MON-526 Comparison of ACR-TIRADS to American Thyroid Association Guidelines: Can We Choose Wisely Without Missing Malignancy?
Bibliographic record
Abstract
Abstract Thyroid ultrasound has been widely used to determine which nodules need further work up. The goal of this study was to apply the new ACR-TIRADs criteria to a retrospective data set and compare the outcomes to the ATA scoring system. Methods: In a retrospective study, ultrasonographic images of the all nodules biopsied in 2015 were reviewed by radiologists, blinded to fine needle aspiration (FNA) biopsy result, using a checklist to report the image. The checklist was prepared based on 2015 ATA guideline. The ultrasonographic characteristics of thyroid nodules were compared with the result of biopsy to determine positive predictive value (PPV), negative predictive value (NPV), sensitivity and specificity of checklist in predicting malignancy. These results were published previously. The same data was then reviewed using the ACR-TiRADS tool to assess the number of US and FNA that would been avoided and the number of non-benign cytologies that would have been avoided had these criteria guided care in 2015. Results: 419 thyroid nodules were reviewed 7.1% were malignant, 10.3% were FLUS and 78.3% were benign. Sensitivity of the ACR-TIRADs and ATA respectively was to detect non-benign nodules was 70% and 97% Specificity was 29% and 11%. Positive predictive value was 18% and 9% whereas Negative predictive value was 81% and 98%. 28% of the FNAs done in 2015 could have been avoiding if applying the TIRADs criteria, however 15 non-benign and 8 malignant cases would have been missed.Conclusion: The TIRADs approach adds value to the system by reducing many unnecessary biopsies but clinicians need to use their own judgement as some non-benign cases will be missed.
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 | 0.018 | 0.066 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".