BMC Medical Informatics and Decision Making

When outbreak detection algorithms (ODAs) are considered individually, the task of outbreak detection can be seen as a classification problem and the ODA as a sensor providing a binary decision (outbreak yes or no) for each day of surveillance. When they are considered jointly (in cases where several ODAs analyze the same surveillance signal), the outbreak detection problem should be treated as a decision fusion (DF) problem of multiple sensors. This study evaluated the benefit for a decisions support system of using DF methods (fusing multiple ODA decisions) compared to using a single method of outbreak detection. For each day, we merged the decisions of six ODAs using 5 DF methods (two voting methods, logistic regression, CART and Bayesian network - BN). Classical metrics of accuracy, prediction and timelines were used during the evaluation steps. In our results, we observed the greatest gain (77%) in positive predictive value compared to the best ODA if we used DF methods with a learning step (BN, logistic regression, and CART). To identify disease outbreaks in systems using several ODAs to analyze surveillance data, we recommend using a DF method based on a Bayesian network. This method is at least equivalent to the best of the algorithms considered, regardless of the situation faced by the system. For those less familiar with this kind of technique, we propose that logistic regression be used when a training dataset is available.

In 2003, the International Patient Decision Aid Standards (IPDAS) Collaboration was established to enhance the quality and effectiveness of patient decision aids by establishing an evidence-informed framework for improving their content, development, implementation, and evaluation. Over this 10 year period, the Collaboration has established: a) the background document on 12 core dimensions to inform the original modified Delphi process to establish the IPDAS checklist (74 items); b) the valid and reliable IPDAS instrument (47 items); and c) the IPDAS qualifying (6 items), certifying (6 items + 4 items for screening), and quality criteria (28 items). The objective of this paper is to describe the evolution of the IPDAS Collaboration and discuss the standardized process used to update the background documents on the theoretical rationales, evidence and emerging issues underlying the 12 core dimensions for assessing the quality of patient decision aids.

Currently, one of the commonly used methods for disseminating electronic health record (EHR)-based phenotype algorithms is providing a narrative description of the algorithm logic, often accompanied by flowcharts. A challenge with this mode of dissemination is the potential for under-specification in the algorithm definition, which leads to ambiguity and vagueness. This study examines incidents of under-specification that occurred during the implementation of 34 narrative phenotyping algorithms in the electronic Medical Record and Genomics (eMERGE) network. We reviewed the online communication history between algorithm developers and implementers within the Phenotype Knowledge Base (PheKB) platform, where questions could be raised and answered regarding the intended implementation of a phenotype algorithm. We developed a taxonomy of under-specification categories via an iterative review process between two groups of annotators. Under-specifications that lead to ambiguity and vagueness were consistently found across narrative phenotype algorithms developed by all involved eMERGE sites. Our findings highlight that under-specification is an impediment to the accuracy and efficiency of the implementation of current narrative phenotyping algorithms, and we propose approaches for mitigating these issues and improved methods for disseminating EHR phenotyping algorithms.

The wide offer of information on pharmaceuticals does not often fulfill physicians’ needs: problems of relevance, access, quality and applicability are widely recognized, and doctors often rely on their own experience and expert opinions rather than on available evidence. A quali-quantitative research was carried out in Italy to provide an overview on information seeking behavior and information needs of doctors, in particular of infectious disease specialists, and to suggest an action plan for improving relevance, quality and usability of scientific information. We did a quantitative survey and three focus groups. Two hundred infectious disease specialists answered a 24-item questionnaire aimed at investigating features of scientific information they receive and their ratings about its completeness, quality and usability. Subsequent focus groups, each involving eight specialists, investigated their opinions on information sources and materials, and their suggestions on how these could better support their information needs. The quantitative survey indicated doctors’ appreciation of traditional channels (especially drug representatives) and information materials (brochures), but also their attitude to autonomous search of information and their wish to have more digital channels available. Focus groups provided more depth and, not surprisingly, revealed that physicians consider critical to get complete, comparative and specific information quickly, but also that they would like to discuss their doubts with expert colleagues. Quite strikingly, limited concerns were expressed on information validity, potential biases and conflicts of interests, as scientific validity seems to be related to the perceived authoritativeness of information sources rather than to the availability of a transparent evaluation framework. Although this research investigated views of infectious disease specialists, we believe that their opinions and perceived needs should not substantially differ from those of other clinicians, either in primary or in secondary care. In participants’ view, the ideal information framework should provide quick and tailored answers through available evidence and favor the exchange of information between practitioners and trusted experts. The general consensus existing within the scientific and medical community on the need for integrating available evidence and experience is confirmed, although the issues of information validity and conflicts of interests seem definitely overlooked.

