Towards Physiologically Sensible Predictions via the Rule-based Reinforcement Learning Layer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917907531825152 |
|---|---|
| author | Zhu, Lingwei Chen, Zheng Nagai, Yukie Sun, Jimeng |
| author_facet | Zhu, Lingwei Chen, Zheng Nagai, Yukie Sun, Jimeng |
| contents | This paper adds to the growing literature of reinforcement learning (RL) for healthcare by proposing a novel paradigm: augmenting any predictor with Rule-based RL Layer (RRLL) that corrects the model's physiologically impossible predictions. Specifically, RRLL takes as input states predicted labels and outputs corrected labels as actions. The reward of the state-action pair is evaluated by a set of general rules. RRLL is efficient, general and lightweight: it does not require heavy expert knowledge like prior work but only a set of impossible transitions. This set is much smaller than all possible transitions; yet it can effectively reduce physiologically impossible mistakes made by the state-of-the-art predictor models. We verify the utility of RRLL on a variety of important healthcare classification problems and observe significant improvements using the same setup, with only the domain-specific set of impossibility changed. In-depth analysis shows that RRLL indeed improves accuracy by effectively reducing the presence of physiologically impossible predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19055 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Physiologically Sensible Predictions via the Rule-based Reinforcement Learning Layer Zhu, Lingwei Chen, Zheng Nagai, Yukie Sun, Jimeng Machine Learning Artificial Intelligence This paper adds to the growing literature of reinforcement learning (RL) for healthcare by proposing a novel paradigm: augmenting any predictor with Rule-based RL Layer (RRLL) that corrects the model's physiologically impossible predictions. Specifically, RRLL takes as input states predicted labels and outputs corrected labels as actions. The reward of the state-action pair is evaluated by a set of general rules. RRLL is efficient, general and lightweight: it does not require heavy expert knowledge like prior work but only a set of impossible transitions. This set is much smaller than all possible transitions; yet it can effectively reduce physiologically impossible mistakes made by the state-of-the-art predictor models. We verify the utility of RRLL on a variety of important healthcare classification problems and observe significant improvements using the same setup, with only the domain-specific set of impossibility changed. In-depth analysis shows that RRLL indeed improves accuracy by effectively reducing the presence of physiologically impossible predictions. |
| title | Towards Physiologically Sensible Predictions via the Rule-based Reinforcement Learning Layer |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.19055 |