Classifying chronic pain conditions using deep learning and resting-state fMRI
Bibliographic record
Abstract
Introduction: Due to its comorbidities with other symptoms and lack of effective treatments, chronic pain is considered a complex disease. At the same time, advancements in brain imaging, the spread of machine learning methods, and the creation of new diagnostic tools based on these technologies have demonstrated that these tools may be an option for assisting healthcare professionals in making decisions. However, a growing body of research in neuroimaging suggests that functional networks show dynamic changes in connection strength as well as variable phase difference (nonzero time-lag) between regions. Our goal is to compare performances in developing and evaluating deep learning (DL) and traditional machine learnings (MLs) in predicting chronic pain.Methods: A resting state functional MRI (rsfMRI) data with pain status were obtained from UK BioBank (UKBB) 6500 dataset. We computed functional brain activity to evaluate how well the 6 ML models (i.e., K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), AdaBoost (Ada), LightGBM (GBM) and convolutional neural network (CNN), categorized chronic pain patients and pain-free controls in this study. They were compared using Area Under the Curve (AUC).Results: Training a CNN with preprocessed images produced the best results. CNN has an AUC of 0.69 compared to KNN (AUC = 0.52), LR (AUC = 0.55), RF (AUC = 0.54), XGB (AUC = 0.54), Ada (AUC = 0.52), and GBM (AUC = 0.54).Conclusion: The idea that resting-state fMRI data could be used as a biomarker for chronic pain conditions is supported by these findings.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".