A comparison of biomarker modalities for predicting disease progression in dementia patients
Bibliographic record
Abstract
Dementia encompasses a group of neurodegenerative disorders that pose a major public health challenge, particularly in consideration of the aging global population. Accurate prediction of disease progression is crucial for effective treatment planning for affected patients. This study explores two novel machine learning (ML) models for predicting cognitive decline in patients with dementia within a predictive horizon of 22–38 months. Cognitive change was assessed in this work using the Montreal Cognitive Assessment (MoCA) score as the output of interest, and predicted using baseline data consisting of either cerebrospinal fluid (CSF) biomarkers or T1-weighted magnetic resonance imaging (MRI) data. Therefore, data collected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the National Alzheimer’s Coordinating Center (NACC) was utilized to develop and evaluate the ML models, focusing on patients diagnosed with mild cognitive impairment or one of the varying forms of dementia, including Alzheimer’s disease, vascular dementia, Lewy body dementia, or frontotemporal dementia. The models developed, optimized, and compared in this study include a XGBoost model for analyzing tabular CSF data and a convolutional neural network for the structural T1-weighted MRI data. For each model, a total of 388 patients were considered, split into 272/58/58 for training/validation/testing. The results of the comparison analysis revealed that the CSF model achieved 73.1% accuracy with a ROC-AUC of 77.0%, while the MRI model attained 65.1% accuracy with a ROC-AUC of 73.5%. Saliency maps for the MRI model highlighted brain regions typically affected by dementia, confirming the model’s ability to learn relevant structural biomarkers from the T1-weighted images. Overall, this study presents a novel comparison analysis for predicting the severity of patient cognitive decline using two distinct and widely used data modalities in a diverse cohort of patients with dementia.
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 | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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".