Bibliographic record
Abstract
Practicing evidence-based medicine relies on identifying related evidences like medical literature or clinical trial which include credible information related to the clinical case where such evidence typically contains imaging and non-imaging data. However, classical machine learning techniques rely on using monomodal learning that process only a single modality (e.g. text, images or videos). Although this type of learning has provided extraordinary results in clinical science including diagnosis and prognosis, it has limited usage capabilities related to precision and evidence-based medicine. Multimodal learning, however, utilizes techniques to process and find relationships between different types of data modalities to comprehend the case description as some clinical cues exist only in certain modalities. Actually in clinical practice, clinicians use imaging modalities like computed tomography (CT) scans or X-ray images beside non-image modalities like electroencephalogram (EEG) data or tabular data used in the electronic healthcare records to describe clinical cases. In this article we are presenting a multimodal machine framework that can be used for evidence-based practice using fine tuned MedCLIP transformer model to fetch relevant PubMed articles based on three different scenarios of usage where clinicians can provide multimodal queries in their search for relevant PubMed articles.
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 | 0.007 | 0.027 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".