Customized k-nearest neighbourhood analysis in the management of adolescent idiopathic scoliosis using 3D markerless asymmetry analysis
Bibliographic record
Abstract
Adolescent Idiopathic Scoliosis (AIS) is a 3D spinal deformity characterized by curvature and rotation of the spine. Markerless surface topography (ST) analysis has been proposed for diagnosing and monitoring AIS to reduce the X-ray radiation exposure to patients. This method captures scans of the cosmetic deformity of the torso using visible, radiation-free light. The asymmetry analysis of the torso, represented as a deviation contour map with deviation patches outlining the areas of cosmetic asymmetries, has previously been shown to predict the severity and progression of the condition in comparison with radiographs, by using classification trees. While the classification results were promising, it was reported that some mild curves were erroneously diagnosed. Furthermore, this approach is highly sensitive to threshold values selected in the decision trees. Therefore, this study aims to define a custom Neighbourhood Classifier algorithm for AIS classification to improve the accuracy, sensitivity, and specificity of predicting curve severity and curve progression in AIS. Curve severity was predicted with 80% accuracy (sensitivity = 81%; specificity = 79%) for thoracic-thoracolumbar curves and 72% (sensitivity = 93%; specificity = 53%) for lumbar curves. This represents an improvement over the previous method with curve severity accuracies of 77% and 63% for thoracic-thoracolumbar and lumbar curves, respectively. Additionally, curve progression was predicted with 93% accuracy (sensitivity = 83%; specificity = 95%) representing a substantial improvement over the previous method with an accuracy of 59%. The current method has shown the potential to further reduce radiation exposure for AIS patients by avoiding X-rays for mild and non-progressive curves identified using ST analysis.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".