Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta‐Analysis
Künstliche-Intelligenz-gestützte Kapselendoskopie versus konventionelle Kapselendoskopie zum Nachweis von Läsionen des Dünndarms: systematische Übersicht und Metaanalyse
Journal of Gastroenterology and Hepatology · 2025-05 · 40 (5) · 1105-1118
DOI: 10.1111/jgh.16931 ↗Auf einen Blick
14 Studien verglichen KI-gestützte mit konventioneller Kapselendoskopie. KI-gestützte CE zeigte höhere Sensitivität und negative prädiktive Werte, aber niedrigere Spezifität.
Fragestellung
Wie unterscheiden sich diagnostische Genauigkeit, Spezifität, Sensitivität sowie negative und positive prädiktive Werte von KI-gestützter im Vergleich zu konventioneller Kapselendoskopie bei Dünndarmläsionen?
Methode
Systematische Übersicht und Metaanalyse; Suche in PubMed, SCOPUS und EMBASE bis 24. November 2024; eingeschlossen wurden Originalarbeiten, Übersichten, Metaanalysen und Fallserien; Analyse mit Comprehensive Meta-Analysis v4.0.
Ergebnisse
14 Studien. Pooled Accuracy: 0,966 (95 %-KI 0,925–0,988) vs. 0,9185 (95 %-KI 0,9138–0,9233); Sensitivität: 0,860 (95 %-KI 0,786–0,934) vs. 0,9239 (95 %-KI 0,8648–0,9870); Spezifität: 0,998 (95 %-KI 0,996–0,999) vs. 0,5367 (95 %-KI 0,5244–0,5492).
Schlussfolgerung der Autor:innen
Die Autor:innen berichten, dass KI-gestützte CE eine höhere diagnostische Genauigkeit, Sensitivität und positive prädiktive Werte bei niedrigerer gepoolter Spezifität als konventionelle CE zeigt.
Kernaussagen
- KI-gestützte CE: höhere Sensitivität als konventionelle CE
- KI-gestützte CE: niedrigere Spezifität als konventionelle CE
- 14 Studien wurden in die Metaanalyse eingeschlossen
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 Gastroenterology and Hepatology, online erschienen am 13.03.2025. Verfasst von Arkadeep Dhali und 16 weiteren Autor:innen. Beteiligte Einrichtung: Academic Unit of Gastroenterology, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK. Hauptthemen laut MEDLINE: Capsule Endoscopy, Intestine, Small, Artificial Intelligence, Intestinal Diseases. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Capsule endoscopy (CE) is a valuable tool used in the diagnosis of small intestinal lesions. The study aims to systematically review the literature and provide a meta‐analysis of the diagnostic accuracy, specificity, sensitivity, and negative and positive predictive values of AI‐assisted CE in the diagnosis of small bowel lesions in comparison to CE .
Methods
Literature searches were performed through PubMed, SCOPUS, and EMBASE to identify studies eligible for inclusion. All publications up to 24 November 2024 were included. Original articles (including observational studies and randomized control trials), systematic reviews, meta‐analyses, and case series reporting outcomes on AI‐assisted CE in the diagnosis of small bowel lesions were included. The extracted data were pooled, and a meta‐analysis was performed for the appropriate variables, considering the clinical and methodological heterogeneity among the included studies. Comprehensive Meta‐Analysis v4.0 (Biostat Inc.) was used for the analysis of the data.
Results
A total of 14 studies were included in the present study. The mean age of participants across the studies was 54.3 years (SD 17.7), with 55.4% men and 44.6% women. The pooled accuracy for conventional CE was 0.966 (95% CI: 0.925–0.988), whereas for AI‐assisted CE, it was 0.9185 (95% CI: 0.9138–0.9233). Conventional CE exhibited a pooled sensitivity of 0.860 (95% CI: 0.786–0.934) compared with AI‐assisted CE at 0.9239 (95% CI: 0.8648–0.9870). The positive predictive value for conventional CE was 0.982 (95% CI: 0.976–0.987), whereas AI‐assisted CE had a PPV of 0.8928 (95% CI: 0.7554–0.999). The pooled specificity for conventional CE was 0.998 (95% CI: 0.996–0.999) compared with 0.5367 (95% CI: 0.5244–0.5492) for AI‐assisted CE . Negative predictive values were higher in AI‐assisted CE at 0.9425 (95% CI: 0.9389–0.9462) versus 0.760 (95% CI: 0.577–0.943) for conventional CE .
Conclusion
AI‐assisted CE displays superior diagnostic accuracy, sensitivity, and positive predictive values albeit the lower pooled specificity in comparison with conventional CE . Its use would ensure accurate detection of small bowel lesions and further enhance their management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Academic Unit of Gastroenterology, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK.
- School of Medicine and Population Health, University of Sheffield, Sheffield, UK.
- Faculty of Health Sciences, University of Nairobi, Nairobi, Kenya.
- Institute of Post Graduate Medical Education and Research, Kolkata, India.
- University of Massachusetts Chan Medical School, Worcester, Massachusetts, USA.
- College of Medicine and Sagore Dutta Hospital, Kolkata, India.
ORCID-Profile: Arkadeep Dhali, Rick Maity, Hareesha Rishab Bharadwaj
Zitieren
APA
Dhali, A., Kipkorir, V., Maity, R., Srichawla, B. S., Biswas, J., Rathna, R. B., Bharadwaj, H. R., Ongidi, I., Chaudhry, T., Morara, G., Waithaka, M., Rugut, C., Lemashon, M., Cheruiyot, I., Ojuka, D., Ray, S., & Dhali, G. K. (2025). Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta‐Analysis. Journal of Gastroenterology and Hepatology, 40(5), 1105-1118. https://doi.org/10.1111/jgh.16931
Vancouver
Dhali A, Kipkorir V, Maity R, Srichawla BS, Biswas J, Rathna RB, et al. Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta‐Analysis. Journal of Gastroenterology and Hepatology. 2025;40(5):1105-1118. doi:10.1111/jgh.16931
BibTeX
@article{Dhali2025,
author = {Dhali, Arkadeep and Kipkorir, Vincent and Maity, Rick and Srichawla, Bahadar S and Biswas, Jyotirmoy and Rathna, Roger B and Bharadwaj, Hareesha Rishab and Ongidi, Ibsen and Chaudhry, Talha and Morara, Gisore and Waithaka, Maryann and Rugut, Clinton and Lemashon, Miheso and Cheruiyot, Isaac and Ojuka, Daniel and Ray, Sukanta and Dhali, Gopal Krishna},
title = {Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta‐Analysis},
journal = {Journal of Gastroenterology and Hepatology},
year = {2025},
volume = {40},
number = {5},
pages = {1105--1118},
doi = {10.1111/jgh.16931}
}
EUVIMED