Advanced machine learning applications in fibromyalgia to assess the relationship between 3D spinal alignment with clinical outcomes
Bibliographic record
Abstract
This study leveraged machine learning (ML) models to explore the relationship between three-dimensional (3D) spinal alignment parameters and clinical outcomes in patients suffering from fibromyalgia syndrome (FMS). A cohort of 303 FMS patients, diagnosed according to the 2016 American College of Rheumatology criteria, underwent comprehensive assessments of sagittal imbalance, coronal imbalance, vertebral rotation, pelvic obliquity, pelvic torsion, and pelvic rotation using a validated 3D imaging system. Clinical outcomes, included the fibromyalgia impact questionnaire (FIQ), pain catastrophizing scale (PCS), Pittsburgh sleep quality index (PSQI), and algometric pain scores. Five ML models were employed: Fast Kolmogorov-Arnold Networks with Bee Colony Optimization (FastKAN-BCO), FastKAN with LBFGS, Multilayer Perceptron with LBFGS (MLP-LBFGS), Multilayer Perceptron with ADAM (MLP-ADAM), and linear regression. Among the models tested, FastKAN-BCO demonstrated the highest R-squared value (0.95) for algometric pain, while the MLP-LBFGS model achieved superior performance for PCS (R 2 = 0.94), FIQ (R 2 = 0.88), and PSQI (R 2 = 0.97) predictions. Sagittal imbalance and pelvic obliquity were identified as key predictors of symptom severity. Stratification revealed that individuals with more pronounced pelvic asymmetry and vertebral rotation exceeding 10° experienced increased symptom intensity. The contribution of vertebral rotation was nonlinear, indicating a threshold-dependent impact. This study illustrates the potential of ML techniques to uncover complex associations between 3D spinal alignment and FMS outcomes, offering a foundation for personalized diagnostic and therapeutic approaches. The results emphasize the critical role of postural dysfunction in FMS and highlight the potential of advanced ML models.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.000 | 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".