Hepatobiliary and Pancreatic Diseases: Novel Strategies of Diagnosis and Treatments

30 pages, 7385 KB

Open AccessReview

Spectrum of Biliary Lesions/Neoplasms in Hepatic Parenchyma with Reference to a Precursor of Small Duct-Type Intrahepatic Cholangiocarcinoma: Comprehensive Categorization into Three Groups

by Yasuni Nakanuma, Motoko Sasaki, Yuko Kakuda and Takuma Oishi

Cancers 2026, 18(2), 328; https://doi.org/10.3390/cancers18020328 - 21 Jan 2026

Viewed by 235

Abstract

Intrahepatic cholangiocarcinomas (iCCAs) are histologically subdivided into small duct-type (SD-iCCA) and large duct-type (LD-iCCA). LD-iCCA versus SD-iCCA may differ in the molecular/genetic profiles and oncogenesis, including precursor lesions. While several precursors, such as high-grade biliary intraepithelial neoplasm (BilIN) and intraductal papillary neoplasm of bile duct (IPNB), have been proposed for LD-iCCA, the potential SD-iCCA precursors remain to be identified. Amid growing interests in the precursors of SD-iCCA, benign “biliary lesions/neoplasms developing in the hepatic parenchyma (BLNP)” such as von Meyenburg complexes (VMCs), bile duct adenomas (BDAs), and biliary adenofibroma (BAF), have been noted to determine whether they have the potential for precursor of SD-iCCA. Herein, these BLNPs were reviewed. BLNP can be classified into three categories. First, traditional VMC and BDA in normal livers which lack atypical features are categorized as “traditional BLNP”. Second, a constellation of several lesions such as VMC and BDA detectable in the background livers of SD-iCCA and in chronic liver disease (unusual VMC and BDA), VMC with dysplastic features, BDA located in the deep hepatic parenchyma, multiple BDA, BDA presenting the BRAF V600E mutation, and BAF harboring variable dysplasia or in situ carcinomas, which may include neoplastic lesions but do not show invasive growth, are categorized as “unusual/dysplastic BLNP”. Third, tubulocystic carcinoma with BAF-like features (AI-TCC) and SD-iCCA with ductal plate malformation (DPMP) which share overlapping features and show relatively good post-operative outcomes and retained features of VMC or DPM, and BDA and BAF, are categorized as “low-grade malignant BLNP”. While the first category is benign and may not be related to SD-iCCA, some of the second category may be related to SD-iCCA, and the third category is malignant and shows invasive growth. The latter two categories may form a common biliary tumorigenic spectrum involving BLNP. Precursors of SD-iCCA, if they exist, may be included in the second category, and the third category may represent unique carcinomas possibly associated with or followed by conventional SD-iCCA. In conclusion, this novel approach to categorize BLNPs into three categories guarantees further studies of precursors of and their progression to conventional SD-iCCA. Full article

(This article belongs to the Topic Hepatobiliary and Pancreatic Diseases: Novel Strategies of Diagnosis and Treatments—Second Edition)

► Show Figures

Figure 1

14 pages, 1176 KB

Open AccessSystematic Review

The Efficacy of Electronic Health Record-Based Artificial Intelligence Models for Early Detection of Pancreatic Cancer: A Systematic Review and Meta-Analysis

by George G. Makiev, Igor V. Samoylenko, Valeria V. Nazarova, Zahra R. Magomedova, Alexey A. Tryakin and Tigran G. Gevorkyan

Cancers 2026, 18(2), 315; https://doi.org/10.3390/cancers18020315 - 20 Jan 2026

Viewed by 154

Abstract

Background: The persistently low 5-year survival rate for pancreatic cancer (PC) underscores the critical need for early detection. However, population-wide screening remains impractical. Artificial Intelligence (AI) models using electronic health record (EHR) data offer a promising avenue for pre-symptomatic risk stratification. Objective: To systematically review and meta-analyze the performance of AI models for PC prediction based exclusively on structured EHR data. Methods: We systematically searched PubMed, MedRxiv, BioRxiv, and Google Scholar (2010–2025). Inclusion criteria encompassed studies using EHR-derived data (excluding imaging/genomics), applying AI for PC prediction, reporting AUC, and including a non-cancer cohort. Two reviewers independently extracted data. Random-effects meta-analysis was performed for AUC, sensitivity (Se), and specificity (Sp) using R software version 4.5.1. Heterogeneity was assessed using I² statistics and publication bias was evaluated. Results: Of 946 screened records, 19 studies met the inclusion criteria. The pooled AUC across all models was 0.785 (95% CI: 0.759–0.810), indicating good overall discriminatory ability. Neural Network (NN) models demonstrated a statistically significantly higher pooled AUC (0.826) compared to Logistic Regression (LogReg, 0.799), Random Forests (RF, 0.762), and XGBoost (XGB, 0.779) (all p < 0.001). In analyses with sufficient data, models like Light Gradient Boosting (LGB) showed superior Se and Sp (99% and 98.7%, respectively) compared to NNs and LogReg, though based on limited studies. Meta-analysis of Se and Sp revealed extreme heterogeneity (I² ≥ 99.9%), and the positive predictive values (PPVs) reported across studies were consistently low (often < 1%), reflecting the challenge of screening a low-prevalence disease. Conclusions: AI models using EHR data show significant promise for early PC detection, with NNs achieving the highest pooled AUC. However, high heterogeneity and typically low PPV highlight the need for standardized methodologies and a targeted risk-stratification approach rather than general population screening. Future prospective validation and integration into clinical decision-support systems are essential. Full article

(This article belongs to the Topic Hepatobiliary and Pancreatic Diseases: Novel Strategies of Diagnosis and Treatments—Second Edition)

► Show Figures

Figure 1

Submit your Abstract

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Cancers cancers	4.4	8.8	2009	19.1 Days	CHF 2900	Submit
Diagnostics diagnostics	3.3	5.9	2011	21.6 Days	CHF 2600	Submit
Journal of Clinical Medicine jcm	2.9	5.2	2012	18.5 Days	CHF 2600	Submit
Biomedicines biomedicines	3.9	6.8	2013	21 Days	CHF 2600	Submit
Gastrointestinal Disorders gastrointestdisord	0.8	1.2	2019	22.2 Days	CHF 1400	Submit
Current Oncology curroncol	3.4	4.9	1994	22.8 Days	CHF 2200	Submit
Therapeutics therapeutics	-	-	2024	15.0 days *	CHF 1000	Submit

* Median value for all MDPI journals in the second half of 2025.

Topic Menu

Topic Editors

Hepatobiliary and Pancreatic Diseases: Novel Strategies of Diagnosis and Treatments—Second Edition

Topic Information

Keywords

Participating Journals

Published Papers (2 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI