Recent Clinical Datasets in Supporting the Clinical Decision: A Portuguese Case Study
Bibliographic record
Abstract
The evaluation of a patient's condition is a challenging task that physicians have to deal with in their daily clinical practice, as there are some specific conditions where the diagnosis is not straightforward.Therefore, clinical guidelines frequently recommend the use of models that were developed with the objective of aiding the clinical decision.However, these models have some significant flaws, namely under specific conditions can present a lack of performance.Moreover, large datasets that resulted from patients data gathered directly in the hospital or through telemonitoring systems are available.These datasets may comprise very useful information in order to complement the current clinical knowledge on a specific disease/condition.The proposed approach addresses this issue, through three different perspectives: i) improving the representation of current clinical knowledge (model enhancement); ii) knowledge discovery strategies, able to extract useful new knowledge from existent clinical datasets; iii) flexible combination schemes that allow the combination of the new knowledge directly extracted from the datasets with the current clinical models.This work is being developed in the context of cardiovascular disease (CVD), namely in the identification of the CVD risk of each patient as the correct stratification of patients may significantly contribute to the optimization of the health care strategies.A dataset made available by the Portuguese Society of Cardiology (PSC) comprising 11112 patients with acute coronary syndrome gathered between 1 st of October 2010 and 6 th of November 2014 is applied to support the present work.Some preliminary results were achieved, showing the potential of the proposed strategy to aid the clinical decision.
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 | 0.009 | 0.043 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".