Information on ethnicity is commonly used by health services and researchers to plan services, ensure equality of access, and for epidemiological studies. In common with other important demographic and clinical data it is often incompletely recorded. This paper presents a method for imputing missing data on the ethnicity of cancer patients, developed for a regional cancer registry in the UK. Routine records from cancer screening services, name recognition software (Nam Pehchan and Onomap), 2001 national Census data, and multiple imputation were used to predict the ethnicity of the 23% of cases that were still missing following linkage with self-reported ethnicity from inpatient hospital records. The name recognition software were good predictors of ethnicity for South Asian cancer cases when compared with data on ethnicity derived from hospital inpatient records, especially when combined (sensitivity 90.5%; specificity 99.9%; PPV 93.3%). Onomap was a poor predictor of ethnicity for other minority ethnic groups (sensitivity 4.4% for Black cases and 0.0% for Chinese/Other ethnic groups). Area-based data derived from the national Census was also a poor predictor non-White ethnicity (sensitivity: South Asian 7.4%; Black 2.3%; Chinese/Other 0.0%; Mixed 0.0%). Currently, neither method for assigning individuals to an ethnic group (name recognition and ethnic distribution of area of residence) performs well across all ethnic groups. We recommend further development of name recognition applications and the identification of additional methods for predicting ethnicity to improve their precision and accuracy for comparisons of health outcomes. However, real improvements can only come from better recording of ethnicity by health services.

Unstructured data from electronic health records represent a wealth of information. Doc’EDS is a pre-screening tool based on textual and semantic analysis. The Doc’EDS system provides a graphic user interface to search documents in French. The aim of this study was to present the Doc’EDS tool and to provide a formal evaluation of its semantic features. Doc’EDS is a search tool built on top of the clinical data warehouse developed at Rouen University Hospital. This tool is a multilevel search engine combining structured and unstructured data. It also provides basic analytical features and semantic utilities. A formal evaluation was conducted to measure the impact of Natural Language Processing algorithms. Approximately 18.1 million narrative documents are stored in Doc’EDS. The formal evaluation was conducted in 5000 clinical concepts that were manually collected. The F-measures of negative concepts and hypothetical concepts were respectively 0.89 and 0.57. In this formal evaluation, we have shown that Doc’EDS is able to deal with language subtleties to enhance an advanced full text search in French health documents. The Doc’EDS tool is currently used on a daily basis to help researchers to identify patient cohorts thanks to unstructured data.

Advanced mobile communications and portable computation are now combined in handheld devices called “smartphones”, which are also capable of running third-party software. The number of smartphone users is growing rapidly, including among healthcare professionals. The purpose of this study was to classify smartphone-based healthcare technologies as discussed in academic literature according to their functionalities, and summarize articles in each category. In April 2011, MEDLINE was searched to identify articles that discussed the design, development, evaluation, or use of smartphone-based software for healthcare professionals, medical or nursing students, or patients. A total of 55 articles discussing 83 applications were selected for this study from 2,894 articles initially obtained from the MEDLINE searches. A total of 83 applications were documented: 57 applications for healthcare professionals focusing on disease diagnosis (21), drug reference (6), medical calculators (8), literature search (6), clinical communication (3), Hospital Information System (HIS) client applications (4), medical training (2) and general healthcare applications (7); 11 applications for medical or nursing students focusing on medical education; and 15 applications for patients focusing on disease management with chronic illness (6), ENT-related (4), fall-related (3), and two other conditions (2). The disease diagnosis, drug reference, and medical calculator applications were reported as most useful by healthcare professionals and medical or nursing students. Many medical applications for smartphones have been developed and widely used by health professionals and patients. The use of smartphones is getting more attention in healthcare day by day. Medical applications make smartphones useful tools in the practice of evidence-based medicine at the point of care, in addition to their use in mobile clinical communication. Also, smartphones can play a very important role in patient education, disease self-management, and remote monitoring of patients.

