Correspondence to letter to the editor 2 on “Conventional and machine learning-based risk scores for patients with early-stage hepatocellular carcinoma”

Article information

Clin Mol Hepatol. 2025;31(1):e101-e102
Publication date (electronic) : 2024 November 6
doi : https://doi.org/10.3350/cmh.2024.0946
1Division of Gastroenterology and Hepatology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
2Department of Health Service Administration, College of Public Health, China Medical University, Taichung, Taiwan
3Division of General Medicine, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
4School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
5Institute of Clinical Medicine, School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
Corresponding author : Chien-Wei Su Division of General Medicine, Department of Medicine, Taipei Veterans General Hospital, No. 201, Sec. 2, Shih-Pai Rd., Peitou District, Taipei 11217, Taiwan Tel: +886-2-28712121 ext. 3352, Fax: +886-2-28739318, E-mail: cwsu2@vghtpe.gov.tw
Editor: Han Ah Lee, Chung-Ang University College of Medicine, Korea
Received 2024 October 25; Accepted 2024 November 1.

Dear Editor,

We would like to express our gratitude for the insightful comments by Xiping Shen and Ji Wu [1] on our recent work [2]. We are grateful for the opportunity to further discuss our methodology and findings.

Shen et al comments regarding the incorporation of competing risks are well-founded. However, whether patients with early-stage hepatocellular carcinoma (HCC) primarily die from liver-related events remains a matter of debate. Since early-stage HCC generally has a relatively favorable prognosis [3], our goal is to identify those truly at risk of mortality rather than focusing solely on liver-related events. Mortality directly related to the tumor was less frequently observed in early-stage HCC patients compared to those with advanced-stage HCC. Several previous studies have demonstrated the impact of non-liver and non-tumor factors on the prognosis of patients with early-stage HCC, such as systemic inflammation, liver functional reserve, and nutritional status [4,5]. Additionally, we adjusted for antiviral agent usage and other common confounding factors in our analysis. It is also common for researchers to consider all-cause mortality as the primary outcome of their research, especially for early-stage HCC [5,6]. We appreciate Shen et al.’s thoughtful comments and would like to provide a broader perspective on the outcome measures for HCC patients.

In their second point, Shen et al. suggested exploring additional demographic and clinical factors, including prophylactic antiviral treatment, treatment modality, Charlson Comorbidity Index (CCI), and socioeconomic factors, all of which could indeed influence survival outcomes. We fully agree that treatment modality is a key factor in patient survival, and this was included in our study [2,7]. Regarding socioeconomic factors, our study was conducted at a tertiary center in Taiwan, where treatment guidelines are clear and healthcare insurance coverage is extensive, minimizing the impact of socioeconomic factors on the treatment access [8]. As for the CCI, while it is an important measure of comorbidity, our objective was to develop a score that could be more easily applied in clinical settings. Therefore, we focused on overall survival and specific comorbidities, rather than retrospectively assessing 19 different disease categories over the past year to convert them into a score. Shen et al.’s suggestions are valuable, and we addressed these considerations during the design of our study.

Lastly, regarding the association between gender and survival, we appreciate the suggestion to conduct a subgroup analysis based on gender. Although sex-based differences in HCC prognosis have garnered increasing attention, the results remain controversial. We previously published a study demonstrating that gender was not an independent predictor of outcomes in HCC patients, especially in those over 50 years old [9]. In our current analysis, we observed similar findings, with gender not emerging as an independent risk factor for overall survival in HCC patients. Therefore, we believe that a gender-based subgroup analysis is less urgent in our cohort.

Once again, we sincerely appreciate the comments by Shen et al. We believe that machine learning continues to provide valuable insights into the survival analysis of patients with various diseases, including HCC [10]. We hope our responses clarify our approach and underscore our commitment to advancing the understanding of HCC prognosis.

Notes

Authors’ contribution

Conceptualization, E C-H Tan and C-W Su; Original draft, C-T Ho; Review and editing, C-W Su.

Conflicts of Interest

There are no potential conflicts of financial and non-financial interests in the study. Chien-Wei Su: Speakers’ bureau: Gilead Sciences, Bristol-Myers Squibb, AbbVie, Bayer, and Roche. Advisory arrangements: Gilead Sciences. Grants: Bristol-Myers Squibb and Eiger.

Abbreviations

CCI

Charlson Comorbidity Index

HCC

hepatocellular carcinoma

References

1. Shen X, Wu J. Development of risk scores for prognosis prediction among patients with early-stage hepatocellular carcinoma. Clin Mol Hepatol 2025;31:e17–e18.
2. Ho CT, Tan EC, Lee PC, Chu CJ, Huang YH, Huo TI, et al. Conventional and machine learning-based risk scores for patients with early-stage hepatocellular carcinoma. Clin Mol Hepatol 2024;30:406–420.
3. Yang JD. Detect or not to detect very early stage hepatocellular carcinoma? The western perspective. Clin Mol Hepatol 2019;25:335–343.
4. Ho CT, Chia-Hui Tan E, Lee PC, Chu CJ, Huang YH, Huo TI, et al. Prognostic nutritional index as a prognostic factor for very early-stage hepatocellular carcinoma. Clin Transl Gastroenterol 2024;15:e00678.
5. Chang CY, Wei CY, Chen PH, Hou MC, Chao Y, Chau GY, et al. The role of albumin-bilirubin grade in determining the outcomes of patients with very early-stage hepatocellular carcinoma. J Chin Med Assoc 2021;84:136–143.
6. Wang Q, Qiao W, Zhang H, Liu B, Li J, Zang C, et al. Nomogram established on account of Lasso-Cox regression for predicting recurrence in patients with early-stage hepatocellular carcinoma. Front Immunol 2022;13:1019638.
7. Llovet JM, De Baere T, Kulik L, Haber PK, Greten TF, Meyer T, et al. Locoregional therapies in the era of molecular and immune treatments for hepatocellular carcinoma. Nat Rev Gastroenterol Hepatol 2021;18:293–313.
8. Chien RN, Lu SN, Pwu RF, Wu GH, Yang WW, Liu CL. Taiwan accelerates its efforts to eliminate hepatitis C. Glob Health Med 2021;3:293–300.
9. Liao CY, Lee CY, Wei CY, Chao Y, Huang YH, Hou MC, et al. Differential prognoses among male and female patients with hepatocellular carcinoma. J Chin Med Assoc 2022;85:554–565.
10. Dai J, Lai JC, Wong GL, Yip TC. Unlocking the future: machine learning sheds light on prognostication for early-stage hepatocellular carcinoma: editorial on “conventional and machine learning-based risk scores for patients with early-stage hepatocellular carcinoma”. Clin Mol Hepatol 2024;30:698–701.

Article information Continued