Accurate classification of secondary progression in multiple sclerosis
Bibliographic record
Abstract
Abstract Transition from a relapsing-remitting to the secondary progressive phenotype is an important milestone in the clinical evolution of multiple sclerosis. In the absence of reliable imaging or biological markers of phenotype transition, assignment of current phenotype status relies on retrospective evaluation of the medical history of an individual. Here, we sought to determine if demographic and clinical information from multiple sclerosis patients can be used to accurately assign current disease phenotypes: either relapsing-remitting or secondary progressive status. Data from the most recent clinical visit of 14,387 multiple sclerosis patients were extracted from the Swedish Multiple Sclerosis Registry. Decision trees based on sex, symptom onset age, Expanded Disability Scale Status score, and age & disease duration at the most recent clinic visit, were examined to build a classifier to determine disease phenotype. Validation was conducted using an independent cohort of multiple sclerosis patients from British Columbia, Canada, and a previously published classifier to assign phenotype was also tested. Clinical records of 100 randomly selected patients were used to manually categorize phenotype by three independent neurologists. A decision tree (the classifier) containing only most recently available disability score and age obtained 89.3% (95% confidence intervals (CI): 88.8% to 89.8%) classification accuracy, defined as concordance with the latest reported status in the registry. Replication in an independent cohort from British Columbia resulted in 82.0% (95%CI: 81.0% to 83.1%) accuracy. A previously published classification algorithm with slight modifications achieved 77.8% (95%CI: 77.1% to 78.4%) accuracy when assigning disease phenotype. With complete patient history data, three neurologists obtained 84.7% accuracy on average compared with 85 for the classifier using the same data. The model is easily interpretable and could allow research studies and randomized clinical trials to estimate the probability of patients having already reached the secondary progressive stage when they have not yet been retrospectively assigned this status, and to standardize definitions of disease phenotype across different cohorts. Clinically, this model could assist neurologists by providing additional information about the probability of having secondary progressive disease. This could also benefit patients who may be introduced to new therapies targeting progressive multiple sclerosis.
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 | 0.010 |
| 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 | 0.001 |
| 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".