The Learning Health System (LHS) describes linking routine healthcare systems directly with both research translation and knowledge translation as an extension of the evidence-based medicine paradigm, taking advantage of the ubiquitous use of electronic health record (EHR) systems. TRANSFoRm is an EU FP7 project that seeks to develop an infrastructure for the LHS in European primary care. Methods. The project is based on three clinical use cases, a genotype-phenotype study in diabetes, a randomised controlled trial with gastroesophageal reflux disease, and a diagnostic decision support system for chest pain, abdominal pain, and shortness of breath. Results. Four models were developed (clinical research, clinical data, provenance, and diagnosis) that form the basis of the projects approach to interoperability. These models are maintained as ontologies with binding of terms to define precise data elements. CDISC ODM and SDM standards are extended using an archetype approach to enable a two-level model of individual data elements, representing both research content and clinical content. Separate configurations of the TRANSFoRm tools serve each use case. Conclusions. The project has been successful in using ontologies and archetypes to develop a highly flexible solution to the problem of heterogeneity of data sources presented by the LHS.

BackgroundObservational and experimental studies of the diagnostic task have demonstrated the importance of the first hypotheses that come to mind for accurate diagnosis. A prototype decision support system (DSS) designed to support GPs’ first impressions has been integrated with a commercial electronic health record (EHR) system.AimTo evaluate the prototype DSS in a high-fidelity simulation.Design and settingWithin-participant design: 34 GPs consulted with six standardised patients (actors) using their usual EHR. On a different day, GPs used the EHR with the integrated DSS to consult with six other patients, matched for difficulty and counterbalanced.MethodEntering the reason for encounter triggered the DSS, which provided a patient-specific list of potential diagnoses, and supported coding of symptoms during the consultation. At each consultation, GPs recorded their diagnosis and management. At the end, they completed a usability questionnaire. The actors completed a satisfaction questionnaire after each consultation.ResultsThere was an 8–9% absolute improvement in diagnostic accuracy when the DSS was used. This improvement was significant (odds ratio [OR] 1.41, 95% confidence interval [CI] = 1.13 to 1.77, P<0.01). There was no associated increase of investigations ordered or consultation length. GPs coded significantly more data when using the DSS (mean 12.35 with the DSS versus 1.64 without), and were generally satisfied with its usability. Patient satisfaction ratings were the same for consultations with and without the DSS.ConclusionThe DSS prototype was successfully employed in simulated consultations of high fidelity, with no measurable influences on patient satisfaction. The substantially increased data coding can operate as motivation for future DSS adoption.

BackgroundMultimorbidity, defined as the presence of at least two chronic conditions, becomes increasingly common in older people and is associated with poorer health outcomes and significant polypharmacy. The National Institute for Clinical Excellence (NICE) recently published a multimorbidity guideline that advises providing an individualised medication review for all people prescribed 15 or more repeat medicines. This study incorporates this guideline and aims to assess the effectiveness of a complex intervention designed to support general practitioners (GPs) to reduce potentially inappropriate prescribing and consider deprescribing in older people with multimorbidity and significant polypharmacy in Irish primary care.MethodsThis study is a cluster randomised controlled trial, involving 30 general practices and 450 patients throughout Ireland. Practices will be eligible to participate if they have at least 300 patients aged 65 years and over on their patient panel and if they use either one of the two predominant practice management software systems in use in Ireland. Using a software patient finder tool, practices will identify and recruit patients aged 65 years and over, who are prescribed at least 15 repeat medicines. Once baseline data collection is complete, practices will be randomised using minimisation by an independent third party to either intervention or control. Given the nature of the intervention, it is not possible to blind participants or study personnel. GPs in intervention practices will receive login details to a website where they will access training videos and a template for conducting an individualised structured medication review, which they will undertake with each of their included patients. Control practices will deliver usual care over the 6-month study period. Primary outcome measures pertain to the individual patient level and are the proportion of patients with any PIP and the number of repeat medicines.DiscussionDisease-specific approaches in multimorbidity may be inappropriate and result in fragmented and poorly co-ordinated care. This pragmatic study is evaluating a complex intervention that is relevant across multiple conditions and addresses potential concerns around medicines safety in this vulnerable group of patients. The potential for system-wide implementation will be explored with a parallel mixed methods process evaluation.Trial registration ISRCTN: 12752680, Registered 20 October 2016.

Decision support systems are used as a method of promoting consistent guideline-based diagnosis supporting clinical reasoning at point of care. However, despite the availability of numerous commercial products, the wider acceptance of these systems has been hampered by concerns about diagnostic performance and a perceived lack of transparency in the process of generating clinical recommendations. This resonates with the Learning Health System paradigm that promotes data-driven medicine relying on routine data capture and transformation, which also stresses the need for trust in an evidence-based system. Data provenance is a way of automatically capturing the trace of a research task and its resulting data, thereby facilitating trust and the principles of reproducible research. While computational domains have started to embrace this technology through provenance-enabled execution middlewares, traditionally non-computational disciplines, such as medical research, that do not rely on a single software platform, are still struggling with its adoption. In order to address these issues, we introduce provenance templates - abstract provenance fragments representing meaningful domain actions. Templates can be used to generate a model-driven service interface for domain software tools to routinely capture the provenance of their data and tasks. This paper specifies the requirements for a Decision Support tool based on the Learning Health System, introduces the theoretical model for provenance templates and demonstrates the resulting architecture. Our methods were tested and validated on the provenance infrastructure for a Diagnostic Decision Support System that was developed as part of the EU FP7 TRANSFoRm project.