Evaluation of Thyroid Ultrasound Report Quality and Assessing Effect of Adherence to Risk Stratification Criteria on Referral for Thyroid Nodule Biopsy
Bibliographic record
Abstract
Purpose: This study aims to evaluate the quality of diagnostic thyroid ultrasound reports and determine the impact of consistent adherence to 2015 American Thyroid Association (ATA) and 2017 American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) on reducing unnecessary referrals for thyroid nodule biopsy. Materials and Methods: Reports from 291 referrals for thyroid nodule biopsy were included for retrospective report evaluation (males: 42; mean age: 56) according to 2015 ATA and ACR TI-RADS lexicon. Cytology results were collected for each patient. Two radiologists blinded to cytology results independently, retrospectively reviewed imaging of the referrals, and rescored them according to 2015 ATA and 2017 ACR TI-RADS risk stratification systems. Statistical analysis was completed using chi-square analysis and calculation of κ statistic for interobserver variability. Results: No report completely addressed all features associated with malignancy. Over half of the reports did not include descriptors on echogenicity, shape, margin, or echogenic foci. In all, 9.3% of biopsies showed malignant histology. Rescoring of referrals demonstrated decrease in biopsy referrals by 55% as per 2017 ACR TI-RADS and 14% as per 2015 ATA ( P < .0001). There was no impact on detection of malignancy with adherence to ATA or ACR criteria and less interobserver variability with application of 2017 ACR TI-RADS compared to 2015 ATA. Conclusion: Thyroid ultrasound report quality was found variable with respect to nodule description. Reports recommended biopsy based on nodule size with no detailed description of other imaging features. Adherence to risk stratification system would have resulted in significant reduction in the number of unnecessary biopsy referrals.
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 | 0.042 | 0.160 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".