Abstract: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.
Abstract:The Chief Complaint (CC) is a crucial component of a patient's medical record as it describes the main reason or concern for seeking medical care. It provides critical information for healthcare providers to make informed decisions about patient care. However, documenting CCs can be time-consuming for healthcare providers, especially in busy emergency departments. To address this issue, an autocompletion tool that suggests accurate and well-formatted phrases or sentences for clinical notes can be a valuable resource for triage nurses. In this study, we utilized text generation techniques to develop machine learning models using CC data. In our proposed work, we train a Long Short-Term Memory (LSTM) model and fine-tune three different variants of Biomedical Generative Pretrained Transformers (BioGPT), namely microsoft/biogpt, microsoft/BioGPT-Large, and microsoft/BioGPT-Large-PubMedQA. Additionally, we tune a prompt by incorporating exemplar CC sentences, utilizing the OpenAI API of GPT-4. We evaluate the models' performance based on the perplexity score, modified BERTScore, and cosine similarity score. The results show that BioGPT-Large exhibits superior performance compared to the other models. It consistently achieves a remarkably low perplexity score of 1.65 when generating CC, whereas the baseline LSTM model achieves the best perplexity score of 170. Further, we evaluate and assess the proposed models' performance and the outcome of GPT-4.0. Our study demonstrates that utilizing LLMs such as BioGPT, leads to the development of an effective autocompletion tool for generating CC documentation in healthcare settings.