Bayesian Machine Learning for Estimating Optimal Dynamic Treatment Regimes with Ordinal Outcomes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916647058538496 |
|---|---|
| author | Wang, Xinru Chakraborty, Tanujit Chakraborty, Bibhas |
| author_facet | Wang, Xinru Chakraborty, Tanujit Chakraborty, Bibhas |
| contents | Dynamic treatment regimes (DTRs) are sequences of decision rules designed to tailor treatment based on patients' treatment history and evolving disease status. Ordinal outcomes frequently serve as primary endpoints in clinical trials and observational studies. However, constructing optimal DTRs for ordinal outcomes has been underexplored. This paper introduces a Bayesian machine learning (BML) framework to handle ordinal outcomes in the DTR setting. To deal with potential nonlinear associations between outcomes and predictors, we first introduce ordinal Bayesian additive regression trees (OBART), a new model that integrates the latent variable framework within the traditional Bayesian additive regression trees (BART). We then incorporate OBART into the BML to estimate optimal DTRs based on ordinal data and quantify the associated uncertainties. Extensive simulation studies are conducted to evaluate the performance of the proposed approach against existing methods. We demonstrate the application of the proposed approach using data from a smoking cessation trial and provide the OBART R package along with R code for implementation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bayesian Machine Learning for Estimating Optimal Dynamic Treatment Regimes with Ordinal Outcomes Wang, Xinru Chakraborty, Tanujit Chakraborty, Bibhas Methodology Dynamic treatment regimes (DTRs) are sequences of decision rules designed to tailor treatment based on patients' treatment history and evolving disease status. Ordinal outcomes frequently serve as primary endpoints in clinical trials and observational studies. However, constructing optimal DTRs for ordinal outcomes has been underexplored. This paper introduces a Bayesian machine learning (BML) framework to handle ordinal outcomes in the DTR setting. To deal with potential nonlinear associations between outcomes and predictors, we first introduce ordinal Bayesian additive regression trees (OBART), a new model that integrates the latent variable framework within the traditional Bayesian additive regression trees (BART). We then incorporate OBART into the BML to estimate optimal DTRs based on ordinal data and quantify the associated uncertainties. Extensive simulation studies are conducted to evaluate the performance of the proposed approach against existing methods. We demonstrate the application of the proposed approach using data from a smoking cessation trial and provide the OBART R package along with R code for implementation. |
| title | Bayesian Machine Learning for Estimating Optimal Dynamic Treatment Regimes with Ordinal Outcomes |
| topic | Methodology |
| url | https://arxiv.org/abs/2503.06199 |