# How Reliable AI Chatbots are for Disease Prediction from Patient Complaints?

arXiv: https://arxiv.org/abs/2405.13219 · HTML: https://mlsanity.com/paper/2405.13219/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Bias of AI-Generated Content: An Examination of News Produced by Large Language Models](https://mlsanity.com/paper/2309.09825/) (2023)
- [Evaluation of AI Chatbots for Patient-Specific EHR Questions](https://mlsanity.com/paper/2306.02549/) (2023)
- [Autocompletion of Chief Complaints in the Electronic Health Records using Large Language Models](https://mlsanity.com/paper/2401.06088/) (2024)
- [Chief complaint classification with recurrent neural networks](https://mlsanity.com/paper/1805.07574/) (2018)

## Built on by (most cited first, 5 of 5)

- [LLM-based Prompt Ensemble for Reliable Medical Entity Recognition from EHRs](https://mlsanity.com/paper/2505.08704/) (2025)
- [Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics](https://mlsanity.com/paper/2506.12365/) (2025)
- [RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being](https://mlsanity.com/paper/2506.08486/) (2025)
- [Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment](https://mlsanity.com/paper/2512.04210/) (2025)
- [Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement](https://mlsanity.com/paper/2504.14068/) (2025)

## Abstract (arXiv)

Artificial Intelligence (AI) chatbots leveraging Large Language Models (LLMs) are gaining traction in healthcare for their potential to automate patient interactions and aid clinical decision-making. This study examines the reliability of AI chatbots, specifically GPT 4.0, Claude 3 Opus, and Gemini Ultra 1.0, in predicting diseases from patient complaints in the emergency department. The methodology includes few-shot learning techniques to evaluate the chatbots' effectiveness in disease prediction. We also fine-tune the transformer-based model BERT and compare its performance with the AI chatbots. Results suggest that GPT 4.0 achieves high accuracy with increased few-shot data, while Gemini Ultra 1.0 performs well with fewer examples, and Claude 3 Opus maintains consistent performance. BERT's performance, however, is lower than all the chatbots, indicating limitations due to limited labeled data. Despite the chatbots' varying accuracy, none of them are sufficiently reliable for critical medical decision-making, underscoring the need for rigorous validation and human oversight. This study reflects that while AI chatbots have potential in healthcare, they should complement, not replace, human expertise to ensure patient safety. Further refinement and research are needed to improve AI-based healthcare applications' reliability for disease prediction.