A pattern recognition approach to the development of a classification system for upper-limb musculoskeletal disorders of workers
Bibliographic record
Abstract
OBJECTIVES: Workers' musculoskeletal disorders are often pain-based and elude specific diagnoses; yet diagnosis or classification is the cornerstone to researching and managing these disorders. Clinicians are skilled in pattern recognition and use it in their daily practice. The purpose of this study was to use the clinical reasoning of experienced clinicians to recognize patterns of signs and symptoms and thus create a classification system. METHODS: Two hundred and forty-two workers consented to a standardized physical assessment and to completing a questionnaire. Each physical assessment finding was dichotomized (normal versus abnormal), and the results were graphically displayed on body diagrams. At two different workshops, groups of experienced researchers or clinicians were led through an exercise of pattern recognition (clustering and naming of clusters) to arrive at a classification system. Interobserver reliability was assessed (8 observers, 40 workers), and the classification system was revised to improve reliability. RESULTS: The initial classification system had good face validity but low interobserver reliability (kappa <0.3). Revisions were made that resulted in a proposed triaxial classification system. The signs and symptoms axes quantified the areas in the involved upper limbs. The proposed third axis described the likelihood of a specific clinical diagnosis being made and the degree of certainty. The interobserver reliability improved to approximately 0.70. CONCLUSIONS: This triaxial classification system for musculoskeletal disorders is based on clinically observable findings. Further testing and application in other populations is required. This classification system could be useful for both clinicians and epidemiologists.
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 | 0.021 | 0.063 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.008 | 0.004 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".