain knowledge and have considerable experience and an impressive armamentarium with which to face the new milieu provided by the Internet.

Artificial Intelligence↗
PubMed2001

Machine learning for medical diagnosis: history, state of the art and perspective.

The paper provides an overview of the development of intelligent data analysis in medicine from a machine learning perspective: a historical view, a state-of-the-art view, and a view on some future trends in this subfield of applied artificial intelligence. The paper is not intended to provide a comprehensive overview but rather describes some subareas and directions which from my personal point of view seem to be important for applying machine learning in medical diagnosis. In the historical overview, I emphasize the naive Bayesian classifier, neural networks and decision trees. I present a comparison of some state-of-the-art systems, representatives from each branch of machine learning, when applied to several medical diagnostic tasks. The future trends are illustrated by two case studies. The first describes a recently developed method for dealing with reliability of decisions of classifiers, which seems to be promising for intelligent data analysis in medicine. The second describes an approach to using machine learning in order to verify some unexplained phenomena from complementary medicine, which is not (yet) approved by the orthodox medical community but could in the future play an important role in overall medical diagnosis and treatment.

Artificial Intelligence↗
PubMed2001

AIM: a personal view of where I have been and where we might be going.

My own career in medical informatics and AI in medicine has oscillated between concerns with medical records and concerns with knowledge representation with decision support as a pivotal integrating issue. It has focused on using AI to organise information and reduce 'muddle' and improve the user interfaces to produce 'useful and usable systems' to help doctors with a 'humanly impossible task'. Increasingly knowledge representation and ontologies have become the fulcrum for orchestrating re-use of information and integration of systems. Encouragingly, the dilemma between computational tractability and expressiveness is lessening, and ontologies and description logics are joining the mainstream both in AI in Medicine and in Intelligent Information Management generally. It has been shown possible to scale up ontologies to meet medical needs, and increasingly ontologies are playing a key role in meeting the requirements to scale up the complexity of clinical systems to meet the ever increasing demands brought about by new emphasis on reduction of errors, clinical accountability, and the explosion of knowledge on the Web.

Artificial Intelligence↗
PubMed1997

Retrieving cases for treatment advice in nursing using text representation and structured text retrieval.

A nursing database which records patient details and treatments as fields in a standard database format is transformed into a collection, in text form, of patient case days with history. Each case is represented as text strings encoding the patient details, the current problems, treatments and their associated history. The cosine measure of similarity is used to compute a whole case similarity between a text query and the cases in text form. This standard text retrieval technique is used and compared to a simple rule base. In case-based reasoning, the similarity of cases is often computed by combining similarities of the case features involved. In this work the standard text retrieval function is modified to incorporate this case structure by combining individual matches of case components based on the cosine measure. The combination is based on a linear regression model for learning the weights assigned to the components of this retrieval function. For the 1355 records two tasks were tried: predicting the treatment for a new problem and predicting the treatment for a continuing problem when a change of treatment is required. Simple text retrieval was better than the rule base for one task and case structured retrieval was at least 18% better on both tasks. Further techniques are discussed.

Age Factors↗
PubMed2000

Research needs and priorities in health informatics.

A Delphi study was accomplished on the topic "what is needed to implement the information society within healthcare? and which research topics should be given higher priority than other topics to achieve the desired evolution?", involving 29 international experts. The study comprised of four phases, (I) a brainstorming phase based on a open question; (II) an evaluation phase for mutual commenting; (III) a feedback phase allowing corrections/extensions; and (IV) a phase collecting the ratings of individual issues within a questionnaire synthesised from the previous phases. A total of 110 research items and 58 supplementary barriers were raised, divided into 14 topics grouped according to homogeneity. The emphasised research topics are business process re-engineering, the electronic patient record and connected inter-operating systems, (support for) evidence-based medicine and clinical guidelines, and education. Issues inherent to the healthcare domain often are the kernel of the research recommended. Similarly, methods and 'people'-issues are strongly emphasised among the research issues in general and among those for which the experts' joint opinion was rated as statistically significant. In contrast, only a minority of the research issues emphasised was related to technical issues.

Delphi Technique↗
PubMed2001

Knowledge representation and retrieval using conceptual graphs and free text document self-organisation techniques.

Hospitals generate and store a large amount of clinical data each year, a significant portion of which is in free text format. Conventional database storage and retrieval algorithms are incapable of effectively processing free text medical data. The rich information and knowledge buried in healthcare records are unavailable for clinical decision-making. We examined a number of techniques for structuring and processing free text documents to effective and efficient for information retrieval and knowledge discovery. One critical success criterion is that the complexity of the techniques must be polynomial both in space and time for them to be able to cope with very large databases. We used conceptual graphs (CG) to capture the structure and semantic information/knowledge contained within the free text medical documents. Ordering and self-organising techniques (lattice techniques and knowledge space) were used to improve organisation of concepts from standard medical nomenclatures and large sets of free text medical documents. Pair-wise union of CG was performed to identify the common generalisation structure and a lattice structure of these CG documents. A combination of all three techniques allowed us to organise a set of 9000 discharge summaries into a generalisation hierarchy that supported efficient and rich information/knowledge retrieval.

