An Evidence-Based Health Care Knowledge Integration System: Assessment Protocol (Preprint)
Bibliographic record
Abstract
BACKGROUND The rapid advancements in health care can make it difficult for general physicians and specialists alike to keep their knowledge up to date. In medicine today, there are deficiencies in the application of knowledge translation (KT) in clinical practice. Some medical procedures are not required, and therefore, no value is added to the patient’s care. These unnecessary procedures increase pressures on the health care system’s resources, reduce the quality of care, and expose the patients to stress and to other potential risks. KT tools and better access to medical recommendations can lead to improvements in physicians’ decision-making processes depending on the patient’s specific clinical situation. These tools can provide the physicians with the available options and promote an efficient professional practice. Software for the Evolution of Knowledge in MEDicine (SEKMED) is a technological solution providing access to high-quality evidence, based on just-in-time principles, in the application of medical recommendations for clinical decision-making processes recognized by community members, accreditation bodies, the recommendations from medical specialty societies made available through campaigns such as Choosing Wisely, and different standards or accreditive bodies. OBJECTIVE The main objective of this protocol is to assess the usefulness of the SEKMED platform used within a real working clinical practice, specifically the Centre intégré de santé et des services sociaux de l’Outaouais in Quebec, Canada. To achieve our main objective, 20 emergency physicians from the Hull and Gatineau Hospitals participate in the project as well as 20 patient care unit physicians from the Hull Hospital. In addition, 10 external students or residents studying family medicine from McGill University will also participate in our study. METHODS The project is divided into 4 phases: (1) orientation; (2) data synthesis; (3) develop and validate the recommendations; and (4) implement, monitor, and update the recommendations. These phases will enable us to meet our 6 specific research objectives that aim to measure the integration of recommendations in clinical practices, the before and after improvements in practices, the value attributed by physicians to recommendations, the user’s platform experience, the educational benefits according to medical students, and the organizational benefits according to stakeholders. The knowledge gained during each phase will be applied on an iterative and continuous basis to all other phases over a period of 2 years. RESULTS This project was funded in April 2018 by the Fonds de soutien à l’innovation en santé et en services sociaux for 24 months. Ethics approval has been attained, the study began in June 2018, the data collection will be complete at the end of December 2019, and the data analysis will start in winter 2020. Both major city hospitals in the Outaouais region, Quebec, Canada, have agreed to participate in the project. CONCLUSIONS If results show preliminary efficacy and usability of the system, a large-scale implementation will be conducted. INTERNATIONAL REGISTERED REPOR DERR1-10.2196/11754
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.090 | 0.206 |
| Meta-epidemiology (narrow) | 0.002 | 0.003 |
| Meta-epidemiology (broad) | 0.004 | 0.007 |
| Bibliometrics | 0.006 | 0.009 |
| Science and technology studies | 0.005 | 0.003 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.007 | 0.010 |
| Insufficient payload (model declined to judge) | 0.129 | 0.030 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".