BackgroundThe vision of transforming health systems into learning health systems (LHSs) that rapidly and continuously transform knowledge into improved health outcomes at lower cost is generating increased interest in government agencies, health organizations, and health research communities. While existing initiatives demonstrate that different approaches can succeed in making the LHS vision a reality, they are too varied in their goals, focus, and scale to be reproduced without undue effort. Indeed, the structures necessary to effectively design and implement LHSs on a larger scale are lacking. In this paper, we propose the use of architectural frameworks to develop LHSs that adhere to a recognized vision while being adapted to their specific organizational context. Architectural frameworks are high-level descriptions of an organization as a system; they capture the structure of its main components at varied levels, the interrelationships among these components, and the principles that guide their evolution. Because these frameworks support the analysis of LHSs and allow their outcomes to be simulated, they act as pre-implementation decision-support tools that identify potential barriers and enablers of system development. They thus increase the chances of successful LHS deployment.DiscussionWe present an architectural framework for LHSs that incorporates five dimensions—goals, scientific, social, technical, and ethical—commonly found in the LHS literature. The proposed architectural framework is comprised of six decision layers that model these dimensions. The performance layer models goals, the scientific layer models the scientific dimension, the organizational layer models the social dimension, the data layer and information technology layer model the technical dimension, and the ethics and security layer models the ethical dimension. We describe the types of decisions that must be made within each layer and identify methods to support decision-making.ConclusionIn this paper, we outline a high-level architectural framework grounded in conceptual and empirical LHS literature. Applying this architectural framework can guide the development and implementation of new LHSs and the evolution of existing ones, as it allows for clear and critical understanding of the types of decisions that underlie LHS operations. Further research is required to assess and refine its generalizability and methods.

We propose a new method to mitigate (identify and address) adverse interactions (drug-drug or drug-disease) that occur when a patient with comorbid diseases is managed according to two concurrently applied clinical practice guidelines (CPGs). A lack of methods to facilitate the concurrent application of CPGs severely limits their use in clinical practice and the development of such methods is one of the grand challenges for clinical decision support. The proposed method responds to this challenge. We introduce and formally define logical models of CPGs and other related concepts, and develop the mitigation algorithm that operates on these concepts. In the algorithm we combine domain knowledge encoded as interaction and revision operators using the constraint logic programming (CLP) paradigm. The operators characterize adverse interactions and describe revisions to logical models required to address these interactions, while CLP allows us to efficiently solve the logical models - a solution represents a feasible therapy that may be safely applied to a patient. The mitigation algorithm accepts two CPGs and available (likely incomplete) patient information. It reports whether mitigation has been successful or not, and on success it gives a feasible therapy and points at identified interactions (if any) together with the revisions that address them. Thus, we consider the mitigation algorithm as an alerting tool to support a physician in the concurrent application of CPGs that can be implemented as a component of a clinical decision support system. We illustrate our method in the context of two clinical scenarios involving a patient with duodenal ulcer who experiences an episode of transient ischemic attack.

SummaryBackground: Asthma exacerbations are one of the most common medical reasons for children to be brought to the hospital emergency department (ED). Various prediction models have been proposed to support diagnosis of exacerbations and evaluation of their severity. Objectives: First, to evaluate prediction models constructed from data using machine learning techniques and to select the best performing model. Second, to compare predictions from the selected model with predictions from the Pediatric Respiratory Assessment Measure (PRAM) score, and predictions made by ED physicians. Design: A two-phase study conducted in the ED of an academic pediatric hospital. In phase 1 data collected prospectively using paper forms was used to construct and evaluate five prediction models, and the best performing model was selected. In phase 2 data collected prospectively using a mobile system was used to compare the predictions of the selected prediction model with those from PRAM and ED physicians. Measurements: Area under the receiver operating characteristic curve and accuracy in phase 1; accuracy, sensitivity, specificity, positive and negative predictive values in phase 2. Results: In phase 1 prediction models were derived from a data set of 240 patients and evaluated using 10-fold cross validation. A naive Bayes (NB) model demonstrated the best performance and it was selected for phase 2. Evaluation in phase 2 was conducted on data from 82 patients. Predictions made by the NB model were less accurate than the PRAM score and physicians (accuracy of 70.7%, 73.2% and 78.0% respectively), however, according to McNemar's test it is not possible to conclude that the differences between predictions are statistically significant. Conclusion: Both the PRAM score and the NB model were less accurate than physicians. The NB model can handle incomplete patient data and as such may complement the PRAM score. However, it requires further research to improve its accuracy. Research Article