Statins, which are inhibitors of 3-hydroxy-3-methyl-glutaryl-coenzyme A (HMG-CoA) reductase, are an effective pharmacological tool for lowering blood cholesterol levels. This property makes statins one of the most popular drugs used primarily to prevent cardiovascular diseases, where hyperlipidemia is a significant risk factor that increases mortality. Nevertheless, studies conducted mainly in the last decade have shown that statins might prevent and treat liver cancer, one of the leading causes of cancer-related mortality worldwide. This narrative review summarizes the scientific achievements to date regarding the role of statins in liver tumors. Molecular biology tools have revealed that cell growth and proliferation can be inhibited by statins, which further inhibit angiogenesis. Clinical studies, supported by meta-analysis, confirm that statins are highly effective in preventing and treating hepatocellular carcinoma and cholangiocarcinoma. However, this effect may depend on the statin’s type and dose, and more clinical trials are required to evaluate clinical effects. Moreover, their potential hepatotoxicity is a significant caveat for using statins in clinical practice. Nevertheless, this group of drugs, initially developed to prevent cardiovascular diseases, is now a key candidate in hepato-oncology patient management. The description of new drug-statin-like structures, e.g., with low toxicity to liver cells, may bring another clinically significant improvement to current cancer therapies.

Background/Objectives: Liver cancer is an exceedingly heterogeneous malignancy with high mortality rates, and despite extensive research, there have been no significant improvements in treatment outcomes. In the process of navigating the complex landscape of liver cancer, AI has arisen as the “knight in shining armour”, sparking hope and offering invaluable insight into early detection, diagnosis, staging, treatment selection, and post-treatment surveillance. By integrating imaging, clinical, pathological, and molecular data, AI emerges as a transformative tool that offers unique opportunities to enhance patient care. Methods: A comprehensive literature search of PubMed and Scopus, was conducted using the terms “artificial intelligence,” “machine learning,” “deep learning,” “radiomics,” and “liver cancer.” Eligible studies included peer-reviewed original research applying AI to detection, diagnosis, prognosis, treatment planning, or surveillance of liver cancer. Key findings are organized along the clinical continuum. Results: Imaging-based AI models for tumor detection were the most advanced, with several achieving diagnostic accuracy above 90% in retrospective studies. Applications for treatment decision-making are emerging, but most remain at proof-of-concept stages. Generally, few of these innovations have progressed to large-scale clinical trials or received regulatory approval, slowing their integration into clinical practice. Conclusions: This narrative review highlights AI’s potential to transform liver cancer management and addresses the ethical, regulatory, and logistical barriers to its clinical adoption, serving as a call to action for integrating AI into practice to improve patient outcomes.

Background/Objectives: Treatment allocation for hepatocellular carcinoma (HCC) is a highly complex task that requires multidisciplinary tumor board (MDT) input; however, its accessibility and reliability can vary across the healthcare system. Large language models (LLMs) have emerged as potential clinical decision-making tools to aid MDTs. Our aim was to compare different LLM-generated treatment recommendations for HCC cases with MDT decisions. Methods: We retrospectively analyzed 100 HCC cases discussed during MDT meetings in a tertiary-care hospital in Cluj-Napoca, Romania. Identical prompts and structured clinical information were offered to four different LLMs (ChatGPT-5, a customized Tumor Board ChatGPT, Gemini 2.5 Flash, and Gemini 2.5 Pro), each of which was required to provide treatment recommendations. Concordance with the MDT decisions was assessed across the first, second, and third treatment options. Inter-model differences were evaluated using Cochran’s Q and Holm-adjusted exact McNemar tests. Chance-corrected agreement was assessed using Cohen’s kappa (κ), and generalized estimating equations evaluated associations between concordance and clinical complexity. Results: First-recommendation concordance was 81% (95% CI 72.2–87.5) for GPT-5, 80% (71.1–86.7) for Gemini 2.5 Pro, 78% (68.9–85.0) for TumorBoard ChatGPT, and 63% (53.2–71.8) for Gemini 2.5 Flash; cumulative top-3 concordance reached 95%, 92%, 95%, and 86%, respectively. GPT-5 (κ = 0.754) and Gemini 2.5 Pro (κ = 0.743) showed substantial chance-corrected agreement. Gemini 2.5 Flash showed significantly lower concordance, including after adjustment for BCLC stage, Child–Pugh class, tumor burden, and treatment category (p = 0.006), while these clinical complexity variables were not significantly associated with concordance. Conclusions: LLMs showed moderate-to-substantial agreement with MDT decisions, with meaningful inter-model differences, for a complex disease, such as HCC. Our study highlights that, while the need for human oversight is essential, LLMs could serve as supportive tools for expert guidance in some clinical settings and underscore AI’s potential in enhancing liver cancer care.

