Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
A Model Based on Artificial Intelligence Algorithm for Monitoring Recurrence of HCC after Hepatectomy: A Multicenter Study
27 Pages Posted: 16 Oct 2019
More...Abstract
Objective: There is no satisfactory indicator for monitoring recurrence after resection in hepatocellular carcinoma (HCC). For patients without metastasis after hepatectomy, an HCC monitor recurrence (HMR) model was designed and validated by a multicenter retrospective study.
Methods: A training cohort was recruited of 1179 patients with HCC without metastasis after hepatectomy from February 2012 to December 2015. An HMR model was proposed with an AdaBoost classifier algorithm; factors included patient age, TNM staging, tumor size, and pre/postoperative dynamic variations of alpha-fetoprotein (AFP). The diagnostic efficacy of the model was evaluated relative to that of the traditional AFP monitoring recurrence model based on the areas under the respective receiver operating characteristic curves (AUCs). Prediction of recurrence was evaluated relative to computed tomography/magnetic resonance imaging (CT/MRI). The model was validated via an internal cohort comprising 695 patients, and two external cohorts of 30 and 33 patients, respectively.
Results: In preoperative patients with positive or negative AFP, the AUCs of the HMR model (0.8708-0.9609) indicated better diagnostic efficacy compared with serum AFP (0.7348-0.8196). The HMR model predicted recurrence earlier than did CT/MRI, by 77.64 to 191.58 days.
Conclusion: The HMR model was more accurate than serum AFP for monitoring recurrence after hepatectomy of HCC, and can be used for real-time monitoring of the postoperative status of patients with HCC without metastasis. The HMR model should help individualize strategies for reexaminations, and guide adjuvant treatment schemes for patients with HCC.
Funding Statement: This work was supported by grants from the National Natural Science Foundation of China (grant no. 81602468 & 81800556).
Declaration of Interests: The authors declare no competing interests.
Ethics Approval Statement: The Ethics Committee of Sun Yat-Sen University Cancer Center (SYSUCC) approved this study. Every participant provided signed informed consent.
Keywords: hepatocellular carcinoma; model; hepatectomy; monitor; recurrence
Suggested Citation: Suggested Citation