Leveraging Large Language Models to Extract and Translate Medical Information in Doctors' Notes for Health Records and Diagnostic Billing Codes

• URL: http://arxiv.org/abs/2603.22625v1
• Date: Wed, 14 Jan 2026 12:21:12 GMT
• Title: Leveraging Large Language Models to Extract and Translate Medical Information in Doctors' Notes for Health Records and Diagnostic Billing Codes
• Abstract summary: This thesis explores using open-weight Large Language Models (LLMs) to extract clinical information from physician notes and translate it into ICD-10-CM diagnostic codes without reliance on cloud-based services.<n>A privacy-focused pipeline was developed using Ollama, LangChain, and containerized environments to evaluate multiple open-weight models.<n>Results show that strict schema enforcement achieved near 100% compliance, but accurate generation of specific diagnostic codes remains challenging for smaller models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physician burnout in the United States has reached critical levels, driven in part by the administrative burden of Electronic Health Record (EHR) documentation and complex diagnostic codes. To relieve this strain and maintain strict patient privacy, this thesis explores an on-device, offline automatic medical coding system. The work focuses on using open-weight Large Language Models (LLMs) to extract clinical information from physician notes and translate it into ICD-10-CM diagnostic codes without reliance on cloud-based services. A privacy-focused pipeline was developed using Ollama, LangChain, and containerized environments to evaluate multiple open-weight models, including Llama 3.2, Mistral, Phi, and DeepSeek, on consumer-grade hardware. Model performance was assessed for zero-shot, few-shot, and retrieval-augmented generation (RAG) prompting strategies using a novel benchmark of synthetic medical notes. Results show that strict JSON schema enforcement achieved near 100% formatting compliance, but accurate generation of specific diagnostic codes remains challenging for smaller local models (7B-20B parameters). Contrary to common prompt-engineering guidance, few-shot prompting degraded performance through overfitting and hallucinations. While RAG enabled limited discovery of unseen codes, it frequently saturated context windows, reducing overall accuracy. The findings suggest that fully automated unsupervised coding with local open-source models is not yet reliable; instead, a human-in-the-loop assisted coding approach is currently the most practical path forward. This work contributes a reproducible local LLM architecture and benchmark dataset for privacy-preserving medical information extraction and coding.

Related papers

• Training a Large Language Model for Medical Coding Using Privacy-Preserving Synthetic Clinical Data [10.24013423253024]
  We investigate whether a modern open-weight foundation model can be adapted for an expert-level medical coding task.<n>We fine-tune Llama 3-70B on pairs of clinical notes and gold codes generated from EHR-grounded templates and coding policies.<n>After fine-tuning on the synthetic corpus, exact-match F1 exceeded 0.70, representing a large absolute gain across both code systems.
  arXiv  Detail & Related papers  (2026-03-06T02:02:49Z)
• MedDCR: Learning to Design Agentic Workflows for Medical Coding [55.51674334874892]
  Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes.<n>We present MedDCR, a closed-loop framework that treats design as a learning problem.<n>On benchmark datasets, MedDCR outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-17T13:30:51Z)
• Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering [70.44269982045415]
  Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) We introduce Medical Retrieval-Augmented Generation Benchmark (MedRGB) that provides various supplementary elements to four medical QA datasets. Our experimental results reveals current models' limited ability to handle noise and misinformation in the retrieved documents.
  arXiv  Detail & Related papers  (2024-11-14T06:19:18Z)
• MedCodER: A Generative AI Assistant for Medical Coding [3.7153274758003967]
  We introduce MedCodER, a Generative AI framework for automatic medical coding. MedCodER achieves a micro-F1 score of 0.60 on International Classification of Diseases (ICD) code prediction. We present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts.
  arXiv  Detail & Related papers  (2024-09-18T19:36:33Z)
• Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router [0.7499722271664144]
  Social Determinants of Health (SDOH) play a significant role in patient health outcomes. Large language models (LLMs) show promise on extracting unstructured data from EHRs. We introduce an intelligent routing system for SDOH coding that uses a language model router to direct medical record data to open source LLMs.
  arXiv  Detail & Related papers  (2024-05-30T02:33:28Z)
• Can GPT-3.5 Generate and Code Discharge Summaries? [45.633849969788315]
  We generated and coded 9,606 discharge summaries based on lists of ICD-10 code descriptions. Neural coding models were trained on baseline and augmented data. We report micro- and macro-F1 scores on the full codeset, generation codes, and their families.
  arXiv  Detail & Related papers  (2024-01-24T15:10:13Z)
• Automatic Coding at Scale: Design and Deployment of a Nationwide System for Normalizing Referrals in the Chilean Public Healthcare System [0.0]
  We propose a two-step system for automatically coding diseases in referrals from the Chilean public healthcare system. Specifically, our model uses a state-of-the-art NER model for recognizing disease mentions and a search engine system based on for assigning the most relevant codes associated with these disease mentions. Our system obtained a MAP score of 0.63 for the subcategory level and 0.83 for the category level, close to the best-performing models in the literature.
  arXiv  Detail & Related papers  (2023-07-09T16:19:35Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)
• Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines [0.42641920138420947]
  We present our Read, Attend, and Code (RAC) model for learning the medical code assignment mappings. RAC establishes a new state of the art (SOTA) considerably outperforming the current best Macro-F1 by 18.7%. This new milestone marks a meaningful step toward fully autonomous medical coding (AMC) in machines.
  arXiv  Detail & Related papers  (2021-07-10T06:01:58Z)
• A Meta-embedding-based Ensemble Approach for ICD Coding Prediction [64.42386426730695]
  International Classification of Diseases (ICD) are the de facto codes used globally for clinical coding. These codes enable healthcare providers to claim reimbursement and facilitate efficient storage and retrieval of diagnostic information. Our proposed approach enhances the performance of neural models by effectively training word vectors using routine medical data as well as external knowledge from scientific articles.
  arXiv  Detail & Related papers  (2021-02-26T17:49:58Z)
• Learning Contextualized Document Representations for Healthcare Answer Retrieval [68.02029435111193]
  Contextual Discourse Vectors (CDV) is a distributed document representation for efficient answer retrieval from long documents. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse. We show that our generalized model significantly outperforms several state-of-the-art baselines for healthcare passage ranking.
  arXiv  Detail & Related papers  (2020-02-03T15:47:19Z)
• DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction [67.91606509226132]
  Clinical trials are essential for drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. DeepEnroll is a cross-modal inference learning model to jointly encode enrollment criteria (tabular data) into a shared latent space for matching inference.
  arXiv  Detail & Related papers  (2020-01-22T17:51:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.