Precision oncology and AI: The ACMA system for personalized treatment matching using real-world data.

Abstract

e23134 Background: Precision oncology promises tailored cancer treatments, yet current methods often overlook individual patient variability. The AI-powered Case Matching Assistant (ACMA) system addresses this by utilizing real-world data (RWD) from over 100,000 clinical cases to personalize treatment strategies, considering genetic profiles, cancer types, treatment stages, and drug interactions. Methods: ACMA enhances the Large Language Model (LLM) with oncology-specific pretraining that encompasses both molecular and clinical data, ensuring a holistic understanding of patient profiles. It employs cosine similarity for multi-faceted case comparisons, integrating genetic, biomarker, and vital clinical information. Context-aware learning prompts fine-tune the LLM, generating recommendations that reflect the full spectrum of patient-specific data, from genetic variations to clinical histories and treatment responses, facilitating truly personalized treatment pathways. Results: Preliminary results show ACMA's tailored recommendations improve patient outcomes, with increased median survival rates and cost-effective treatment options. The system's 90% relevance match for clinical trial enrollment also expands access to novel therapies. In the absence of a standard treatment protocol for BRCA germline mutations in advanced lung cancer, ACMA provides crucial insights. For instance, a 36-year-old female with BRCA1 c.527del mutation achieved complete remission with a PFS of 38 months after a combination therapy trial. A 56-year-old male with a BRCA2 S1722Yfs*mutation saw partial remission and over 6 months PFS with olaparib. Another male patient, a smoker with concurrent BRCA2 G1712X and TP53 mutations, experienced partial remission following apatinib therapy. ACMA analyzed treatment data from similar genetic profiles and identified a targeted therapy that had shown efficacy in comparable cases. The oncologist used this information as a reference to adjust the treatment plan, resulting in a positive clinical outcome for the patient. This example underscores the potential of ACMA to provide actionable insights for personalized cancer care. Conclusions: Surpassing traditional single-feature matching, ACMA rapidly aligns multi-dimensional characteristics such as cancer type, disease stage, molecular data, and treatment phases. It customizes the interplay of these features with medical logic, delivering tailored outputs through the LLM. This approach offers an economical, convenient, and timely solution, setting a new benchmark in personalized oncology and establishing ACMA as a leader in the field. This distinctive advantage not only enhances patient outcomes but also establishes a formidable barrier to entry for competitors, solidifying ACMA's position at the forefront of oncology practice.