Exploring fall‐related hospitalizations following a new dementia diagnosis using prescribing clusters: a population‐based cohort study in Ontario, Canada
Bibliographic record
Abstract
BACKGROUND: Older adults living with dementia are a heterogenous population which can make studying optimal medication management challenging. Hierarchical clustering, an unsupervised machine learning method, can be used to summarize complex patterns of concurrently prescribed drug therapies across individuals. We aimed to determine if prescribing clusters (derived by grouping individuals dispensed similar medications) were associated with fall-related hospitalizations in older adults living with dementia. METHOD: We identified a cohort of 99,046 older adults (aged ≥67 years) recently diagnosed with dementia in Ontario, Canada between 2014 and 2016 using health administrative data. Individuals were assigned to one of six distinct prescribing clusters: high cardiovascular (angiotensin-converting enzyme-specific) (22.6% of the population), central nervous system active (21.3%), hypothyroidism (22.9%), respiratory (3.9%), and angiotensin receptor blocker-specific cardiovascular (6.1%), and a group with lower dispensation of medications in general (23.1%)). The outcome was fall-related hospitalizations (emergency department or acute care) over one year following the dementia diagnosis. Cause-specific survival models estimated the hazard of fall-related hospitalizations by prescribing cluster, accounting for demographic characteristics, chronic conditions, and history of Beers criteria medications. RESULT: Five percent of the cohort experienced a fall-related hospitalization within the first year of physician-diagnosed dementia, with highest prevalence in the CNS-active cluster (5.3%) and the lowest in general low medication use cluster (4.1%). The CNS-active cluster had a significantly higher relative hazard of fall-related hospitalization after multivariable adjustment (HR, 1.12, 95% CI: [1.03-1.22]), compared to those with generally limited medication use. CONCLUSION: The hazard of fall-related hospitalizations differed across prescribing clusters in persons recently diagnosed with dementia, but these differences did not persist after adjustment for key covariates. These methods can be used in future pharmacoepidemiology studies to summarize large amounts of medication data that can then be incorporated into outcomes or causal research.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.005 |
| Science and technology studies | 0.004 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".