# RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction

arXiv: https://arxiv.org/abs/2610.02979 · HTML: https://mlsanity.com/paper/2610.02979/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination](https://mlsanity.com/paper/1809.01852/) (2018)
- [Deepr: A Convolutional Net for Medical Records](https://mlsanity.com/paper/1607.07519/) (2016)
- [GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs](https://mlsanity.com/paper/2305.12788/) (2023)
- [AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration](https://mlsanity.com/paper/1911.12205/) (2019)
- [StageNet: Stage-Aware Neural Networks for Health Risk Prediction](https://mlsanity.com/paper/2001.10054/) (2020)
- [Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards](https://mlsanity.com/paper/2107.00176/) (2021)
- [Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices](https://mlsanity.com/paper/2405.01249/) (2024)
- [RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs](https://mlsanity.com/paper/2409.04421/) (2024)
- [Contrastive Learning on Medical Intents for Sequential Prescription Recommendation](https://mlsanity.com/paper/2408.10259/) (2024)
- [Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation](https://mlsanity.com/paper/2508.21320/) (2025)
- [Aspect-Oriented Summarization for Psychiatric Short-Term Readmission Prediction](https://mlsanity.com/paper/2502.10388/) (2025)
- [RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models](https://mlsanity.com/paper/2604.17725/) (2026)

## Abstract (arXiv)

Unstructured discharge notes in Electronic Health Records (EHRs) often carry signal complementary to structured medical codes, holding patient-specific evidence that standardized cohort-level codes alone cannot capture. However, this evidence in notes is frequently buried in lengthy, noisy text that is not intentionally written with any specific clinical prediction in mind. Summarization is an obvious mitigation, but generic summaries, tuned for fluency rather than the outcome, routinely omit decisive evidence while retaining plausible but uninformative detail. To this end, we propose RASPER, a Reward-Aligned Summarizer for Prediction in EHR, that optimizes note summarization directly against the downstream clinical task. RASPER employs a tunable LLM-based summarizer to extract task-relevant evidence from discharge notes and trains it via reinforcement learning from prediction feedback, using a reward derived from the downstream predictor's loss. To ground the summarizer, a longitudinal encoder converts structured codes into soft prompts that incorporate each patient's clinical context into note summarization. By rewarding the quality of the resulting multimodal prediction, RASPER encourages the summarizer to retain patient-specific evidence that complements, rather than duplicates, information captured by structured codes. RASPER consistently outperforms strong baselines on both readmission prediction and medication recommendation across MIMIC-III and MIMIC-IV.