Liver Cancer: Artificial Intelligence (AI)-Based Integrated Therapeutic Approaches

The advent of artificial intelligence and machine leaning techniques has revolutionized the diagnosis and therapy of diseases such as cancer [1,2,3]. A Web of Science search with the keywords “artificial intelligence and diagnosis and and therapy” yields 3034 results as of 31 July 2025, indicating the amount of research of this area. Liver cancer, predominantly hepatocellular carcinoma (HCC), stands as the sixth most commonly diagnosed malignancy and the third leading cause of cancer-related deaths globally [4]. Its multifactorial origin encompasses chronic hepatitis B and C virus infections, alcohol-induced liver cirrhosis, non-alcoholic fatty liver disease (NAFLD), aflatoxin B1 exposure, and metabolic syndromes. The aggressive nature of HCC and its typically late-stage diagnosis result in poor prognosis and limited therapeutic success [5]. In addition to its silent clinical progression, the heterogeneity of tumor biology presents a significant challenge in effective disease management [6,7]. Geographic and ethnic variations further influence the incidence and origin of HCC, with developing regions experiencing a disproportionately higher disease burden due to inadequate screening and vaccination programs. Recent advances in molecular biology and genomics have elucidated the key oncogenic signaling pathways involved in liver carcinogenesis. They include Wnt/β-catenin, PI3K/Akt/mTOR, MAPK/ERK, and TGF-β pathways. These discoveries have paved the way for the development of targeted therapies, including multi-kinase inhibitors like sorafenib and lenvatinib, which offer modest survival benefits (Figure 1). However, therapeutic resistance and adverse side effects remain major hurdles [8,9], which are surmountable with the judicious use of AI- and ML-based methods.

The emergence of immunotherapy, and particularly the use of immune checkpoint inhibitors targeting programmed cell death protein 1 (PD-1), its ligand PD-L1, and cytotoxic T-lymphocyte-associated antigen 4 (CTLA-4), has demonstrated significant promise in enhancing antitumor immune responses in patients with hepatocellular carcinoma (HCC). These agents work by restoring T-cell activation and enabling the immune system to recognize and eliminate tumor cells more effectively [10,11]. While monotherapy with checkpoint inhibitors has yielded encouraging results in a subset of patients, response rates remain variable [12].

Immunotherapy combined with anti-angiogenic agents such as bevacizumab normalizes tumor vasculature promoting immune cell infiltration, as does immunotherapy combined with locoregional treatments like transarterial chemoembolization (TACE) and radiofrequency ablation (RFA). These techniques induce immunogenic cell death and enhance immune priming. Such multimodal approaches are under active clinical investigation, aiming to improve overall survival, progression-free survival, and long-term tumor control in advanced-stage HCC patients [13,14]. Despite these advancements, early detection remains critical. Current diagnostic tools, including imaging techniques and serum biomarkers like alpha-fetoprotein (AFP), lack sufficient sensitivity and specificity for detecting early-stage HCC. Thus, novel biomarkers and liquid biopsy approaches are being explored to enhance diagnostic precision and monitor treatment response [15,16].

Prevention strategies, particularly vaccination against hepatitis B virus and antiviral therapies for hepatitis C, have significantly reduced the incidence of HCC in high-risk populations. Nevertheless, the global burden of liver cancer is projected to rise due to the increasing prevalence of obesity and NAFLD-related hepatic disorders [17,18]. In conclusion, liver cancer remains a formidable threat to life. A multidisciplinary approach based on artificial intelligence (AI), machine learning (ML), and nanotechnology, integrating prevention, early diagnosis, personalized effective therapy, and continuous care, is essential to improve clinical outcomes [19]. Future research should focus on uncovering novel molecular targets, optimizing therapeutic combinations, and refining diagnostic methodologies to combat this life-threatening malignancy effectively with the use of combinatorial biochemistry and high-throughput screening techniques [20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37].