Different applications of Artificial Intelligence in liver cancer: a scoping review – part II, from treatment planning and efficacy assessment to prognosis prediction and follow-up. (Preprint)

Abstract

BACKGROUND Artificial Intelligence (AI) plays a pivotal role in early detection and personalized treatment of liver cancer. The integration of AI in screening and diagnosis enhances detection accuracy and aids in formulating effective treatment strategies, but it can be an effective tool to guide liver cancer management in all the steps from treatment deliverance to follow-up. OBJECTIVE This is the second part of a scoping review on implementation of AI and liver cancer, focusing on treatment planning and efficacy assessment, prognosis prediction, and follow-up. METHODS A systematic review was performed on PubMed, Embase, Scopus, and Web of Science databases including research published between January the 1st 2020 and September the 30th 2023. RESULTS AI-driven tools offer predictive analytics for prognosis, treatment planning, and efficacy assessment, aiming to optimize patient outcomes. In liver cancer management, AI assists in treatment planning, such as liver resection and radioembolization, by improving preoperative mapping and predicting therapeutic response. Additionally, AI models predict chemotherapy efficacy based on patient-specific factors, facilitating tailored treatment approaches. Moreover, leveraging AI models, integrating clinical, biochemical, radiological, and histological data, enables accurate prognostication at diagnosis and post-treatment. Key factors such as microvascular invasion, tumor capsule integrity, and grade significantly influence liver cancer prognosis, often assessed using AI-driven predictive models. Imaging modalities, coupled with AI algorithms, exhibit high accuracy in predicting microvascular invasion, aiding treatment planning and prognosis assessment. Following treatment, AI plays a crucial role in prognosis assessment. For patients undergoing liver resection, machine learning models predict disease-free survival, aiding decisions regarding adjuvant chemotherapy. Similarly, models for thermoablation and liver transplantation provide insights into recurrence risk, guiding post-treatment follow-up. In patients receiving systemic treatment like immunotherapy, AI-based models predict cancer-related mortality and overall survival, facilitating treatment response assessment and patient stratification. CONCLUSIONS AI finds wide application in the management of liver cancer treatment and follow-up. Despite promising advancements, challenges remain, including the need for external validation and adaptation to diverse patient populations. Further research is essential to realize the full potential of AI in liver cancer management and translate it into clinical impact. CLINICALTRIAL