Abstract
Background
Currently, it is still confused whether preoperative aminotransferase-to-platelet ratio (APRI) and gamma-glutamyl transferase-to-platelet ratio (GPR) can predict microvascular invasion (MVI) in solitary hepatocellular carcinoma (HCC). We aimed to develop and validate a machine-learning integration model for predicting MVI using APRI, GPR and gadoxetic acid disodium (Gd-EOB-DTPA) enhanced MRI.
Methods
A total of 314 patients from XinQiao Hospital of Army Medical University were divided chronologically into training set (n = 220) and internal validation set (n = 94), and recurrence-free survival was determined to follow up after surgery. Seventy-three patients from Chongqing University Three Gorges Hospital and Luzhou People’s Hospital served as external validation set. Overall, 387 patients with solitary HCC were analyzed as whole dataset set. Least absolute shrinkage and selection operator, tenfold cross-validation and multivariate logistic regression were used to gradually filter features. Six machine-learning models and an ensemble of the all models (ENS) were built. The area under the receiver operating characteristic curve (AUC) and decision curve analysis were used to evaluate model’s performance.
Results
APRI, GPR, HBPratio3 ([liver SI‒tumor SI]/liver SI), PLT, peritumoral enhancement, non-smooth margin and peritumoral hypointensity were independent risk factors for MVI. Six machine-learning models showed good performance for predicting MVI in training set (AUCs range, 0.793–0.875), internal validation set (0.715–0.832), external validation set (0.636–0.746) and whole dataset set (0.756–0.850). The ENS achieved the highest AUCs (0.879 vs 0.858 vs 0.839 vs 0.851) in four cohorts with excellent calibration and more net benefit. Subgroup analysis indicated that ENS obtained excellent AUCs (0.900 vs 0.809 vs 0.865 vs 0.908) in HCC >5cm, ≤5cm, ≤3cm and ≤2cm cohorts. Kaplan‒Meier survival curves indicated that ENS achieved excellent stratification for MVI status.
Conclusion
The APRI and GPR may be new potential biomarkers for predicting MVI of HCC. The ENS achieved optimal performance for predicting MVI in different sizes HCC and may aid in the individualized selection of surgical procedures.
Abbreviations
AFP, α-fetoprotein; AUC, area under the curve; ALP, alkaline phosphatase; AST, aspartate aminotransferase; APRI, aminotransferase-to-platelet ratio; ALT, alanine aminotransferase; DCA, decision curve analysis; HBP, hepatobiliary phase; Gd-EOB-DTPA, gadoxetic acid disodium; LR, logistic regression; Xgboost, eXtreme Gradient Boosting; Knn, K-nearest neighbor; ROC, receiver operating characteristic curve; GPR, gamma-glutamyl transferase-to-platelet ratio; HCC, hepatocellular carcinoma; MVI, microvascular invasion; LASSO, least absolute shrinkage and selection operator logistic regression; ICC, intraclass correlation coefficient; SI, signal intensity; PLT, platelet count; MRI, magnetic resonance imaging; Neu, neutrophilic granulocyte count; RF, random forest; Tree, decision Tree; SVM, support Vector Machine; OS, overall survival; RFS, recurrence-free survival; ENS, ensemble models.
Data Sharing Statement
The original manuscript contained in the research is included in the article. Further inquiries can be made directly to the corresponding author.
Ethics Statement
This retrospective study was approved by the Ethics Committee of XinQiao Hospital of the Army Medical University (No: 2023-047-01) and was in conformation with the ethical guidelines of the 2008 Declaration of Helsinki. As a retrospective study, to ensure patient confidentiality, the identities of the individuals included in this study were anonymized using computer-generated ID numbers. Thus, the requirement for written informed consent was waived.
Consent to Publish
All authors have read and approved the submitted manuscript, the manuscript has not been submitted elsewhere nor published elsewhere in whole or in part.
Acknowledgments
The authors thank American Journal Experts (AJE) for assisting in the preparation of this paper.
Disclosure
All authors have no relevant financial or non-financial interests to disclose for this work.