Background and Aims: To develop an inclusive, predictive framework for hepatocellular carcinoma patients, beyond what the Barcelona Clinic Liver Cancer (BCLC) staging system captures alone, non-invasive scores have emerged as potential contributors. Among them, the CRAFITY score (CRP and AFP in ImmunoTherapY), originally developed for immunotherapy-treated HCC populations, and the Platelet-Albumin-Bilirubin (PALBI) score have shown promising prognostic performance in selected cohorts. Likewise, the macrotrabecular-massive (MTM) histological subtype has been identified as a strong independent predictor of tumor recurrence, particularly in surgical series; whether it retains the prognostic significance in a mixed-treatment cohort remains unexplored. We aimed to evaluate the independent prognostic performance of CRAFITY and PALBI across all HCC treatment modalities, determine MTM prevalence and assess whether histological subtyping adds prognostic value beyond these readily available clinical scores. Methods: The study included 500 consecutive, pathologically confirmed HCC patients at a tertiary gastroenterology center in Cluj-Napoca, Romania. MTM subtype was defined as >50% macrotrabecular architectural pattern on histological review by two senior pathologists. Overall survival (OS) and recurrence-free survival (RFS) were assessed by Kaplan–Meier analysis and multivariable Cox regression. A random survival forest (RSF) model was constructed to identify dominant prognostic predictors. Results: MTM was identified in 14 patients (2.8%) and did not independently predict OS (HR 0.94, 95% CI 0.49–1.81, p = 0.85) or recurrence (OR 3.78, p = 0.116). In this heterogeneous cohort spanning multiple treatment modalities, CRAFITY (HR 1.68, 95% CI 1.42–1.98, p < 0.001) and PALBI (HR 1.51, 95% CI 1.22–1.87, p < 0.001) were strong independent predictors of OS after BCLC stage. RSF analysis confirmed this hierarchy with a C-index of 0.734. Conclusions: CRAFITY and PALBI demonstrated strong, independent predictive performance for a large, underrepresented, heterogenous Eastern European HCC cohort. In contrast, MTM subtype showed limited prognostic value in this cohort. The results support the broader applicability of CRAFITY beyond its original immunotherapy context and underline the low prevalence of MTM subtype.

Within the Liver Imaging Reporting and Data System (LI-RADS), LI-RADS Malignant (LR-M) lesions remain diagnostically challenging: imaging indicates malignancy, but often fails to distinguish hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (iCCA). Established serum-based tools, such as GALAD, are optimized for HCC, but are not designed to resolve entity ambiguity within LR-M. In this pilot proof of concept study, we investigated whether small extracellular vesicles (EVs) integrated with routine serological markers could resolve LR-M lesion situation. A rare LR-M cohort (HCC = 25, iCCA = 25) was evaluated using least absolute shrinkage and selection operator (LASSO) logistic regression and PCA to prioritize informative biomarkers. Hybrid models combined CD9⁺CD133/2⁺ and CD81⁺CD133/2⁺ EVs with alkaline phosphatase, serum C-reactive protein, CA19-9, and optional alpha-fetoprotein (AFP). Models were internally validated using an 80:20 train-test split and assessed with bootstrap and Monte Carlo perturbation (±5-20%). Individual markers demonstrated limited discrimination (AUROC ≤0.82). Hybrid logistic regression models showed moderate internal discrimination (AUROC 0.86 with AFP; 0.91 without AFP). Translation into additive scoring systems using ROC-Youden-derived cut-offs yielded high internal AUROC estimates (e.g. 0.95-0.96), although these remain internally validated. A simplified 5-point PRISM score retained comparable discriminatory performance (AUROC ∼0.91). In an exploratory survival analysis among patients with iCCA (n = 25), those with above-median CD9⁺CD133/2⁺ EV levels (n = 13) had shorter overall survival (median 91 vs. 389 days; HR: 2.80, 95% CI: 1.16-6.74; p = 0.005). Integrated EV and serological profiling could enable minimally invasive differentiation between HCC and iCCA within LR-M lesions. By transforming machine learning (ML)-guided model discovery into a clinically interpretable paper-and-pencil additive score, we illustrate a translational pathway from computational discovery to practical application. This study provides a scientific rationale for integrating small EV phenotyping with conventional serum biomarkers to improve minimally invasive differentiation between HCC and iCCA in LR-M lesions. By translating a machine learning (ML)-derived hybrid model into a simple additive scoring system, we demonstrate how ML can yield clinically interpretable tools that bridge computational discovery and bedside application. The findings are particularly relevant for hepatologists, oncologists, and radiologists managing patients in whom imaging remains indeterminate and biopsy carries procedural risk. The 5-point model can be applied using routine laboratory values, providing a paper-and-pencil diagnostic aid that requires no specialized software or hardware. Although external multicenter validation is necessary given the cohort size, this approach illustrates how transparent, interpretable ML can support precision diagnostics in primary liver cancer.