Surface Topography Classification Trees for Assessing Severity and Monitoring Progression in Adolescent Idiopathic Scoliosis
Bibliographic record
Abstract
STUDY DESIGN: A validation study. OBJECTIVE: The aim of this study was to independently validate the diagnostic accuracy of surface topography (ST) classification trees to identify curve severity and progression using a new sample of data in participants with adolescent idiopathic scoliosis (AIS). SUMMARY OF BACKGROUND DATA: Radiographs for diagnosing and monitoring AIS involve harmful radiation exposure repeated at successive clinical visits. Classification trees using a novel ST technique have been proposed to determine curve severity and progression noninvasively that could be used to monitor scoliosis. METHODS: Forty-five adolescents with AIS treated nonoperatively, with ST scans and radiographs at baseline and follow-up (1 year later), were recruited from a scoliosis clinic. The Cobb angle (CA) from radiographs determined curve severity as mild (10° < CA < 25°) or moderate/severe (CA ≥ 25°) and progression as an increase >5°.ST scans were analyzed to calculate the best plane of symmetry and associated deviation color map. Root mean squares and maximum deviation were calculated for each area of asymmetry. ST measurements were analyzed using two published decision trees developed to maximize sensitivity and negative predictive value. Curves were classified as mild or moderate/severe and curve progression was predicted. Accuracy statistics were calculated to evaluate performance. RESULTS: For curve severity, sensitivity and specificity were 95% and 35%, respectively. Negative and positive predictive values were 90% and 53%, respectively, with an accuracy of 61%. For curve progression, sensitivity and specificity were 73% and 44%, respectively. Negative and positive predictive values were 83% and 30%, respectively, with an accuracy of 51%. Assuming that mild and nonprogressive curves would not require an x-ray, the use of ST decision trees could eliminate 31% of x-rays. CONCLUSION: Decision trees showed strong negative predictive values and sensitivity suggesting it may be possible to safely use ST asymmetry analysis with validated decision trees to reduce x-rays in patients with mild and nonprogressive curves. LEVEL OF EVIDENCE: 2.
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 | 0.011 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.001 | 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".