Development and Validation of Predictive Machine Learning Models for Postoperative Recurrence and Microvascular Invasion in Hepatocellular Carcinoma Using Nuclear Magnetic Resonance Metabolomics.
1/5 보강
[BACKGROUND] Hepatocellular carcinoma (HCC) has a poor prognosis, necessitating better diagnostic tools.
- p-value P < 0.001
- 95% CI 1.11-1.30
- HR 1.20
APA
Tan H, Xu Y, et al. (2026). Development and Validation of Predictive Machine Learning Models for Postoperative Recurrence and Microvascular Invasion in Hepatocellular Carcinoma Using Nuclear Magnetic Resonance Metabolomics.. Journal of hepatocellular carcinoma, 13, 589098. https://doi.org/10.2147/JHC.S589098
MLA
Tan H, et al.. "Development and Validation of Predictive Machine Learning Models for Postoperative Recurrence and Microvascular Invasion in Hepatocellular Carcinoma Using Nuclear Magnetic Resonance Metabolomics.." Journal of hepatocellular carcinoma, vol. 13, 2026, pp. 589098.
PMID
42003876
Abstract
[BACKGROUND] Hepatocellular carcinoma (HCC) has a poor prognosis, necessitating better diagnostic tools. Nuclear magnetic resonance (NMR)-based metabolomics has emerged as a powerful tool for cancer biomarker discovery, yet its application in HCC prognosis remains underexplored. This study aimed to identify plasma metabolic biomarkers for the diagnosis and prognosis of HCC, and to develop predictive models for postoperative recurrence and microvascular invasion (MVI) to enhance clinical management.
[METHODS] We performed untargeted NMR metabolomic profiling of plasma from 92 HCC patients and 92 matched healthy controls. Differential metabolites were identified, and their diagnostic performance was assessed using receiver operating characteristic curves. Predictive models for postoperative recurrence and MVI were developed and validated using multiple machine learning algorithms, such as random forest, support vector machine, and gradient boosting machine models.
[RESULTS] Significant metabolic differences were identified, with 67 metabolites and blood-lipid indicators showing marked alterations. Acetic acid, dimethylsulfone, glycerol, glycine, and low-density lipoprotein (LDL)-3 cholesterol exhibited the highest discriminatory power (area under the curve [AUC] ≥0.954). Regarding HCC recurrence prediction, the StepCox[forward] + random survival forest model achieved an AUC of 0.811 and was an independent prognostic indicator (multivariate Cox HR = 1.20, 95% CI: 1.11-1.30, P < 0.001). Regarding MVI prediction, the support vector machine model demonstrated superior performance (AUC = 0.957). Calibration curve, decision curve, and SHapley Additive exPlanations (SHAP) analyses confirmed model robustness and clinical utility. Two online platforms were developed for clinical implementation.
[CONCLUSION] This study developed and validated NMR-based prognostic and MVI prediction models for HCC, offering valuable tools for precision management. Their clinical value warrants further validation in larger prospective cohorts.
[METHODS] We performed untargeted NMR metabolomic profiling of plasma from 92 HCC patients and 92 matched healthy controls. Differential metabolites were identified, and their diagnostic performance was assessed using receiver operating characteristic curves. Predictive models for postoperative recurrence and MVI were developed and validated using multiple machine learning algorithms, such as random forest, support vector machine, and gradient boosting machine models.
[RESULTS] Significant metabolic differences were identified, with 67 metabolites and blood-lipid indicators showing marked alterations. Acetic acid, dimethylsulfone, glycerol, glycine, and low-density lipoprotein (LDL)-3 cholesterol exhibited the highest discriminatory power (area under the curve [AUC] ≥0.954). Regarding HCC recurrence prediction, the StepCox[forward] + random survival forest model achieved an AUC of 0.811 and was an independent prognostic indicator (multivariate Cox HR = 1.20, 95% CI: 1.11-1.30, P < 0.001). Regarding MVI prediction, the support vector machine model demonstrated superior performance (AUC = 0.957). Calibration curve, decision curve, and SHapley Additive exPlanations (SHAP) analyses confirmed model robustness and clinical utility. Two online platforms were developed for clinical implementation.
[CONCLUSION] This study developed and validated NMR-based prognostic and MVI prediction models for HCC, offering valuable tools for precision management. Their clinical value warrants further validation in larger prospective cohorts.
같은 제1저자의 인용 많은 논문 (5)
- Assessing Treatment Heterogeneity in Predictive Models for HCC Retreatment Response.
- A Pharmacovigilance Study of Immune Checkpoint Inhibitor-Associated Cholangitis: Insights From the FDA Adverse Event Reporting System.
- exacerbates experimental colitis and colitis-associated colorectal cancer via pathogenic NETosis activation.
- Circulating levels of high mobility group box-1 and nucleophosmin/B23 proteins and clinical significance in debut non-small cell lung cancer patients.
- Comparative analysis of metabolome and transcriptomes to explore the inhibited influence of sonodynamic therapy combined with lonidamine on hepatocellular carcinoma.