Improving Patient-Clinical Trial Matching Using Convolution Neural Networks
Bibliographic record
Abstract
Clinical trial matching is critical for identifying the most suitable trials for patients based on their unique medical profiles. Traditionally, this process relies on manual screen-ing by medical professionals, which is labour-intensive and inefficient, especially considering the vast number of available trials. Recent advancements explored automating this process, with large language models (LLMs) emerging as a popular solution. These models extract inclusion and exclusion criteria from unstructured patient data, encode the criteria from trials, and utilize cosine similarity to rank potential matches. However, a significant limitation of this approach lies in the interpretability of the cosine similarity scores—how and why the matches are produced often remain unclear. Our method introduces a method that combines a fine-tuned LLM for criteria generation with cosine similarity-based matching and is reinforced by symbolic reasoning to validate and enhance the interpretability of trial outcomes. Integrating neural network outputs with symbolic reasoning techniques represents a step forward in neuro-symbolic AI, aiming to provide accurate and explainable trial-matching results. The potential implications of this work are significant, offering a more reliable and transparent method for clinical trial matching that could improve patient outcomes and foster greater trust in AI-driven medical applications by validating and reinforcing the decisions of LLM and cosine similarity through additional layers of symbolic reasoning.
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 | 0.010 | 0.051 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".