Correspondence on Letter regarding “Toward hepatitis C virus elimination using artificial intelligence”

Article information

Clin Mol Hepatol. 2024;30(2):274-275

Publication date (electronic) : 2024 March 5

doi : https://doi.org/10.3350/cmh.2024.0152

Ming-Ying Lu ¹^,², Ming-Lung Yu^,¹^,²^,³

¹School of Medicine and Doctoral Program of Clinical and Experimental Medicine, College of Medicine and Center of Excellence for Metabolic Associated Fatty Liver Disease, National Sun Yat-sen University, Kaohsiung, Taiwan

²Hepatobiliary Division, Department of Internal Medicine and Hepatitis Center, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan

³Hepatitis Research Center, College of Medicine and Center for Liquid Biopsy and Cohort Research, Kaohsiung Medical University, Kaohsiung, Taiwan

Corresponding author : Ming-Lung Yu Hepatobiliary Division, Department of Internal Medicine, Kaohsiung Medical University Hospital, 100 Tzyou Road, Kaohsiung City 807, Taiwan Tel: +886-7-312-1101 ext. 7475, Fax: +886-7-312-3955, E-mail: fish6069@gmail.com

Editor: Han Ah Lee, Chung-Ang University College of Medicine, Korea

Received 2024 February 28; Accepted 2024 March 1.

Keywords: HCV; DAA; AI; SDG 3

Dear Editor,

We are grateful for the comments [1] from Professor Hur and Professor Lee on our recent publication. We developed artificial intelligence (AI) models for predicting direct-acting antiviral agents (DAAs) failure among a large chronic hepatitis C (HCV) cohort [2]. In patients with decompensated liver cirrhosis, the AI model is beneficial in determining the optimal timing for the initiation of DAA therapy. We agreed that more intensive antiviral therapy beyond the current guidelines may be considered for HCV patients who are susceptible to DAA failure.

Due to the presence of overfitting in the training dataset, the current AI model needs further optimization to improve its generalizability. We have ever tried hyperparameter tuning and simplifying the input features through dimensional reduction to avoid overfitting. In such an imbalanced dataset, it is a challenge to maintain the accuracy of the AI model and avoid overfitting. Unsolved overfitting may imply there are unidentified risk factors regarding treatment response. Our study only incorporated 55 clinical host and virologic features before and after treatment in the current model. The diversity of host genetics, cytokine dynamics, immunity, metabolism, baseline or treatment-emergent resistance-associated substitutions of HCV, etc. may simultaneously affect the efficacy of DAA [3-6]. A combination of multi-omics in the AI model may enhance the predictive accuracy of the validation datasets in the future. Furthermore, all the subjects were enrolled from a single ethnic population. It is necessary to validate this AI model in independent cohorts of various ethnicities. Seeking opportunities for international research collaboration to verify and optimize this AI model is mandatory.

Notes

Authors’ contribution

MY LU drafted the manuscript. ML Yu reviewed and finalized the manuscript.

Conflicts of Interest

MY Lu has no conflicts to disclose. ML Yu disclosed the following: research grant from Abbvie, Gilead, Merck, and Roche diagnostics; consultant for Abbvie, BMS, Gilead, Roche, and Roche diagnostics; and speaker for Abbvie, BMS, Eisai, Gilead, Roche, and Roche diagnostics.

Abbreviations

artificial intelligence

DAAs

direct-acting antiviral agents

HCV

hepatitis C virus

References

1. Hur MH, Lee JH. Toward hepatitis C virus elimination using artificial intelligence. Clin Mol Hepatol 2024;30:147–149.

2. Lu MY, Huang CF, Hung CH, Tai CM, Mo LR, Kuo HT, et al. Artificial intelligence predicts direct-acting antivirals failure among hepatitis C virus patients: A nationwide hepatitis C virus registry program. Clin Mol Hepatol 2024;30:64–79.

3. Kim KA, Lee S, Park HJ, Jang ES, Lee YJ, Cho SB, et al. Nextgeneration sequencing analysis of hepatitis C virus resistanceassociated substitutions in direct-acting antiviral failure in South Korea. Clin Mol Hepatol 2023;29:496–509.

4. Huang CF, Hung CH, Cheng PN, Bair MJ, Huang YH, Kao JH, et al. An open-label, randomized, active-controlled trial of 8 versus 12 weeks of elbasvir/grazoprevir for treatment-naive patients with chronic hepatitis C genotype 1b infection and mild fibrosis (EGALITE Study): Impact of baseline viral loads and NS5A resistance-associated substitutions. J Infect Dis 2019;220:557–566.

5. Huang CF, Yeh ML, Huang JF, Yang JF, Hsieh MY, Lin ZY, et al. Host interleukin-28B genetic variants versus viral kinetics in determining responses to standard-of-care for Asians with hepatitis C genotype 1. Antiviral Res 2012;93:239–244.

6. Lu MY, Huang CI, Dai CY, Wang SC, Hsieh MY, Hsieh MH, et al. Elevated on-treatment levels of serum IFN-gamma is associated with treatment failure of peginterferon plus ribavirin therapy for chronic hepatitis C. Sci Rep 2016;6:22995.

Article information Continued

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.