Knowledge retrieval as one type of knowledge-based decision support in medicine: results of an evaluation study

Cooperative Problem Solving with Personal Mobile Information Tools in Hospitals

Health-care professionals have a broad range of needs for information and cooperation while working at different points of care (e.g., outpatient departments, wards, and functional units such as operating theaters). Patient-related data and medical knowledge have to be widely available to support high-quality patient care. Furthermore, due to the increased specialization of health-care professionals, efficient collaboration is required. Personal mobile information tools have a considerable potential to realize almost ubiquitous information and collaborative support. They enable to unite the functionality of conventional tools such as paper forms, dictating machines, and pagers into one tool. Moreover, they can extend the support already provided by clinical workstations. An approach is described for the integration of mobile information tools with heterogeneous hospital information systems. This approach includes identification of functions which should be provided on mobile tools. Major functions are the presentation of medical records and reports, electronic mailing to support interpersonal communication, and the provision of editors for structured clinical documentation. To realize those functions on mobile tools, we propose a document-based client-server architecture that enables mobile information tools to interoperate with existing computer-based application systems. Open application systems and powerful, partially wireless, hospital-wide networks are the prerequisites for the introduction of mobile information tools.

Health professionals’ attitudes towards evidence-based medicine and the role of the information professional in exploitation of the research evidence

The aim of a survey, undertaken at an English National Health Service (NHS) trust hospital in the summer of 1996, was to examine health professionals’ awareness of evidence-based medicine (EBM), their attitudes towards problems in implementing EBM locally and their views of the role of the library in supporting EBM. A postal questionnaire (response rate 40%: 182/475) provided baseline information for planning. More doctors than nurses or PAMs (professionals allied to medicine) had heard of the term EBM, but most of the health professionals were in agreement with the principles of EBM despite not understanding the term fully. Most of the health professionals wanted access to resources at the workplace, and doctors in particular preferred to do their own searching. Many health professionals doubted whether a librarian could find the relevant research articles, suggesting the need for better promotion of library services in support of EBM, emphasising value-added services.

Analysis of PubMed User Sessions Using a Full-Day PubMed Query Log: A Comparison of Experienced and Nonexperienced PubMed Users

Background

PubMed is the largest biomedical bibliographic information source on the Internet. PubMed has been considered one of the most important and reliable sources of up-to-date health care evidence. Previous studies examined the effects of domain expertise/knowledge on search performance using PubMed. However, very little is known about PubMed users’ knowledge of information retrieval (IR) functions and their usage in query formulation.

Objective

The purpose of this study was to shed light on how experienced/nonexperienced PubMed users perform their search queries by analyzing a full-day query log. Our hypotheses were that (1) experienced PubMed users who use system functions quickly retrieve relevant documents and (2) nonexperienced PubMed users who do not use them have longer search sessions than experienced users.

Methods

To test these hypotheses, we analyzed PubMed query log data containing nearly 3 million queries. User sessions were divided into two categories: experienced and nonexperienced. We compared experienced and nonexperienced users per number of sessions, and experienced and nonexperienced user sessions per session length, with a focus on how fast they completed their sessions.

Results

To test our hypotheses, we measured how successful information retrieval was (at retrieving relevant documents), represented as the decrease rates of experienced and nonexperienced users from a session length of 1 to 2, 3, 4, and 5. The decrease rate (from a session length of 1 to 2) of the experienced users was significantly larger than that of the nonexperienced groups.

Conclusions

Experienced PubMed users retrieve relevant documents more quickly than nonexperienced PubMed users in terms of session length.

A study on PubMed search tag usage pattern: association rule mining of a full-day PubMed query log

Background

The practice of evidence-based medicine requires efficient biomedical literature search such as PubMed/MEDLINE. Retrieval performance relies highly on the efficient use of search field tags. The purpose of this study was to analyze PubMed log data in order to understand the usage pattern of search tags by the end user in PubMed/MEDLINE search.

Methods

A PubMed query log file was obtained from the National Library of Medicine containing anonymous user identification, timestamp, and query text. Inconsistent records were removed from the dataset and the search tags were extracted from the query texts. A total of 2,917,159 queries were selected for this study issued by a total of 613,061 users. The analysis of frequent co-occurrences and usage patterns of the search tags was conducted using an association mining algorithm.

Results

The percentage of search tag usage was low (11.38% of the total queries) and only 2.95% of queries contained two or more tags. Three out of four users used no search tag and about two-third of them issued less than four queries. Among the queries containing at least one tagged search term, the average number of search tags was almost half of the number of total search terms. Navigational search tags are more frequently used than informational search tags. While no strong association was observed between informational and navigational tags, six (out of 19) informational tags and six (out of 29) navigational tags showed strong associations in PubMed searches.

Conclusions

The low percentage of search tag usage implies that PubMed/MEDLINE users do not utilize the features of PubMed/MEDLINE widely or they are not aware of such features or solely depend on the high recall focused query translation by the PubMed’s Automatic Term Mapping. The users need further education and interactive search application for effective use of the search tags in order to fulfill their biomedical information needs from PubMed/MEDLINE.

Evaluation of Term Ranking Algorithms for Pseudo-Relevance Feedback in MEDLINE Retrieval

OBJECTIVES

The purpose of this study was to investigate the effects of query expansion algorithms for MEDLINE retrieval within a pseudo-relevance feedback framework.

METHODS

A number of query expansion algorithms were tested using various term ranking formulas, focusing on query expansion based on pseudo-relevance feedback. The OHSUMED test collection, which is a subset of the MEDLINE database, was used as a test corpus. Various ranking algorithms were tested in combination with different term re-weighting algorithms.

