EUVIMEDOpdag EUVIMED
Systematische Übersicht

Systematic Review: Use of Artificial Intelligence and Unmet Needs in Eosinophilic Oesophagitis

Systematische Übersicht: Einsatz von künstlicher Intelligenz und unerfüllte Bedürfnisse bei eosinophiler Ösophagitis

Ester Castagnaro, Enrico Felici, Roberta Spaccapelo, Mariangela Amoroso, Devis Moretti, Jean Pierre Saab, Annalisa Stassaldi, Andrea Tassone, Osvaldo Borrelli iD, Nicola De Bortoli iD, Giulio Del Corso, Edward Gaynor and 7 more

Alimentary Pharmacology & Therapeutics · 2025-07 · 62 (2) · 110-127

DOI: 10.1111/apt.70222 ↗

Auf einen Blick

Die systematische Übersicht fasst 28 Studien zu KI bei eosinophiler Ösophagitis zusammen. Für Diagnostik, Prognose, Präzisionsmedizin und Verlaufskontrolle zeigte KI Potenzial, viele Ansätze brauchen aber Validierung.

Fragestellung

Wie werden Anwendungen von KI bei eosinophiler Ösophagitis eingesetzt, und welche Lücken bestehen in der Literatur?

Methode

Systematische Übersichtsarbeit zu KI-Anwendungen in Diagnostik, Prognose, Präzisionsmedizin und Nachbeobachtung bei EoE; Suche in MEDLINE, Embase und Embase Classic bis 28. Februar 2025.

Ergebnisse

28 Studien; 18 zur Diagnostik. KI wurde für histologische Bildanalyse in 7 und endoskopische Bildanalyse in 3 Studien genutzt. Nicht-invasive Modelle zeigten hohe Genauigkeit; prognostisch wurden Nahrungsbolus-Impakt, Schweregrad und Fibrose adressiert.

Einschränkungen

Zu wenige Studien bei Kindern/Jugendlichen, zur Vorhersage des Therapieansprechens und zu besseren Studiendesigns.

Schlussfolgerung der Autor:innen

KI zeigte Potenzial zur Verbesserung des EoE-Managements, benötigt aber Validierung in größeren, unabhängigen und prospektiven Kohorten. Für die klinische Umsetzung müssen Bias, Datenschutz, Erklärbarkeit und Regulierung geklärt werden.

Kernaussagen

  • 28 Studien zu KI bei EoE
  • Hauptsächlich Diagnostik; auch Prognose, Präzisionsmedizin und Follow-up
  • Validierung und bessere Studiendesigns sind laut Autor:innen nötig

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Alimentary Pharmacology & Therapeutics, published online on 2025-06-05. Written by Ester Castagnaro and 18 co-authors. Institution: Department of Medicine and Surgery, University of Perugia, Perugia, Italy. Major MEDLINE topics: Artificial Intelligence, Eosinophilic Esophagitis. Cited 6 times so far (Crossref); 68 references.

Auf einen BlickAbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Artificial intelligence (AI) has been applied extensively to eosinophilic oesophagitis (EoE), but its clinical impact and comprehensiveness remain unclear.

Aims

To summarise the state of the art of applications of AI in EoE, identify gaps in the literature and disclose unmet needs.

Methods

We performed a systematic review of applications of AI in diagnosis, prognosis, precision medicine and follow‐up in EoE. We searched MEDLINE, Embase and Embase Classic (via Ovid) from inception until 28th February 2025. Clinical trials, cohort, case–control, cross‐sectional and case series studies were eligible for inclusion.

Results

We identified 28 studies on AI in EoE, with 18 focusing on diagnosis. AI was used for histology image analysis in digital pathology in seven and endoscopic image analysis in three studies. AI‐based non‐invasive diagnostic predictive models showed high accuracy in detecting EoE. As a prognostic tool, AI showed potential in predicting food impaction, histologic disease severity and fibrosis. AI was used in precision medicine for biomarker discovery, endotype prediction based on transcriptomics and treatment personalisation, as well as in disease monitoring and follow‐up. Unmet needs included insufficient studies on children/adolescents, prediction of treatment response and improvement of study designs.

Conclusions

Although AI showed promise at improving EoE management across various domains, most tools require validation on larger, independent and prospective cohorts. Several challenges, including algorithmic bias, data privacy, explainability and regulatory hurdles, need to be addressed for clinical implementation. Future studies should focus on developing non‐invasive diagnostic tools for younger populations, treatment response prediction and disease monitoring.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceEosinophilic EsophagitisHumansPrognosisPrecision Medicine

Author keywords

artificial intelligencedeep learningdiagnosiseosinophilic oesophagitismachine learningprecision medicineprognosis

Authors and institutions

  • Department of Medicine and Surgery, University of Perugia, Perugia, Italy.
  • Pediatric and Pediatric Emergency Unit, Children Hospital, AOU SS Antonio e Biagio e C. Arrigo, Alessandria, Italy.
  • Department of Medicine and Surgery and Centre of Functional Genomics, C.U.R.Ge.F, University of Perugia, Perugia, Italy.
  • Sanofi Italia, Milan, Italy.
  • Department of Gastroenterology, Great Ormond Street Hospital, London, UK.
  • Gastroenterology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, Pisa, Italy.

ORCID profiles: Osvaldo Borrelli, Nicola De Bortoli, Salvatore Oliva

Cite

APA

Castagnaro, E., Felici, E., Spaccapelo, R., Amoroso, M., Moretti, D., Saab, J. P., Stassaldi, A., Tassone, A., Borrelli, O., De Bortoli, N., Corso, G. D., Gaynor, E., Goh, L., Oliva, S., Rea, F., Renzo, S., Romano, C., Savarino, E. V., & Visaggi, P. (2025). Systematic Review: Use of Artificial Intelligence and Unmet Needs in Eosinophilic Oesophagitis. Alimentary Pharmacology & Therapeutics, 62(2), 110-127. https://doi.org/10.1111/apt.70222

Vancouver

Castagnaro E, Felici E, Spaccapelo R, Amoroso M, Moretti D, Saab JP, et al. Systematic Review: Use of Artificial Intelligence and Unmet Needs in Eosinophilic Oesophagitis. Alimentary Pharmacology & Therapeutics. 2025;62(2):110-127. doi:10.1111/apt.70222

BibTeX
@article{Castagnaro2025,
  author = {Castagnaro, Ester and Felici, Enrico and Spaccapelo, Roberta and Amoroso, Mariangela and Moretti, Devis and Saab, Jean Pierre and Stassaldi, Annalisa and Tassone, Andrea and Borrelli, Osvaldo and De Bortoli, Nicola and Corso, Giulio Del and Gaynor, Edward and Goh, Leanne and Oliva, Salvatore and Rea, Francesca and Renzo, Sara and Romano, Claudio and Savarino, Edoardo V and Visaggi, Pierfrancesco},
  title = {Systematic Review: Use of Artificial Intelligence and Unmet Needs in Eosinophilic Oesophagitis},
  journal = {Alimentary Pharmacology & Therapeutics},
  year = {2025},
  volume = {62},
  number = {2},
  pages = {110--127},
  doi = {10.1111/apt.70222}
}
Start for free →