Family Medicine Forum Research Proceedings 2014/Compte rendu sur la recherche au Forum en médecine familiale 2014
Bibliographic record
Abstract
Context Cardiovascular disease is the most prevalent chronic medical condition in Canada. A strategy of managing cardiovascular disease risk based on routinely performing personalized risk estimates and progressively targeting interventions toward risk factors can reduce morbidity and mortality. One barrier to the widespread adoption of such a risk stratification approach in clinical practice is the lack of an easy-to-use tool that provides risk-based recommendations and encourages shared decision making. Objective To develop a patient-centred, clinical decision support tool for the primary prevention of cardiovascular disease that encourages evidence-based decision making. Design Systematic review. Methods The clinical practice guideline database of the Canadian Medical Association was reviewed for guidelines focused on the primary prevention of cardiovascular disease in adult populations. Review of the guidelines led to a search of PubMed for multivariable risk algorithms (key words: Framingham heart study) and a search of the Cochrane database for meta-analyses of recommended interventions (key words: cardiovascular disease and prevention); if meta-analyses were unavailable, PubMed was searched for randomized controlled trials. Results We created a Web-based application (www.cardiovascularcalculator.radarhill.net) that provides personalized multivariable risk estimates of developing coronary artery disease and stroke over the next 10 years based on age, sex, smoking status, family history of early coronary artery disease, systolic blood pressure, use of antihypertensive medication, and lipid profile. The application also presents personalized, risk-based recommendations for lifestyle modification and pharmaceutical intervention from 5 Canadian guidelines for the prevention of cardiovascular disease, in addition to modified risk estimates for developing cardiovascular disease over the next 10 years for selected interventions (smoking cessation, treatment of blood pressure with various agents and to various targets, treatment with cholesterol-lowering agents, and treatment with antiplatelet medication) and risk estimates of developing treatment-related adverse events. Outcomes are presented both graphically and numerically, as absolute risks with accompanying numbers-needed-to-treat estimates and optional confidence intervals. Conclusion We have developed an interactive, Web-based clinical decision support tool that can conveniently assess coronary heart disease and stroke risk and provide personalized, guideline-based recommendations with evidence-based risk reduction estimates for various lifestyle and pharmaceutical interventions. Research | FMF Research Proceedings 2014
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 | 0.021 | 0.049 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.006 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.098 | 0.011 |
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".