Classification of chronic pain and spinal cord stimulation response using machine learning in magnetoencephalography data
Bibliographic record
Abstract
BACKGROUND: Due to the complexity of pain, involving physical, psychological, emotional and social aspects, we are still unable to objectively quantify or fully understand this subjective experience. An increasing number of studies have attempted to identify biomarkers of pain using brain imaging tools like magnetoencephalography (MEG). In this study, we used machine learning to investigate the potential of MEG data as a biomarker for chronic pain and used this biomarker to quantify spinal cord stimulation (SCS) treatment effect. METHODS: The study population consisted of 25 patients with SCS, for whom we recorded resting-state MEG during tonic, burst and sham stimulation, 25 patients with chronic pain and 25 pain-free controls. We derived average power spectral densities across each of the 94 automated anatomical labeling atlas based brain regions and extracted six spectral features: the alpha peak frequency, alpha power ratio, and average power across the theta, alpha, beta, and low-gamma bands. Based on these features, we used automated machine learning to find the optimal combination of machine learning methods to create classification and regression models for pain and pain intensity. RESULTS: The theta power and alpha power ratio were the most promising features to classify chronic pain with an accuracy of 76%. The classification model outputs and self-reported pain scores of patients with SCS showed a Spearman correlation coefficient of 0.12. A regression model based on pain scores of all participants showed Spearman correlation coefficients between 0.27 and 0.41. CONCLUSION: This study achieved a promising 76% accuracy in classifying patients with chronic pain and pain-free controls using the theta power or alpha power ratio. However, this model's output poorly correlated with pain scores of patients with SCS. A larger variety of input features and outcome parameters is recommended.
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 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".