Preoperative plasma ceramide profiling coupled with machine learning accurately predicts recurrence of hepatocellular carcinoma after resection

Lei et al. Lipids in Health and Disease (2025) 24:355 https://doi.org/10.1186/s12944-025-02749-6 Lipids in Health and Disease Open Access RESEARCH Preoperative plasma ceramide profiling coupled with machine learning accurately predicts recurrence of hepatocellular carcinoma after resection Yang Lei1†, Chen Xie1†, Xiangyue Mo1†, Baoxiong Zhuang2, Qingping Li1, Cuiting Liu3, Leyi Liao1, Biao Wang1, Minghui Zeng4, Shanhua Tang1, Haiqing Liu1, Yuancan Xiao1, Suicheng Li1, Dongqing Cai1, Chuanjiang Li1, Jie Zhou1, Jieyuan Li5,7*, Yiyi Li6* and Kai Wang1* Abstract Background Accurate stratification of recurrence risk after curative resection remains a critical challenge in the management of hepatocellular carcinoma (HCC). Dysregulated ceramide (CER) metabolism has been implicated in HCC progression and relapse. This paper evaluates whether preoperative plasma CER profiling coupled with machine learning (ML) enhances the risk prediction of HCC recurrence. Methods In this retrospective study, 257 HCC patients undergoing curative resection participated. Preoperative plasma CERs were quantified by targeted Lipidomics. Independent predictors were identified via multivariate Cox regression and incorporated into ten ML models. Using an internal 20% validation cohort, model performance was assessed by the area under the curve (AUC), concordance index (C-index), calibration, and decision curve analysis. Model interpretability employed Shapley additive explanations (SHAP), correlation analysis, and Bayesian network-based causal inference. The model’s risk stratification capability was evaluated. This study was registered on clinicaltrials.gov (NCT06623474). Results Preoperative plasma CERs exhibited significant prognostic value in patients with HCC after curative resections. Multivariate analyses revealed that serum α-fetoprotein (AFP), tumor size, CER(d18:1/20:1), and CER(d18:1/22:1) independently predicted recurrence, and these variables were incorporated into ten ML models. Among them, the gradient boosting machine (GBM) algorithm demonstrated the best predictive performance † Yang Lei, Chen Xie and Xiangyue Mo Authors share co-first authorship. *Correspondence: Jieyuan Li Yiyi Li Kai Wang Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creati vecommons.org/licenses/by-nc-nd/4.0/. Lei et al. Lipids in Health and Disease (2025) 24:355 Page 2 of 21 (AUC: 0.959 at 1 year, 0.954 at 2 years, 0.931 at 3 years; C-index ≈ 0.93), outperforming all the other approaches. Model interpretability analysis (SHAP) highlighted tumor burden as the major determinant, with CER (d18:1/20:1) acting as a recurrence-promoting factor, and CER (d18:1/22:1) exerting a protective effect. Correlation analyses further revealed that CER(d18:1/20:1) was positively related to tumor multiplicity, systemic inflammation, and shorter recurrence-free survival (RFS), whereas CER(d18:1/22:1) was linked to better liver function and longer RFS. Bayesian causal inference indicated that elevated CER(d18:1/20:1) directly accounted for approximately 26% of the recurrence risk through effects on AFP and tumor size, whereas reduced CER(d18:1/22:1) conferred approximately 30% causal protection by modulating RFS, AFP, Liver function, and inflammation. Notably, the GBM model successfully identified 54 of 56 recurrent cases as high risk, enabling clear stratification of patients for precision surveillance. Conclusions Preoperative plasma CER profiling, integrated with clinical parameters in a GBM framework, provides a highly accurate and interpretable strategy for predicting postoperative HCC recurrence, which paves the way for precise risk stratification and targeted management. This study provides insights that may enhance liver health and reduce disease burden in patients with HCC. Keywords Hepatocellular carcinoma, Ceramides, Recurrence, Machine learning, Prognosis Introduction Primary liver cancer remains among the most prevalent malignancies and ranks as the third leading cause of cancer-related mortality worldwide [1–3]. Over the past decade, the global burden of primary Liver cancer has increased substantially, with a 26% increase in incidence and a 25% increase in mortality [4]. Hepatocellular carcinoma (HCC), which accounts for approximately 80% of all primary liver cancer cases [5]underscores the urgent need for more effective strategies to mitigate its significant burden. Although resection remains the primary curative treatment for HCC, clinical evidence reveals alarmingly high recurrence rates, exceeding 40% within the first two years and surpassing 70% within five years post-operatively [6]. Recurrence after resection has thus emerged as a major therapeutic challenge. Given that both preoperative and postoperative adjuvant therapies have been shown to reduce recurrence and prolong recurrence-free survival (RFS), stratified risk management based on preoperative prognostic estimation is essential [7]. Therefore, accurate risk prediction and timely identification of high-risk individuals enable the implementation of targeted preventive strategies, which are pivotal for improving long-term outcomes in patients with HCC [6]. The investigation of reliable prognostic biomarkers for HCC has intensified. Recent evidence has indicated that dysregulated lipid metabolism contributes to HCC progression and yields valuable prognostic circulating biomarkers [8]. In particular, cancer-associated alterations in lipid metabolites, especially sphingolipids such as ceramides (CERs), have been closely linked to tumor behavior [9, 10]. Comprehensive multiomics analyses of HCC have revealed significant changes in lipid pathways, including the accumulation of certain CER species in tumors, which are correlated with aggressive disease features [9, 10]. CERs are bioactive lipids known to regulate cell death and survival; consistent with this, HCC cells often reprogram CER metabolism to favor tumor growth [9, 10]. The upreg (...truncated)