CRAFITY and PALBI Define a Machine Learning-Supported Prognostic Framework in Hepatocellular Carcinoma—Data from an Eastern European Cohort with Low Macrotrabecular-Massive Prevalence

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.