Effect of discontinuing antipsychotic medications on the risk of hospitalization in long-term care: a machine learning-based analysis
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 anti...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12916-025-04304-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|---|
| ISSN: | 1741-7015 |