# Can Reasoning LLMs Enhance Clinical Document Classification?

arXiv: https://arxiv.org/abs/2504.08040 · HTML: https://mlsanity.com/paper/2504.08040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 5 of 5)

- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales](https://mlsanity.com/paper/2312.07399/) (2023)
- [Exploring LLM Multi-Agents for ICD Coding](https://mlsanity.com/paper/2406.15363/) (2024)
- [Classifying Unstructured Clinical Notes via Automatic Weak Supervision](https://mlsanity.com/paper/2206.12088/) (2022)
- [Classifying medical notes into standard disease codes using Machine Learning](https://mlsanity.com/paper/1802.00382/) (2018)

## Built on by (most cited first, 3 of 3)

- [Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs](https://mlsanity.com/paper/2507.03001/) (2025)
- [Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks](https://mlsanity.com/paper/2511.03328/) (2025)
- [Error-Aware Curriculum Learning for Biomedical Relation Classification](https://mlsanity.com/paper/2507.14374/) (2025)

## Abstract (arXiv)

Clinical document classification is essential for converting unstructured medical texts into standardised ICD-10 diagnoses, yet it faces challenges due to complex medical language, privacy constraints, and limited annotated datasets. Large Language Models (LLMs) offer promising improvements in accuracy and efficiency for this task. This study evaluates the performance and consistency of eight LLMs; four reasoning (Qwen QWQ, Deepseek Reasoner, GPT o3 Mini, Gemini 2.0 Flash Thinking) and four non-reasoning (Llama 3.3, GPT 4o Mini, Gemini 2.0 Flash, Deepseek Chat); in classifying clinical discharge summaries using the MIMIC-IV dataset. Using cTAKES to structure clinical narratives, models were assessed across three experimental runs, with majority voting determining final predictions. Results showed that reasoning models outperformed non-reasoning models in accuracy (71% vs 68%) and F1 score (67% vs 60%), with Gemini 2.0 Flash Thinking achieving the highest accuracy (75%) and F1 score (76%). However, non-reasoning models demonstrated greater stability (91% vs 84% consistency). Performance varied across ICD-10 codes, with reasoning models excelling in complex cases but struggling with abstract categories. Findings indicate a trade-off between accuracy and consistency, suggesting that a hybrid approach could optimise clinical coding. Future research should explore multi-label classification, domain-specific fine-tuning, and ensemble methods to enhance model reliability in real-world applications.