Classification↗
PubMed2001

The retrieval effectiveness of medical information on the web.

The World Wide Web has become such an extensive health information repository in the world that it is increasingly difficult to search for relevant medical information. Many search tools have been developed to help users look for relevant health information on the web, but most of them are still not efficient. In this paper, we discuss some available on-line solutions to medical information retrieval and compare the performances of some general and medicine-specific search engines with the MediAgent, which has been developed by the National University of Singapore (NUS) Medical Informatics Programme. Although a number of medicine-specific searching techniques have been developed, the difficulty of finding medical information still remains because medical search engines are generally not as effective as generic search engines. Different from other search tools, MediAgent's efficiency was quite high, taking only an average of 1.5 links to retrieve the answers, but its retrieving effectiveness is not good enough due to the short period of operation. Whilst the MediAgent project cannot claim to have all the solutions, it nevertheless offers a new alternative to system implementation. New techniques need to be explored in order to overcome the issues of medical information retrieval on the Internet.

Humans↗
PubMed2002

Metadata-driven creation of data marts from an EAV-modeled clinical research database.

Generic clinical study data management systems can record data on an arbitrary number of parameters in an arbitrary number of clinical studies without requiring modification of the database schema. They achieve this by using an Entity-Attribute-Value (EAV) model for clinical data. While very flexible for creating transaction-oriented systems for data entry and browsing of individual forms, EAV-modeled data is unsuitable for direct analytical processing, which is the focus of data marts. For this purpose, such data must be extracted and restructured appropriately. This paper describes how such a process, which is non-trivial and highly error prone if performed using non-systematic approaches, can be automated by judicious use of the study metadata-the descriptions of measured parameters and their higher-level grouping. The metadata, in addition to driving the process, is exported along with the data, in order to facilitate its human interpretation.

Breast Neoplasms↗
PubMed2003

Open Source software in medical informatics--why, how and what.

'Open Source' is a 20-40 year old approach to licensing and distributing software that has recently burst into public view. Against conventional wisdom this approach has been wildly successful in the general software market--probably because the openness lets programmers the world over obtain, critique, use, and build upon the source code without licensing fees. Linux, a UNIX-like operating system, is the best known success. But computer scientists at the University of California, Berkeley began the tradition of software sharing in the mid 1970s with BSD UNIX and distributed the major internet network protocols as source code without a fee. Medical informatics has its own history of Open Source distribution: Massachusetts General's COSTAR and the Veterans Administration's VISTA software have been distributed as source code at no cost for decades. Bioinformatics, our sister field, has embraced the Open Source movement and developed rich libraries of open-source software. Open Source has now gained a tiny foothold in health care (OSCAR GEHR, OpenEMed). Medical informatics researchers and funding agencies should support and nurture this movement. In a world where open-source modules were integrated into operational health care systems, informatics researchers would have real world niches into which they could engraft and test their software inventions. This could produce a burst of innovation that would help solve the many problems of the health care system. We at the Regenstrief Institute are doing our part by moving all of our development to the open-source model.

Database Management Systems↗
PubMed2003

Report of conference track 3: patient empowerment.

Patient empowerment is a philosophy of health care that proceeds from the perspective that optimal outcomes of health care interventions are achieved when patients become active participants in the health care process. Under a patient empowerment philosophy, patients and clinicians jointly set goals, select interventions, and assess outcomes according to mutually-defined parameters. Employing patient empowerment as an information systems design philosophy leads to creation of computerized information resources, management systems and telehealth innovations in a manner that insures patients' abilities to participate as full partners in health care. Discussions in the track 3 discussion group led to refinement of the concept from patient empowerment to patient engagement. This report reflects the discussions by the participants.

Congresses as Topic↗
PubMed1997

Analysis of data about epileptic patients using the GUHA method.

In this paper we search for hypotheses on association between the memory quotient and 13 clinical variables examined in a sample of 214 epilepsy patients. We introduce the General Unary Hypotheses Automaton (GUHA) method that automatically generates hypotheses from empirical data by means of computer procedures. Procedure ASSOC of the program GUHA generates and evaluates the hypotheses on symmetrical association or asymmetrical association using quantifiers. The most used symmetrical and asymmetrical quantifiers of the ASSOC procedure are introduced. Data analysis on epileptic patients using the GUHA method is done and the results are presented. We propose a new interpretation of the results including a graphical presentation.

Age of Onset↗
PubMedDate not supplied

How can usability measurement affect the re-engineering process of clinical software procedures?

As a consequence of the dramatic improvements achieved in information technology standards in terms of single hardware and software components, efforts in the evaluation processes have been focused on the assessment of critical human factors, such as work-flow organisation, man-machine interaction and, in general, quality of use, or usability. This trend is particularly valid when applied to medical informatics, since the human component is the basis of the information processing system in health care context. With the aim to establish an action-research project on the evaluation and assessment of clinical software procedures which constitute an integrated hospital information system, the authors adopted this strategy and considered the measurement of perceived usability as one of the main goals of the project itself: the paper reports the results of this experience.

Evaluation Studies as Topic↗