Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
Liver stiffness-platelet ratio index and machine learning models for the noninvasive diagnosis of significant fibrosis in chronic hepatitis B
Jun-Yi Lin, Zao-Xiu Ai, Man-Jin Luo, Li-Zhen Su, Xin-Gen Gao, Hua-Li Jiang, Ju-Qiang Lin, Hong-Yi Zhang, Ying-Ying Sun, Hong-Tao Yu, Li Zhang, Xian-Qiong Gong
Jun-Yi Lin, Xian-Qiong Gong, The School of Clinical Medicine, Fujian Medical University, Fuzhou 350122, Fujian Province, China
Jun-Yi Lin, Xian-Qiong Gong, Department of Hepatology and Infectious Disease, Zhongshan Hospital of Xiamen University, Xiamen 361000, Fujian Province, China
Zao-Xiu Ai, Man-Jin Luo, Li-Zhen Su, Ying-Ying Sun, Hong-Tao Yu, Department of Liver Diseases, Xiamen Hospital of TCM, Xiamen 361000, Fujian Province, China
Xin-Gen Gao, Hua-Li Jiang, Ju-Qiang Lin, Hong-Yi Zhang, School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen 361000, Fujian Province, China
Li Zhang, Basic Research Laboratory, Chongqing Hospital of Traditional Chinese Medicine, Chongqing 40010, China
Author contributions: Lin JY was responsible for writing original draft; Lin JY, Ai ZX, Luo MJ, Su LZ, Sun YY, and Yu HT were responsible for data curation and investigation; Lin JY, Ai ZX, Su LZ, Gao XG, Jiang HL, Zhang HY, and Zhang L were responsible for formal analysis and validation; Lin JY, Gao XG, Lin JQ, and Zhang HY were responsible for methodology and software; Lin JY and Jiang HL were responsible for visualization; Lin JY and Gong XQ were responsible for conceptualization and methodology; Gao XG and Gong XQ were responsible for funding acquisition; Gong XQ was responsible for supervision, project administration, writing review and editing; all authors have read and approved the final version of the manuscript.
Supported by Fujian Provincial Health Technology Project, No. 2022GGB020; Xiamen Science and Technology Program, No. 3502Z20224020; Traditional Chinese Medicine Foundation of Xiamen, No. XWZY-2023-0610; Xiamen Science and Technology Major Project, No. 3502Z202374113; Natural Science Foundation of Fujian Province, No. 2023J011456 and No. 2023J05084; and Natural Science Foundation of Xiamen, No. 3502Z202373057.
Institutional review board statement: The study protocol was approved by the Medical Ethics Committee of Xiamen Hospital of TCM (No. 2024-k027-01).
Informed consent statement: The requirement for informed consent was waived by the ethics committee due to the retrospective design and anonymization of all patient data, in accordance with the Declaration of Helsinki.
Conflict-of-interest statement: All authors declare no conflict of interest in publishing the manuscript.
Data sharing statement: All data supporting the findings of this study are included in the
Supplementary material or are available from the corresponding author upon reasonable request.
Corresponding author: Xian-Qiong Gong, Chief Physician, The School of Clinical Medicine, Fujian Medical University, No. 88 Jiaotong Road, Taijiang District, Fuzhou 350005, Fujian Province, China.
xianqiong-gong@hotmail.com
Received: February 6, 2026
Revised: February 23, 2026
Accepted: April 16, 2026
Published online: May 27, 2026
Processing time: 109 Days and 15.7 Hours
BACKGROUND
Effective noninvasive tools for identifying significant liver fibrosis remain limited in untreated chronic hepatitis B (CHB).
AIM
To assess a liver stiffness-platelet ratio index (LPRI) derived from transient elastography and platelet count, and to evaluate its incremental value when incorporated into machine learning (ML) and deep learning (DL) models.
METHODS
We retrospectively enrolled 1098 therapy-naïve patients with CHB who underwent liver biopsy with Scheuer staging. Significant fibrosis was defined as S2-S4. We compared eight noninvasive tests and trained ML and DL models with and without the index (LPRI). Discrimination and clinical utility were assessed using the area under the receiver operating characteristic curve and decision curve analysis.
RESULTS
In feature selection analyses, liver stiffness measurement and platelet count ranked as the top predictors of significant fibrosis. LPRI outperformed conventional scores such as the aspartate aminotransferase-to-platelet ratio index and fibrosis-4, achieving an area under the receiver operating characteristic curve of approximately 0.84 in both the training and validation sets. Adding LPRI improved the performance of ML and DL models, and decision curve analysis suggested a net benefit across clinically relevant threshold probabilities.
CONCLUSION
A LPRI provides a simple, noninvasive approach for first-line screening of significant fibrosis in untreated CHB and may reduce unnecessary liver biopsies.
Core Tip: In this biopsy-based retrospective study of 1098 treatment-naïve patients with chronic hepatitis B, a liver stiffness-platelet ratio index, derived from transient elastography and platelet count, showed strong performance in identifying significant fibrosis (S2-S4) relative to conventional noninvasive scores. Liver stiffness-platelet ratio index also provided incremental value in selected machine learning and deep learning models and demonstrated a net benefit in decision curve analysis, supporting its use as a practical first-line triage tool when liver stiffness measurement and platelet count are routinely available.
