AI-guided additive scoring model for differential diagnosis of primary liver cancer
Rattachement africain : de, ro, pl, us. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Background & Aims Within the Liver Imaging Reporting and Data System (LI-RADS), LI-RADS Malignant (LR-M) lesions remain diagnostically challenging: imaging indicates malignancy but often fails to distinguish hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (iCCA). Established serum-based tools such as GALAD are optimized for HCC but are not designed to resolve entity ambiguity within LR-M. In this pilot proof-of-concept study, we investigated whether small extracellular vesicle (EV) integrated with routine serological markers could resolve LR-M lesion situation. Methods A rare LR-M cohort (HCC = 25, iCCA=25) was evaluated using LASSO logistic regression and principal component analysis (PCA) to prioritize informative biomarkers. Hybrid models combined CD9 + CD133/2 + and CD81 + CD133/2 + EVs with alkaline phosphatase, CRP, CA19-9, and optional AFP. Models were internally validated using an 80:20 train–test split and assessed with bootstrap and Monte-Carlo perturbation (±5–20%). Results Individual markers demonstrated limited discrimination (AUROC ≤ 0.82). Hybrid logistic regression models showed moderate internal discrimination (AUROC 0.86 with AFP; 0.91 without AFP). Translation into additive scoring systems using ROC–Youden–derived cut-offs yielded high internal AUROC estimates (e.g., 0.95–0.96), though these remain internally validated. A simplified five-point PRISM score retained comparable discriminatory performance (AUROC ∼0.91). In exploratory survival analysis among iCCA patients (n = 25), those with above-median CD9 + CD133/2 + EV levels (n = 13) had shorter overall survival (median 91 vs. 389 days; HR 2.80, 95% CI 1.16–6.74; p = 0.005). Conclusions Integrated EV and serological profiling may enable minimally invasive differentiation between HCC and iCCA within LR-M lesions. By transforming ML–guided model discovery into a clinically interpretable paper-and-pencil additive score, we illustrate a translational pathway from computational discovery to practical application. Impact and Implications This study provides a scientific rationale for integrating small extracellular vesicle (EV) phenotyping with conventional serum biomarkers to improve minimally invasive differentiation between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (iCCA) in LR-M lesions. By translating a machine learning (ML)_derived hybrid model into a simple additive scoring system, we demonstrate how ML can yield clinically interpretable tools that bridge computational discovery and bedside application. The findings are particularly relevant for hepatologists, oncologists, and radiologists managing patients in whom imaging remains indeterminate and biopsy carries procedural risk. The five-point model can be applied using routine laboratory values, providing a paper-and-pencil diagnostic aid that requires no specialized software or hardware. While external multicenter validation is necessary given the cohort size, this approach illustrates how transparent, interpretable machine learning can support precision diagnostics in primary liver cancer.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- AI-guided additive scoring model for differential diagnosis of primary liver cancer
- Date Crossref
- 01/06/2026
- Éditeur
- Elsevier BV
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
University of Bonn pays non établi dans la noticeUniversité ou école supérieure
-
University Hospital Bonn pays non établi dans la noticeÉtablissement de santé
-
Iuliu Hațieganu University of Medicine and Pharmacy Octavian Fodor Institute for Gastroenterology and Hepatology pays non établi dans la noticeUniversité ou école supérieure
-
Babeș-Bolyai University pays non établi dans la noticeUniversité ou école supérieure
-
Bundeswehrzentralkrankenhaus Koblenz pays non établi dans la noticeÉtablissement de santé
-
University of Duisburg-Essen pays non établi dans la noticeUniversité ou école supérieure
-
Medical University of Warsaw pays non établi dans la noticeUniversité ou école supérieure
-
Beth Israel Deaconess Medical Center Department of Anesthesia pays non établi dans la noticeÉtablissement de santé
-
University Hospital of the Rheinische Friedrich-Wilhelms-University Department of Internal Medicine I pays non établi dans la noticeUniversité ou école supérieure
-
German Armed Forces Central Hospital Koblenz Department of General- Visceral- and Thoracic Surgery pays non établi dans la noticeÉtablissement de santé
-
University Hospital of Bonn Department of Integrated Oncology pays non établi dans la noticeUniversité ou école supérieure
-
Medical Faculty Department of Gastroenterology pays non établi dans la noticeUniversité ou école supérieure
University of Bonn, University Hospital Bonn et Octavian Fodor Institute for Gastroenterology and Hepatology — Iuliu Hațieganu University of Medicine and Pharmacy, avec 9 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.