Cancer-Answer: Empowering Cancer Care with Advanced Large Language Models

2024-11-11

arXiv.org

AI Summary

Gastrointestinal (GI) cancers exhibit complex etiologies and overlapping symptoms, leading to diagnostic delays and lagging access to actionable clinical decision support. To address this, we propose the first domain-specific large language model (LLM)-based question-answering system tailored for GI cancer diagnosis and treatment. Our method introduces a dual-dimensional evaluation framework—A1 (medical entity coverage) and A2 (semantic plausibility)—establishing the first clinical-need-driven LLM adaptation paradigm. We fine-tune GPT-3.5 Turbo with curated clinical guidelines and peer-reviewed literature, incorporating joint entity alignment and semantic similarity assessment. On GI cancer QA tasks, our system achieves A1 = 0.546 and A2 = 0.881, significantly outperforming general-purpose LLMs. Results demonstrate its efficacy and reliability in delivering timely, trustworthy, and interpretable decision support within real-world clinical workflows.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Gastrointestinal (GI) tract cancers account for a substantial portion of the global cancer burden, where early diagnosis is critical for improved management and patient outcomes. The complex aetiologies and overlapping symptoms across GI cancers often delay diagnosis, leading to suboptimal treatment strategies. Cancer-related queries are crucial for timely diagnosis, treatment, and patient education, as access to accurate, comprehensive information can significantly influence outcomes. However, the complexity of cancer as a disease, combined with the vast amount of available data, makes it difficult for clinicians and patients to quickly find precise answers. To address these challenges, we leverage large language models (LLMs) such as GPT-3.5 Turbo to generate accurate, contextually relevant responses to cancer-related queries. Pre-trained with medical data, these models provide timely, actionable insights that support informed decision-making in cancer diagnosis and care, ultimately improving patient outcomes. We calculate two metrics: A1 (which represents the fraction of entities present in the model-generated answer compared to the gold standard) and A2 (which represents the linguistic correctness and meaningfulness of the model-generated answer with respect to the gold standard), achieving maximum values of 0.546 and 0.881, respectively.

Problem

• Addressing delayed diagnosis in GI cancers due to complex symptoms.
• Providing accurate cancer-related information for timely treatment decisions.
• Enhancing patient outcomes using advanced language models for medical queries.

Innovation

• Leverage GPT-3.5 Turbo for cancer queries
• Pre-trained models with medical data
• Metrics A1 and A2 for answer evaluation