# Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia

arXiv: https://arxiv.org/abs/2409.15377 · HTML: https://mlsanity.com/paper/2409.15377/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation](https://mlsanity.com/paper/1807.01473/) (2018)
- [Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine](https://mlsanity.com/paper/2308.06834/) (2023)
- [Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales](https://mlsanity.com/paper/2312.07399/) (2023)
- [A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2311.11483/) (2023)
- [Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data](https://mlsanity.com/paper/1801.09271/) (2018)
- [Deep Reinforcement Learning for Cost-Effective Medical Diagnosis](https://mlsanity.com/paper/2302.10261/) (2023)
- [Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds](https://mlsanity.com/paper/2403.06609/) (2024)
- [Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices](https://mlsanity.com/paper/2405.01249/) (2024)
- [Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus](https://mlsanity.com/paper/2404.05913/) (2024)
- [Optimizing Sepsis Care through Heuristics Methods in Process Mining: A Trajectory Analysis](https://mlsanity.com/paper/2303.14328/) (2023)

## Built on by (most cited first, 1 of 1)

- [Dr. GPT Will See You Now, but Should It? Exploring the Benefits and Harms of Large Language Models in Medical Diagnosis using Crowdsourced Clinical Cases](https://mlsanity.com/paper/2506.13805/) (2025)

## Abstract (arXiv)

In practice, clinicians achieve a diagnosis by following a sequence of steps, such as laboratory exams, observations, or imaging. The pathways to reach diagnosis decisions are documented by guidelines authored by expert organizations, which guide clinicians to reach a correct diagnosis through these sequences of steps. While these guidelines are beneficial for following medical reasoning and consolidating medical knowledge, they have some drawbacks. They often fail to address patients with uncommon conditions due to their focus on the majority population, and are slow and costly to update, making them unsuitable for rapidly emerging diseases or new practices. Inspired by clinical guidelines, our study aimed to develop pathways similar to those that can be obtained in clinical guidelines. We tested three Large Language Models (LLMs) -Generative Pretrained Transformer 4 (GPT-4), Large Language Model Meta AI (LLaMA), and Mistral -on a synthetic yet realistic dataset to differentially diagnose anemia and its subtypes. By using advanced prompting techniques to enhance the decision-making process, we generated diagnostic pathways using these models. Experimental results indicate that LLMs hold huge potential in clinical pathway discovery from patient data, with GPT-4 exhibiting the best performance in all conducted experiments.