Clinically Significant Information Extraction from Radiology Reports
Bibliographic record
Abstract
Radiology reports are one of the most important medical documents that a diagnostician looks into, especially in the emergency context. They provide the emergency physicians with critical information regarding the condition of the patient and help the physicians take immediate action on urgent conditions. However, the reports are in the form of unstructured text, which makes them time consuming for humans to interpret. We have developed a machine learning system to (a) efficiently extract the clinically significant parts and their level of importance in radiology reports, and (b) to classifies the overall report into critical or non-critical categories which help doctors to identify potential high priority reports. As a starting point, the system uses anonymized chest X-RAY reports of adults and provides three levels of importance for medical phrases. We used the Conditional Random Field (CRF) model to identify clinically significant phrases with an average f1-score of 0.75. The proposed system includes a web-based interface which highlights the medical phrases, and their level of importance to the emergency physician. The overall classification of the report is performed using the phrases extracted from the CRF model as features for the classifier. Average accuracy achieved is 85%.
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 | 0.001 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".