Generalizability of the Disease State Index Prediction Model for Identifying Patients Progressing from Mild Cognitive Impairment to Alzheimer's Disease
Bibliographic record
Abstract
BACKGROUND: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. OBJECTIVES: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. METHODS: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 × 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). RESULTS: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. CONCLUSIONS: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".