EP24.03: Prediction of MBS item number and rASRM stage based on deep endometriosis ultrasound
Bibliographic record
Abstract
In March 2022 Australian Medicare Benefits Schedule updated gynecological item numbers relating to endometriosis surgery. Specific item numbers include 35637, 35631 and 35632 (a division of 35638) and 35641 (14). Each item number correlates to staging as per the rAFS (rASRM) stage 1-4, respectively. We aimed to predict to predict four MBS item numbers using ultrasound. A retrospective multicentre study conducted across five countries and six centres from August 2018-November 2019 assessing ultrasound-based rASRM (rASRM-U) correlating with MBS item numbers. This data was also used to evaluate diagnostic accuracy of predicting deep endometriosis following the IDEA consensus with results previously published. Subgroup analysis was performed by dichotomising both ultrasound and surgical stage and MBS item into low and high stage rather than four stage system. 273 patients were included, 54 excluded due to incomplete data. 219 remained for analysis. Prediction of MBS item by rASRM-U stage showed weak agreement with weighted Kappa value 0.31 (0.24 to 0.38, 95% CI). rASRM-U predicted a 0.68 higher surgical stage, alongside large variability with limits of agreement of +/- 1.62 this supports 'over-staging'. Although generally poor for low stage item numbers, there was a sensitivity of 0.96 and specificity 0.44 predicting item 35641. Dichotomised staging shows sensitivity in rASRM-U predicting high stage of 0.99 with specificity 0.34 and NPV 0.95. Prediction of low stage shows sensitivity 0.34, specificity 0.99 and NPV 0.79. The IDEA consensus-based rASRM-U has relatively poor agreement with corresponding MBS item numbers and tends to predict a ‘higher’ stage item. This model is unlikely to predict low stages incorrectly. Although unable to accurately predict individual item numbers for endometriosis surgery, this system was identifies high vs low surgical complexity when ultrasound and surgical groups are dichotomised, and thus could allow for improved surgical planning and financial consent.
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 | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 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) | 0.009 | 0.003 |
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".