# RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records

arXiv: https://arxiv.org/abs/2507.15867 · HTML: https://mlsanity.com/paper/2507.15867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 18 of 18)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://mlsanity.com/paper/1910.11470/) (2019)
- [Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine](https://mlsanity.com/paper/2308.06834/) (2023)
- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [An Agentic System for Rare Disease Diagnosis with Traceable Reasoning](https://mlsanity.com/paper/2506.20430/) (2025)
- [Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study](https://mlsanity.com/paper/2304.10909/) (2023)
- [RareBench: Can LLMs Serve as Rare Diseases Specialists?](https://mlsanity.com/paper/2402.06341/) (2024)
- [Biomedical named entity recognition using BERT in the machine reading comprehension framework](https://mlsanity.com/paper/2009.01560/) (2020)
- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT](https://mlsanity.com/paper/2308.06294/) (2023)
- [The RareDis corpus: a corpus annotated with rare diseases, their signs and symptoms](https://mlsanity.com/paper/2108.01204/) (2021)
- [Clinical Concept Extraction for Document-Level Coding](https://mlsanity.com/paper/1906.03380/) (2019)
- [Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts](https://mlsanity.com/paper/2109.00343/) (2021)
- [Ontology-Driven and Weakly Supervised Rare Disease Identification from Clinical Notes](https://mlsanity.com/paper/2205.05656/) (2022)
- [A Hybrid Framework with Large Language Models for Rare Disease Phenotyping](https://mlsanity.com/paper/2405.10440/) (2024)
- [On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models](https://mlsanity.com/paper/2411.07070/) (2024)

## Abstract (arXiv)

Rare diseases affect 1 in 10 Americans yet remain systematically underdocumented in clinical records. ICD-based systems cannot capture their breadth, over 50% of Orphanet codes lack a direct ICD mapping and only 2.2% of HPO codes have matching ICD codes, leaving patient populations invisible and delaying diagnosis. Mining unstructured clinical notes offers a direct path forward, but real notes are long, noisy, and abbreviation-dense, and limited annotations make fine-tuning infeasible, demanding approaches that generalize without task-specific training. We present Rare Disease Mining Agents (RDMA), an agentic framework equipping smaller quantized LLMs with tools for abbreviation resolution, implicit phenotype reasoning, and ontology grounding against Orphanet and HPO. RDMA substantially outperforms fine-tuned and RAG-based baselines across benchmarks with different data characteristics, without any task-specific training. A small quantized model achieves maximal performance, reducing inference costs by up to 10x and local hardware costs by up to 17x, enabling private deployment on standard hardware without cloud-based PHI exposure. RDMA's uncertainty-flagging mechanism further reduces expert annotation burden while preserving agreement quality, supporting scalable rare disease documentation in clinical practice. Available at https://github.com/jhnwu3/RDMA.