Artificial Intelligence in Lymphoma Histopathology: Systematic Review
Künstliche Intelligenz in der Lymphom-Histopathologie: systematische Übersichtsarbeit
Journal of Medical Internet Research · 14.02.2025 · 27 · e62851
DOI: 10.2196/62851 ↗Auf einen Blick
Die Übersichtsarbeit zu KI-Modellen in der Lymphom-Histopathologie fand bei 41 Artikeln durchgehend ein hohes oder unklares Bias-Risiko. Interne Validierung zeigte AUC-Werte von 0,75 bis 0,99.
Fragestellung
Wie hoch sind Bias-Risiko und klinische Nutzbarkeit veröffentlichter KI-Modelle für Diagnose oder Prognose in der Lymphom-Histopathologie?
Methode
Systematische Übersichtsarbeit; Suche in PubMed, Cochrane Library und Web of Science bis 30. August 2024; Bewertung mit PROBAST; PRISMA 2020 und PROSPERO-registriert.
Ergebnisse
3565 Treffer, 41 eingeschlossene Artikel und 41 KI-Modelle. Davon 17 diagnostische, 10 prognostische, 2 zur Erkennung ektoper Genexpression und 12 weitere Diagnosemodelle; alle Studien mit hohem oder unklarem Bias-Risiko.
Einschränkungen
Alle Studien hatten ein hohes oder unklares Bias-Risiko, vor allem wegen limitierter Analyse und unvollständiger Rekrutierungsangaben.
Schlussfolgerung der Autor:innen
Methodisch wiesen alle Modelle Bias auf. Für bessere Genauigkeit und klinische Translation nennen die Autor:innen umfassendere Berichte, diversere Datensätze, Transparenz, Validierung und regulatorische Standards.
Kernaussagen
- 41 eingeschlossene Artikel; alle Modelle mit hohem oder unklarem Bias-Risiko
- Interne Validierung: AUC 0,75 bis 0,99; Accuracy 68,3 % bis 100 %
- Externe Validierung: AUC 0,93 bis 0,99
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 14.02.2025. Verfasst von Yao Fu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Sichuan Tianfu New Area People's Hospital, Chengdu, China. Hauptthemen laut MEDLINE: Artificial Intelligence, Lymphoma. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Artificial intelligence (AI) shows considerable promise in the areas of lymphoma diagnosis, prognosis, and gene prediction. However, a comprehensive assessment of potential biases and the clinical utility of AI models is still needed.
Objective
Our goal was to evaluate the biases of published studies using AI models for lymphoma histopathology and assess the clinical utility of comprehensive AI models for diagnosis or prognosis.
Methods
This study adhered to the Systematic Review Reporting Standards. A comprehensive literature search was conducted across PubMed, Cochrane Library, and Web of Science from their inception until August 30, 2024. The search criteria included the use of AI for prognosis involving human lymphoma tissue pathology images, diagnosis, gene mutation prediction, etc. The risk of bias was evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Information for each AI model was systematically tabulated, and summary statistics were reported. The study is registered with PROSPERO (CRD42024537394) and follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 reporting guidelines.
Results
The search identified 3565 records, with 41 articles ultimately meeting the inclusion criteria. A total of 41 AI models were included in the analysis, comprising 17 diagnostic models, 10 prognostic models, 2 models for detecting ectopic gene expression, and 12 additional models related to diagnosis. All studies exhibited a high or unclear risk of bias, primarily due to limited analysis and incomplete reporting of participant recruitment. Most high-risk models (10/41) predominantly assigned high-risk classifications to participants. Almost all the articles presented an unclear risk of bias in at least one domain, with the most frequent being participant selection (16/41) and statistical analysis (37/41). The primary reasons for this were insufficient analysis of participant recruitment and a lack of interpretability in outcome analyses. In the diagnostic models, the most frequently studied lymphoma subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and mantle cell lymphoma, while in the prognostic models, the most common subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and Hodgkin lymphoma. In the internal validation results of all models, the area under the receiver operating characteristic curve (AUC) ranged from 0.75 to 0.99 and accuracy ranged from 68.3% to 100%. In models with external validation results, the AUC ranged from 0.93 to 0.99.
Conclusions
From a methodological perspective, all models exhibited biases. The enhancement of the accuracy of AI models and the acceleration of their clinical translation hinge on several critical aspects. These include the comprehensive reporting of data sources, the diversity of datasets, the study design, the transparency and interpretability of AI models, the use of cross-validation and external validation, and adherence to regulatory guidance and standardized processes in the field of medical AI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Sichuan Tianfu New Area People's Hospital, Chengdu, China.
- Department of Pathology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, China.
- Wonders Information Co., Ltd, Shanghai, China.
- Phase I Clinical Trial Unit, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, China.
ORCID-Profile: Yao Fu, Zongyao Huang, Xudong Deng, Linna Xu, Yang Liu, Mingxing Zhang, Jinyi Liu, Bin Huang
Zitieren
APA
Fu, Y., Huang, Z., Deng, X., Xu, L., Liu, Y., Zhang, M., Liu, J., & Huang, B. (2025). Artificial Intelligence in Lymphoma Histopathology: Systematic Review. Journal of Medical Internet Research, 27, e62851. https://doi.org/10.2196/62851
Vancouver
Fu Y, Huang Z, Deng X, Xu L, Liu Y, Zhang M, et al. Artificial Intelligence in Lymphoma Histopathology: Systematic Review. Journal of Medical Internet Research. 2025;27:e62851. doi:10.2196/62851
BibTeX
@article{Fu2025,
author = {Fu, Yao and Huang, Zongyao and Deng, Xudong and Xu, Linna and Liu, Yang and Zhang, Mingxing and Liu, Jinyi and Huang, Bin},
title = {Artificial Intelligence in Lymphoma Histopathology: Systematic Review},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {27},
pages = {e62851},
doi = {10.2196/62851}
}
EUVIMED