The promise of integrating artificial intelligence (AI) in medicine is substantial, offering potential applications across various domains such as personalized care, precision medicine, automated clinical data analysis, and enhancing clinical decision-making and patient communication. Large language models (LLM), particularly, excel in processing extensive datasets including clinical information, lab results, medical histories, and genetic data. In this study, we developed an AI agent specifically designed to assist in making therapeutic decisions for breast cancer (BC) patients. Our system includes a reasoning engine based on GPT-4o, a vector-based semantic search engine (QDrant), a web search engine focused on PUBMED (filtered for clinical studies), the ReAct prompt paradigm, and integrates the most recent AIOM and NCCN guidelines.
Advancing Frontiers: Development of an AI Agent for Breast Cancer Care
Aiello Fabio;Campione Marina.
Writing – Original Draft Preparation
2024-01-01
Abstract
The promise of integrating artificial intelligence (AI) in medicine is substantial, offering potential applications across various domains such as personalized care, precision medicine, automated clinical data analysis, and enhancing clinical decision-making and patient communication. Large language models (LLM), particularly, excel in processing extensive datasets including clinical information, lab results, medical histories, and genetic data. In this study, we developed an AI agent specifically designed to assist in making therapeutic decisions for breast cancer (BC) patients. Our system includes a reasoning engine based on GPT-4o, a vector-based semantic search engine (QDrant), a web search engine focused on PUBMED (filtered for clinical studies), the ReAct prompt paradigm, and integrates the most recent AIOM and NCCN guidelines.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
