Effect of discontinuing antipsychotic medications on the risk of hospitalization in long-term care: a machine learning-based analysis
Bibliographic record
Abstract
BACKGROUND: Antipsychotic medications are frequently prescribed to older residents of long-term care facilities (LTCFs) despite their limited efficacy and considerable safety risks. While discontinuation of these drugs might help reduce their associated morbidity, the impact of stopping antipsychotics on the risk of hospitalization has not been studied yet. The study aimed at estimating the effect of antipsychotic discontinuation on the risk of hospitalization in older LTCF residents and at identifying relevant factors influencing such effect. METHODS: For this registry-based retrospective cohort study, data from a cohort of older LTCF residents in Finland from the years 2014 to 2018 was analyzed. Data sources were the Resident Assessment Instrument for Long-Term Care (RAI-LTC) based comprehensive geriatric assessments and the Finnish Care Register for Health Care. For the initial cohort, 5467 users of antipsychotic medications with at least four assessments, each conducted 6 months apart, were selected. Residents were defined either as discontinuing, if antipsychotics were prescribed at the first two assessments but not at the last two, or as chronic users, if antipsychotics were prescribed at all four assessments. Causal machine learning (ML) methods including double machine learning (DML), double robust (DR), X-learner, and causal forest (CF) were applied to estimate the effect of antipsychotic discontinuation on the risk of hospitalization and to identify factors influencing such effect. The follow-up time was 1 year. The methods of SHAP values (SHapley Additive exPlanations), partial dependence plots (PDP), and surrogate models were used for model interpretation. RESULTS: Nearly 43% of residents in the study discontinued antipsychotic medications. Antipsychotic discontinuation lowered the probability of hospitalization of about 12% (average treatment effect, ATE). The individual treatment effect (ITE) estimations ranged from - 30% to + 1%. The use of restraints, age, and functional impairment were relevant variables in all ITE models in influencing the predicted ITE. CONCLUSIONS: Antipsychotic discontinuation may decrease the likelihood of hospitalization among older LTCF residents, benefiting most users of these drugs. Promoting antipsychotic discontinuation may prevent hospitalizations and reduce morbidity and mortality in long-term care.
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 | 0.018 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.008 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".