EUVIMEDEUVIMED entdecken
Systematische ÜbersichtUmbrella ReviewOpen Access · CC BY 4.0

Artificial intelligence support for diagnosis of neurodevelopmental disorders during childhood: an umbrella review

Künstliche Intelligenz zur Diagnostik neuroentwicklungsbezogener Störungen im Kindesalter: Umbrella Review

Alejandro Alberca-González, Eduardo Fernández-Jiménez

Frontiers in Psychiatry · 18.03.2026 · 17

DOI: 10.3389/fpsyt.2026.1697185 ↗

Auf einen Blick

Das Umbrella Review fasst Evidenz zu KI bei der Diagnose neuroentwicklungsbezogener Störungen im Kindesalter zusammen. Die diagnostische Genauigkeit reichte von 66 % bis 99 %.

Fragestellung

Welche Evidenz liegt aus systematischen Reviews und Metaanalysen zum Einsatz von KI für die Diagnose neuroentwicklungsbezogener Störungen im Kindesalter vor?

Methode

Umbrella Review systematischer Reviews und Metaanalysen; Suche in Web of Science, PsycINFO und PubMed von Januar 2015 bis August 2025.

Ergebnisse

64 Studien wurden eingeschlossen. Am häufigsten wurden ASD (n = 31) und ADHD (n = 14) untersucht. KI-Modelle erreichten Genauigkeiten von 66 % bis 99 %; 80 % der Studien waren nach AMSTAR-2 kritisch niedrig.

Einschränkungen

Meist kritisch niedrige methodische Qualität; fehlende externe Validierung, fehlende Standardisierung und Berichtsinconsistenzen.

Schlussfolgerung der Autor:innen

KI zeigt vielversprechendes Potenzial zur Unterstützung der Biomarkeridentifikation und Diagnose neuroentwicklungsbezogener Störungen.

Kernaussagen

  • 64 Studien im Umbrella Review
  • ASD und ADHD am häufigsten untersucht
  • Genauigkeit 66 % bis 99 %, aber überwiegend kritische Qualität

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 Frontiers in Psychiatry, online erschienen am 18.03.2026. Verfasst von Alejandro Alberca-González und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Law, Education and Humanities, Universidad Europea de Madrid, Madrid, Spain. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 119 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The growing demand for earlier diagnosis of neurodevelopmental disorders has boosted critical assessment of artificial intelligence (AI) as a complementary tool for clinical decision-making.

Methods

This umbrella review aimed to synthesize the available evidence from systematic reviews and meta-analyses on the use of AI to diagnose during childhood any neurodevelopmental disorder [autism spectrum disorder (ASD), attention-deficit/hyperactivity disorder (ADHD), intellectual disability, communication disorders, developmental coordination disorder, and specific learning disorders]. A systematic search was conducted on the Web of Science, PsycINFO, and PubMed, covering studies published from January 2015 to August 2025 and available in any language.

Results

Of the 148 records identified, 64 studies were included based on the predefined inclusion and exclusion criteria. ASD ( n = 31) and ADHD ( n = 14) were the most frequently examined conditions in which AI was applied for diagnostic purposes. To a lesser extent, it was applied to specific learning disorders ( n = 5) and other developmental disorders (intellectual disability and communication disorders, jointly addressed along with other diagnoses, n = 9). The most employed AI models were machine learning (support vector machines and artificial neural networks) and particularly deep learning (such as convolutional neural networks). These models were applied to diverse data modalities, such as neuroimaging ( n = 59 studies), electrophysiological ( n = 19), clinical/sociodemographic ( n = 15), and motion/sensor-based data ( n = 11). Overall, these AI models achieved diagnostic accuracy levels ranging from 66% (based on head/facial/eye movements) to 99% (based on neuroimaging, voice, motion, and sensors). However, the methodological quality of most studies was rated as critically low according to the AMSTAR-2 criteria (80%), while only 5% of studies achieved high quality levels (focused on ASD and ADHD).

Conclusion

AI shows promising potential for supporting biomarker identification and diagnosis of neurodevelopmental disorders. However, future clinical implementation still requires methodologically rigorous research addressing current limitations: insufficient external validation, lack of standardization in data collection and model development, as well as reporting inconsistencies. Systematic Review Registration https://www.crd.york.ac.uk/PROSPERO/view/CRD420251110825 , identifier CRD420251110825.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencechildhooddiagnosisneurodevelopmental disordersumbrella review

Autor:innen und Institutionen

  • Faculty of Law, Education and Humanities, Universidad Europea de Madrid, Madrid, Spain.
  • Department of Child and Adolescent Psychiatry, Clinical Psychology and Mental Health, La Paz University Hospital, Madrid, Spain.
  • Hospital La Paz Institute for Health Research (IdiPAZ), Madrid, Spain.

Zitieren

APA

Alberca-González, A., & Fernández-Jiménez, E. (2026). Artificial intelligence support for diagnosis of neurodevelopmental disorders during childhood: an umbrella review. Frontiers in Psychiatry, 17. https://doi.org/10.3389/fpsyt.2026.1697185

Vancouver

Alberca-González A, Fernández-Jiménez E. Artificial intelligence support for diagnosis of neurodevelopmental disorders during childhood: an umbrella review. Frontiers in Psychiatry. 2026;17. doi:10.3389/fpsyt.2026.1697185

BibTeX
@article{AlbercaGonzlez2026,
  author = {Alberca-González, Alejandro and Fernández-Jiménez, Eduardo},
  title = {Artificial intelligence support for diagnosis of neurodevelopmental disorders during childhood: an umbrella review},
  journal = {Frontiers in Psychiatry},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpsyt.2026.1697185}
}
Kostenlos starten →