AUTHOR=Liu Xiaoli , Wang Xinhui , Yu Lihua , Hou Yixin , Jiang Yuyong , Wang Xianbo , Han Junyan , Yang Zhiyun 

TITLE=A Novel Prognostic Score Based on Artificial Intelligence in Hepatocellular Carcinoma: A Long-Term Follow-Up Analysis

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.817853

DOI=10.3389/fonc.2022.817853

ISSN=2234-943X

ABSTRACT=Object: T cell immunity plays an important role in the anti-tumor effect, and immunosuppression often leads to the development and relapse of cancer. This study was to investigate the effect of T cell number on the long-term prognosis of patients with hepatocellular carcinoma (HCC), and to construct artificial neural networks (ANNs) model to evaluate its prognostic value.
Methods: We enrolled 3427 patients with HCC in Beijing Ditan Hospital, Capital Medical University, and randomly divided them into two groups, 1861 as training set and 809 as validation set. Cox regression analysis were used to screen the independent risk factors of survival in HCC patients. These factors are used to build artificial neural networks (ANNs) model by Python programming language. Concordance index, calibration curve and decision curve analysis were used to evaluate the performance of ANNs model.
Results: The 1-year, 3-year, 5-year and 10-year cumulative OS were 66.9%, 45.7%, 34.9% and 22.6%, respectively. Cox multivariate regression analysis showed that age, white blood cell count, creatinine, total bilirubin, γ-GGT, LDH, tumor ≥ 5cm, tumor number ≥ 2, portal vein tumor thrombus and AFP ≥ 400ng/ml were independent risk factors for long-term survival of HCC. Antiviral therapy, albumin, T cell and CD8 T cell counts were independent protective factors. The ANNs model for long-term survival was constructed. The area under the ROC curve of 1-year, 3-year and 5-year OS by ANNs were 0.838, 0.833 and 0.843, respectively; which were higher than BCLC, TNM, Okuda, CUPI, CLIP, JIS and ALBI models (P < 0.0001). According to the scores of ANNs model, all patients were divided into high-, middle-, and low-risk groups. Compared with low-risk patients, the hazard ratios of 5-year OS of high-risk group were 8.11 (95% CI: 7.0-9.4), 6.13 (95%CI 4.28-8.79) (P<0.0001) in the training set and validation set, respectively.
Conclusion: High levels of circulating T cells and CD8 T cells in peripheral blood may benefit the long-term survival of HCC patients. ANNs model has good individual prediction performance, which can be contribute to assess the prognosis of HCC and lay the foundation for the implementation of precision treatment in the future.