RESULTS

Our comprehensive evaluation showed that the local context analysis ranking algorithm, when used in combination with one of the reweighting algorithms - Rocchio, the probabilistic model, and our variants - significantly outperformed other algorithm combinations by up to 12% (paired t-test; p < 0.05). In a pseudo-relevance feedback framework, effective query expansion would be achieved by the careful consideration of term ranking and re-weighting algorithm pairs, at least in the context of the OHSUMED corpus.

CONCLUSIONS

Comparative experiments on term ranking algorithms were performed in the context of a subset of MEDLINE documents. With medical documents, local context analysis, which uses co-occurrence with all query terms, significantly outperformed various term ranking methods based on both frequency and distribution analyses. Furthermore, the results of the experiments demonstrated that the term rank-based re-weighting method contributed to a remarkable improvement in mean average precision.

Knowledge sources affecting decision-making among social and health care managers

PURPOSE

The purpose of this paper is to investigate how managers in social and health care evaluate the knowledge sources affecting their decision-making, and how the evaluations were associated with the managers' professional background, activity sector, gender, age and management experience.

DESIGN/METHODOLOGY/APPROACH

The study data are gathered from a questionnaire survey to the middle-line doctor, nurse and social managers (n = 404) within the responsibility area of a Finnish university hospital. Assessed the proportions of individual knowledge sources in the complete data set and their associations with the subjects' background data. In addition, grouping of individual knowledge sources variables are made using factor analysis.

FINDINGS

The findings indicate that social and health care managers attempt to utilize diverse knowledge sources. Overall, professional experience and education, organization budget, and action plans of one's own unit are estimated as knowledge sources with the greatest impact. Manager's professional background and activity sector are associated with the kind of knowledge affecting their decision-making. Some differences are noted between genders, but differences with respect to age or management experience are non-significant.

RESEARCH LIMITATIONS/IMPLICATIONS

Social and health care organizations represent expert organizations where decision-making is steered by professions and management tasks.

ORIGINALITY/VALUE

This paper suggests that the future decision-makers will be required to identify versatile knowledge areas across cultural barriers, and to be capable of making comprehensive decisions affecting the entire organization.

On the query reformulation technique for effective MEDLINE document retrieval

Improving the retrieval accuracy of MEDLINE documents is still a challenging issue due to low retrieval precision. Focusing on a query expansion technique based on pseudo-relevance feedback (PRF), this paper addresses the problem by systematically examining the effects of expansion term selection and adjustment of the term weights of the expanded query using a set of MEDLINE test documents called OHSUMED. Implementing a baseline information retrieval system based on the Okapi BM25 retrieval model, we compared six well-known term ranking algorithms for useful expansion term selection and then compared traditional term reweighting algorithms with our new variant of the standard Rocchio's feedback formula, which adopts a group-based weighting scheme. Our experimental results on the OHSUMED test collection showed a maximum improvement of 20.2% and 20.4% for mean average precision and recall measures over unexpanded queries when terms were expanded using a co-occurrence analysis-based term ranking algorithm in conjunction with our term reweighting algorithm (p-value<0.05). Our study shows the behaviors of different query reformulation techniques that can be utilized for more effective MEDLINE document retrieval.

Seven reasons why health professionals search clinical information-retrieval technology (CIRT): toward an organizational model

RATIONALE AND AIM

Clinical Information-Retrieval Technology (CIRT) is increasingly used, for example in accessing drug databases. However, no comprehensive framework exists to understand why health professionals search for information using CIRT. The present article aims to propose such organizational framework.

BACKGROUND

Our literature review suggests six reasons, of which three refer to cognitive objectives (C1, C2, C3) and three to organizational objectives (O1, O2, O3): (C1) to answer-solve-support a clinical question-problem-decision; (C2) to fulfil an educational-research objective; (C3) to search in general or for curiosity; (O1) to share information with patients; (O2) to exchange information with other health professionals; (O3) to plan-manage-monitor tasks with other health professionals.

METHODS

The case study examined the use and impact of the InfoRetriever software on handheld computers in a Canadian family practice centre. Using the Critical Incident Technique, six family doctors were interviewed on specific events. A thematic analysis assigned extracts of interviews to reasons for use.

FINDINGS AND CONCLUSION

Findings illustrate the six reasons, and suggest a seventh reason that refers to a cognitive objective, namely (C4) to overcome the limits of health professional memory. These seven reasons are interpreted according to the literature on information science and organization studies, which suggest ordering reasons at three levels of stimulation of learning and knowledge: none (objective not achieved), moderate (cognitive objective achieved), and high (organizational objective achieved). This paves the way toward a new evaluation of relevance of CIRT in everyday practice (judgement based on professionals' objective achievement) using an organizational model of information-retrieving processes.

Health professional workstations and their integration in a hospital information system: the pragmatic approach MEDIAS

Within the daily workload at a ward there is a considerable amount of information processing. It is the task of a systematic management of hospital information systems to provide health professionals with the right information in the right place at the right time. This paper deals with the consequences for the management of hospital information systems if health professional workstations are introduced as a means for this information logistic and with the experiences gained in the Heidelberg University Hospital. Health professional workstations are formally defined in the context of a three level graph-based model of hospital information systems. It is found that health professional workstations have communication needs not only on the physical level of computer systems in the hospital information system but also on the logical tool level, which is the level of application systems. On this level communication servers or brokers are of considerable importance. In Heidelberg there are about 200 health professional workstations (MEDIAS) in routine use.