Neural networks to estimate multiple sclerosis disability and predict progression using routinely collected healthcare data
Bibliographic record
Abstract
BACKGROUND AND OBJECTIVES: Multiple sclerosis (MS)-related disability is conventionally measured using the Expanded Disability Status Scale (EDSS), which requires neurological examination and is generally embedded in clinical records, making it unavailable in administrative datasets. This limits its utility for population-level estimates and healthcare planning. This study aims to use routinely collected healthcare data to fill this gap. METHODS: We conducted a population-based study using administrative data from Campania Region (Italy) to develop and validate neural network algorithms to estimate MS-related disability and predict its progression (2015-2021). We employed a deep learning approach to estimate the EDSS, and a hybrid model combining survival analysis with neural network predictions to forecast the risk of EDSS progression. RESULTS: The model estimated EDSS with 0.68 accuracy, 0.68 precision, and 0.67 F1-score. The hybrid model had a predictive performance of 0.92. From 2016 to 2021, 9.01% of the population had EDSS ⩽ 3.0, 62.10% had EDSS between 3.5 and 5.5, and 28.89% had EDSS ⩾ 6.0. Looking at projections from 2021 to 2026, 67.68% people with EDSS ⩽ 3.0 are expected to progress to EDSS 3.5-5.5. CONCLUSION: These findings highlight the potential of advanced data analytics using administrative data to improve MS monitoring, healthcare planning, and decision-making.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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 | 0.000 |
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".