Exploring the relationship between medications and heat-related community deaths during the 2021 heat dome: a hybrid approach using machine learning
Bibliographic record
Abstract
BACKGROUND: Extreme heat events (EHEs) are a growing threat to health worldwide. To date, only a limited number of studies have evaluated medications as risk or protective factors for mortality during EHEs. METHODS: We explored the relationship between dispensed pharmaceuticals and heat-related community deaths using linked administrative health data and both logistic regression (LR) and machine learning (ML) models. We conducted a case-control study during the 2021 EHE in British Columbia, Canada, including 504 community deaths from heat exposure as cases and 2520 similar controls who survived the EHE. We used medications dispensed 30, 60 and 90 days prior to death (or 30, 60 and 90 days before the end of the EHE for controls) as predictors, grouped by Anatomical Therapeutic Chemical (ATC) classification at level 2 for LR (28 classes) and level 4 for ML (270 subclasses). Models were adjusted for multiple covariates, including common chronic diseases. FINDINGS: Results from LR showed increased odds of mortality associated with dispensations of antiepileptics, anti-Parkinson drugs, psycholeptics, diuretics, drugs for diabetes, beta blocking agents, analgesics, urologicals and drugs for treatment of bone diseases. We observed a protective association with dispensations of calcium channel blockers and ophthalmologicals. Results varied by sex, age, and other covariates. The ML model highlighted the most computationally important subclasses of medications within each of the ATC level 2 classes. INTERPRETATION: This study leveraged both LR and ML to generate insights about medications and mortality during EHEs. The results add to the existing evidence on pharmaceutical risks during EHEs and provide new avenues for further research. They can be used to help develop more targeted messages to inform individuals whose medications put them at greater risk during EHEs. FUNDING: BC Centre for Disease Control and Ministère de l'Enseignement supérieur du Québec.
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 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 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".