Introduction

Chronic liver disease is a major global health concerns, contributing to over 1.4 million annual deaths worldwide¹. Its primary fatal outcomes, hepatic complications^2,3, arise from liver cirrhosis, hepatocellular carcinoma and hepatic decompensation. The early, reversible stages of chronic liver disease are frequently asymptomatic and overlooked, leading to delayed diagnoses and irreversible complications that treatment options are limited.^4,5. Therefore, reliable tools to identify whether a person will develop hepatic complications in the future have become a public health priority, enabling early diagnosis and timely intervention in high-risk populations.

Aims & Methods

This study aimed to employ machine learning to develop proteomics-based models for the early identification of hepatic complications. In this study, 37,178 adults without hepatic complications at baseline were analyzed from a prospective cohort from United Kingdom, with plasma levels of 2,736 proteins measured using Olink technology. Cox regression was used to identify significant proteins associated with incident hepatic complications. Models based on importance-top-ranking proteins were constructed using LightGBM learners of Automated Machine Learning (AutoML) and internal validated through 5-fold cross validation in the derivation set (n = 37,178). Independent validation was then conducted in a geographically distinct UKB cohort (n = 15,767).

Results

Over a median follow-up of 13.8 years, 338 participants developed hepatic complications. Cox regression identified 593 proteins significantly associated with incident hepatic complications. Among them, GDF15, PROC, GGT1, ANXA10, IL18, MFAP4, COL4A1, CDCP1 and IL6 were ranked highest in protein importance ordering. The protein model showed a considerable predictive accuracy for hepatic complications under different time scenarios in the UKB validation set: all-year (area under the curve [AUC] = 0.89), within 5 years (AUC = 0.88), within 10 years (AUC = 0.91), over 10 years (AUC = 0.81), and achieved superior predictive performance compared to models with demographic predictors, laboratory indicators, polygenic risk score (PRS) and traditional risk score models (Protein 0.89 vs. Demographics 0.83, Laboratory 0.85, PRS 0.49; Fibrosis-4 index [FIB-4] 0.76, Aspartate aminotransferase to platelet ratio index [APRI] 0.78; all P < 0.05). Combined with clinical data and PRS, the predictor performance is further enhanced: all-year (AUC = 0.91), within 5 years (AUC = 0.91), within 10 years (AUC = 0.90), over 10 years (AUC = 0.83). Individuals in the high-risk group stratified by the protein model were 16.27 times more likely to develop hepatic complications.

Conclusion

Our study constructed a novel protein model for hepatic complications risk stratification and could be used to predict individuals who will develop hepatic complications up to 16 years in advance in the general population.

References

1. Tham EKJ, Tan DJH, Danpanichkul P, et al. The Global Burden of Cirrhosis and Other Chronic Liver Diseases in 2021. Liver Int 2025;45:e70001.
2. Åberg F, Asteljoki J, Männistö V, et al. Combined use of the CLivD score and FIB-4 for prediction of liver-related outcomes in the population. Hepatol Baltim Md 2024;80:163–172.
3. Innes H, Morling JR, Buch S, et al. Performance of routine risk scores for predicting cirrhosis-related morbidity in the community. J Hepatol 2022;77:365–376.
4. Karlsen TH, Sheron N, Zelber-Sagi S, et al. The EASL–Lancet Liver Commission: protecting the next generation of Europeans against liver disease complications and premature mortality. The Lancet 2022;399:61–116.
5. Serra-Burriel M, Juanola A, Serra-Burriel F, et al. Development, validation, and prognostic evaluation of a risk score for long-term liver-related outcomes in the general population: a multicohort study. Lancet Lond Engl 2023;402:988–996.

Introduction

Accurate endoscopic diagnosis of colorectal polyps is essential for determining appropriate treatment strategies. The Japan NBI Expert Team (JNET) classification and pit pattern diagnosis are used for diagnosis, but their comparative diagnostic performance in real-world clinical settings remains unclear, particularly between experts and non-experts.

Aims & Methods

This post-hoc analysis aimed to evaluate the diagnostic accuracy of both classification across different levels of expertise using data from a prospective multicenter trial. We conducted a post-hoc analysis of the deTXIon trial¹ , a randomized controlled trial conducted at eight Japanese institutions between March and October 2023. From the per-protocol set, we analyzed colorectal lesions that had both JNET classification and pit pattern diagnosis with confirmed histopathology. JNET classification categorizes lesions into Type 1 (corresponding to hyperplastic polyps [HPs] and sessile serrated lesions [SSLs]), Type 2A (low-grade adenomas), Type 2B (high-grade adenomas or superficial submucosal invasive cancer), and Type 3 (deep submucosal invasive cancer). Pit pattern classification included Type II ( HPs/SSLs ), Type III_S/III_L/IV (low-grade adenomas), Type V_I low-grade (high-grade adenoma), and Type V_I high-grade/V_N (submucosal invasive cancer). We calculated sensitivity (Sen), specificity (Spe), positive predictive value (PPV), and negative predictive value (NPV) for each classification stratified by endoscopist expertise and lesion size.

Results

A total of 1,617 colorectal lesions with a median size (IQR) of 2(1-4) mm were included in this analysis. Histopathological examination revealed that 71.5% (1,156/1,617) were low-grade adenomas, 1.0% (16/1,617) were high-grade adenomas or cancer, 19.3% were HPs (312/1,617), and 8.2% (133/1,617) were SSLs. For JNET Type 1 lesions, diagnostic accuracy was comparable between experts (Sen: 82.8%, Spe: 95.9%, PPV: 88.3%, NPV: 93.7%) and non-experts (Sen: 81.7%, Spe: 93.4%, PPV: 83.1%, NPV: 92.8%). Similarly, for JNET Type 2A, both groups showed high diagnostic performance (experts: Sen 93.8%, Spe 81.0%, PPV: 92.6%, NPV: 83.8%; non-experts: Sen 91.5%, Spe 78.3%, PPV: 90.3%, NPV: 80.6%).
In contrast, pit pattern diagnosis experts showed higher performances, particularly for Type II (experts: Sen 80.9%, Spe 96.3%, PPV: 89.0%, NPV: 93.1%; non-experts: Sen 57.9%, Spe 92.8%, PPV: 76.0%, NPV: 84.8%). The diagnostic performance for small lesions (≤5mm) was consistently high with JNET classification (Type 1: Sen 79.5%, Spe 94.3%; Type 2A: Sen 93.7%, Spe 79.2%), while pit pattern diagnosis showed lower performance (Type II: Sen 70.8%, Spe 94.5%; Type III_S/III_L/IV: Sen 93.6%, Spe 79.5%), for these lesions among non-experts.

Conclusion

JNET classification demonstrates comparable diagnostic performance between expert and non-expert endoscopists, likely due to its standardized and intuitive visual criteria. Pit pattern diagnosis shows experience-dependent performance differences, suggesting that NBI-based assessment may be more suitable for routine clinical practice, especially for diminutive lesions.

References

1. Toyoshima N, Mizuguchi Y, Takamaru H,et al. The Efficacy of Texture and Color Enhancement Imaging Observation in the Detection of Colorectal Lesions: A Multicenter, Randomized Controlled Trial (deTXIon Study). Gastroenterology. 2025 in press

Disclosure

These authors disclose the following: Yutaka Saito, Masashi Misawa, Shin-ei Kudo, and Toshio Uraoka have received lecture fees from Olympus
Corporation. The remaining authors disclose no conflicts.