Objective Bi-Modal Assessment of Knee Osteoarthritis Severity Grades: Model and Mechanism
Bibliographic record
Abstract
Knee osteoarthritis (KOA), a common musculoskeletal disorder, is typically diagnosed by assessing patients’ X-rays. This method may have potential implications for health, especially with long-term and repeated examinations. In this study, we propose a KOA severity prediction (SP) model that utilizes bi-modal data, thermal image combined with personal health data, to objectively classify KOA severity into three categories, following the Kellgren-Lawrence (KL) grading criterion. We establish, for the first time, the KOA dataset and evaluate it with the KOA SP model, achieving the classification accuracy of 89.29%. The generalization of the KOA SP model is validated using data from the other centers, attaining the accuracy of 70.83%. The mechanism of KOA SP model is verified by utilizing the theory of thermal resistance in heat conduction and the anatomy of knee joint. The KOA SP model is developed by modeling handcrafted bi-modal features using gradient boosting tree, and we explain the reasons for not using deep neural networks, based on Vapnik-Chervonenkis dimension (VC dimension), from the perspective of the initial and appropriate feature representation of the task. The KOA SP model is anticipated to significantly alleviate the burden on physicians in assessing the severity of the disease, offering crucial supplementary data for knee disease diagnosis, thereby enhancing both efficiency and diagnostic precision in the KOA field. The KOA dataset and the corresponding code can be accessed publicly athttps://github.com/chenjjsx/KOA.git.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".