Advanced analytics, such as artificial intelligence (AI), increasingly gain relevance in medicine. However, patients’ responses to the involvement of AI in the care process remains largely unclear. The study aims to explore whether individuals were more likely to follow a recommendation when a physician used AI in the diagnostic process considering a highly (vs. less) severe disease compared to when the physician did not use AI or when AI fully replaced the physician. Participants from the USA (n = 452) were randomly assigned to a hypothetical scenario where they imagined that they received a treatment recommendation after a skin cancer diagnosis (high vs. low severity) from a physician, a physician using AI, or an automated AI tool. They then indicated their intention to follow the recommendation. Regression analyses were used to test hypotheses. Beta coefficients (ß) describe the nature and strength of relationships between predictors and outcome variables; confidence intervals [CI] excluding zero indicate significant mediation effects. The total effects reveal the inferiority of automated AI (ß = .47, p = .001 vs. physician; ß = .49, p = .001 vs. physician using AI). Two pathways increase intention to follow the recommendation. When a physician performs the assessment (vs. automated AI), the perception that the physician is real and present (a concept called social presence) is high, which increases intention to follow the recommendation (ß = .22, 95% CI [.09; 0.39]). When AI performs the assessment (vs. physician only), perceived innovativeness of the method is high, which increases intention to follow the recommendation (ß = .15, 95% CI [− .28; − .04]). When physicians use AI, social presence does not decrease and perceived innovativeness increases. Pairing AI with a physician in medical diagnosis and treatment in a hypothetical scenario using topical therapy and oral medication as treatment recommendations leads to a higher intention to follow the recommendation than AI on its own. The findings might help develop practice guidelines for cases where AI involvement benefits outweigh risks, such as using AI in pathology and radiology, to enable augmented human intelligence and inform physicians about diagnoses and treatments.

Better understanding of clinical reasoning could reduce diagnostic error linked to 8% of adverse medical events and 30% of malpractice cases. To a greater extent than the evidence-based movement, the clinical reasoning literature asserts the importance of practitioner intuition—unconscious elements of diagnostic reasoning. The study aimed to analyse the content of case report summaries in ways that explored the importance of an evidence concept, not only in relation to research literature but also intuition. The study sample comprised all 789,712 abstracts in English for case reports contained in the database PUBMED for the period 1 January 1983 to 31 December 2012. It was hypothesised that, if evidence and intuition concepts were viewed by these clinical authors as essential to understanding their case reports, they would be more likely to be found in the abstracts. Computational linguistics software was used in 1) concept mapping of 21,631,481 instances of 201 concepts, and 2) specific concept analyses examining 200 paired co-occurrences for ‘evidence’ and research ‘literature’ concepts. ‘Evidence’ is a fundamentally patient-centred, intuitive concept linked to less common concepts about underlying processes, suspected disease mechanisms and diagnostic hunches. In contrast, the use of research literature in clinical reasoning is linked to more common reasoning concepts about specific knowledge and descriptions or presenting features of cases. ‘Literature’ is by far the most dominant concept, increasing in relevance since 2003, with an overall relevance of 13% versus 5% for ‘evidence’ which has remained static. The fact that the least present types of reasoning concepts relate to diagnostic hunches to do with underlying processes, such as what is suspected, raises questions about whether intuitive practitioner evidence-making, found in a constellation of dynamic, process concepts, has become less important. The study adds support to the existing corpus of research on clinical reasoning, by suggesting that intuition involves a complex constellation of concepts important to how the construct of evidence is understood. The list of concepts the study generated offers a basis for reflection on the nature of evidence in diagnostic reasoning and the importance of intuition to that reasoning.

The ever increasing volume of referrals from primary care to specialist services is putting considerable pressure on resource-constrained health services while effective communication across fragmented services remains a substantial challenge. Previous studies have suggested that electronic referrals (eReferral) can bear important benefits for cross-organisational processes and patient care management. We conducted 25 semi-structured interviews and 1 focus group with primary care providers to elucidate General Practitioners’ (GPs) perspectives on information management processes in the patient pathway in NHSScotland, 1 focus group with members of the Scottish Electronic Patient Record programme and one interview with a senior architect of the Scottish Care Information national eReferral System (SCI Gateway). Using Normalisation Process Theory, we performed a qualitative analysis to elucidate GPs’ perspectives on eReferral to identify the factors which they felt either facilitated or hindered referral processes. The majority of GPs interviewed felt that eReferral substantially streamlined communication processes, with the immediate transfer of referral documents and the availability of an electronic audit trail perceived as two substantial improvements over paper-based referrals. Most GPs felt that the SCI Gateway system was reasonably straightforward to use. Referral protocols and templates could be perceived as useful by some GPs while others considered them to be cumbersome at times. Our study suggests that the deployment and adoption of eReferral across the NHS in Scotland has been achieved by a combination of factors: (i) a policy context – including national mandatory targets for eReferral – which all NHS health-boards were bound to operationalise through their Local Delivery Plans and also (ii) the fact that primary care doctors considered that the overall benefits brought by the deployment of eReferral throughout the patient pathway significantly outweigh any potential disbenefits.