EUVIMEDEUVIMED entdecken
Validierungsstudie

Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators

Junjie Deng, Wen Song, Yuyu Ma, Bin Fan, Xiumin Ma iD, Yumei Liu

Laboratory Medicine · 05.10.2026 · 57 (6)

DOI: 10.1093/labmed/lmag053 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Laboratory Medicine, online erschienen am 09.10.2026. Verfasst von Junjie Deng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Laboratory Center, Xinjiang Medical University Affiliated Traditional Chinese Medicine Hospital, Urumqi, Xinjiang, People's Republic of Chin…. Hauptthemen laut MEDLINE: Liver Cirrhosis, Diagnostic Tests, Routine. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Xinjiang Strategic Talent Training Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Advanced liver fibrosis is a clinically important stage of chronic liver disease. We developed and internally validated an interpretable model based on routine laboratory tests and benchmarked it against the aspartate aminotransferase to platelet ratio index (APRI) and 4-factor fibrosis index (FIB-4).

Methods

This single-center, retrospective, diagnostic prediction study included 1853 inpatients, of whom 988 had report-defined F3 to F4 fibrosis. Primary validation used 10 repeated, stratified 7:3 outer resamples, with preprocessing, least absolute shrinkage and selection operator selection, and model refitting restricted to each development subset. Discrimination, calibration, decision curves, precision recall performance, and linear SHapley Additive exPlanations values were evaluated.

Results

The leakage-aware pipeline achieved a mean (SD) validation area under the curve of 0.800 (0.015), accuracy of 0.753, sensitivity of 0.775, and specificity of 0.729. The final logistic model included platelet count, total bile acids, C3 and C4, red blood cell count, lymphocyte count, and albumin level. In the representative test set, its area under the curve was 0.809 (95% CI, 0.772-0.845) compared with 0.815 for APRI and 0.821 for FIB-4; neither paired difference was statistically significant after Holm adjustment.

Discussion

The model showed moderate discrimination and interpretable output but was not superior to APRI or FIB-4. External validation is required before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver CirrhosisDiagnostic Tests, RoutineHumansRetrospective StudiesFemaleMaleMiddle AgedAgedPlatelet Count

Stichwörter der Autor:innen

SHAPadvanced liver fibrosischronic liver diseasediagnostic prediction modelmachine learningroutine laboratory indicators

Autor:innen und Institutionen

  • Clinical Laboratory Center, Xinjiang Medical University Affiliated Traditional Chinese Medicine Hospital, Urumqi, Xinjiang, People's Republic of China.
  • Clinical Laboratory Center, State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Tumor Hospital Affiliated to Xinjiang Medical University, Urumqi, Xinjiang, People's…
  • Basic Medical College of Xinjiang Medical University, Urumqi, Xinjiang, China.

ORCID-Profile: Xiumin Ma

Förderung

  • Xinjiang Strategic Talent Training Program

Zitieren

APA

Deng, J., Song, W., Ma, Y., Fan, B., Ma, X., & Liu, Y. (2026). Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators. Laboratory Medicine, 57(6). https://doi.org/10.1093/labmed/lmag053

Vancouver

Deng J, Song W, Ma Y, Fan B, Ma X, Liu Y. Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators. Laboratory Medicine. 2026;57(6). doi:10.1093/labmed/lmag053

BibTeX
@article{Deng2026,
  author = {Deng, Junjie and Song, Wen and Ma, Yuyu and Fan, Bin and Ma, Xiumin and Liu, Yumei},
  title = {Development and internal validation of a diagnostic prediction model for advanced liver fibrosis based on routine laboratory indicators},
  journal = {Laboratory Medicine},
  year = {2026},
  volume = {57},
  number = {6},
  doi = {10.1093/labmed/lmag053}
}
Kostenlos starten →