EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access · CC BY 4.0

Artificial intelligence for monitoring hand hygiene compliance in healthcare settings: A scoping review

Künstliche Intelligenz zur Überwachung der Händehygiene-Compliance im Gesundheitswesen: Scoping Review

Xinran Lin, Yu Lv, Qian Xiang, Minhong Cai, Pingping Wang iD

PLOS One · 21.04.2026 · 21 (4) · e0347683

DOI: 10.1371/journal.pone.0347683 ↗

Auf einen Blick

Die Übersichtsarbeit zeigt: KI-gestützte Händehygiene-Überwachung ist technisch machbar und kann objektiver sowie skalierbarer sein. Die Evidenz ist jedoch überwiegend aus kleinen technischen Validierungen abgeleitet.

Fragestellung

Welche Evidenz, technischen Ansätze, Leistungsmerkmale und Implementierungsprobleme gibt es für KI zur Überwachung der Händehygiene-Compliance im Gesundheitswesen?

Methode

Scoping Review nach JBI und PRISMA-ScR; Suche in 5 Datenbanken von Januar 2000 bis September 2025 plus Grauliteratur und Rückwärtszitation.

Ergebnisse

45 Studien (2007–2025) eingeschlossen. Hauptansätze: Computer Vision 53,3 %, Wearable-Sensoren 24,4 %, IoT-Systeme 13,3 %, Radar/Funk 8,9 %. Accuracy bis 95 % in ICU-Modellen, 56 % in generalisierbaren Modellen.

Einschränkungen

Überwiegend kleine technische Validierungen; kein formales Fairness-Assessment; klinische Workflows und Kosteneffektivität selten bewertet.

Schlussfolgerung der Autor:innen

KI-basierte Händehygiene-Überwachung ist vielversprechend für eine objektivere und skalierbare Surveillance, bleibt laut Autor:innen aber in einer weitgehend prätranslationalen Phase.

Kernaussagen

  • Computer Vision war der häufigste technische Ansatz (53,3 %)
  • Accuracy: 95 % in ICU-Modellen, 56 % in generalisierbaren Modellen
  • Es fehlen Fairness-Analysen sowie Daten zu Workflow und Kosten

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

Kurz gefasst

Scoping Review in der Zeitschrift PLOS One, online erschienen am 21.04.2026. Verfasst von Xinran Lin und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, University of Electronic Science and Technology of China, Chengdu, Sichuan, China. Hauptthemen laut MEDLINE: Artificial Intelligence, Hand Hygiene, Guideline Adherence, Cross Infection. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hand hygiene is a fundamental measure for preventing healthcare-associated infections, yet traditional monitoring methods are significantly limited by the Hawthorne effect, high resource demands, and an inability to assess procedural quality. Artificial intelligence (AI) technology has emerged as a transformative, automated, and objective approach to address these long-standing challenges.

Objective

This scoping review sought to systematically map the existing evidence, technical pathways, performance metrics, and implementation challenges of AI for monitoring hand hygiene compliance in healthcare settings.

Methods

Following the Joanna Briggs Institute (JBI) methodological framework and PRISMA-ScR guidelines, we searched five major databases (PubMed, Scopus, Embase, Web of Science, and IEEE Xplore) for articles published between January 2000 and September 2025, supplemented by grey literature searching and backward citation tracking. Two reviewers independently screened records, assessed full-text reports for eligibility, and extracted data, which were synthesized using descriptive statistics and thematic analysis.

Results

Of 800 records identified through database and supplementary searches, 45 studies (2007–2025) were included. The primary technical pathways identified were computer vision (53.3%), wearable sensors (24.4%), Internet of Things-integrated systems (13.3%), and radar/radio frequency-based systems (8.9%). While computer vision achieved high accuracy (95%) in setting-specific ICU models, performance dropped to 56% in generalizable models. Wearable systems demonstrated portability but showed 5%–10% lower specificity than vision-based approaches. Most evidence is derived from small-scale technical validations, with a significant lack of formal fairness analysis and evaluation of clinical workflows or cost-effectiveness.

Conclusion

AI-based hand hygiene monitoring shows promise for supporting more objective and scalable hand hygiene surveillance in healthcare settings. However, the field remains at a largely pre-translational stage. Future research should shift from technical feasibility toward implementation science, focusing on establishing standardized motion databases, evaluating ethical governance (e.g., privacy and automation bias), and conducting pragmatic trials to demonstrate sustained clinical benefit and organizational sustainability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceHand HygieneGuideline AdherenceCross InfectionHumans

Autor:innen und Institutionen

  • School of Medicine, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
  • Public Health Department, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
  • Healthcare-Associated Infection Control Center, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.

ORCID-Profile: Pingping Wang

Zitieren

APA

Lin, X., Lv, Y., Xiang, Q., Cai, M., & Wang, P. (2026). Artificial intelligence for monitoring hand hygiene compliance in healthcare settings: A scoping review. PLOS One, 21(4), e0347683. https://doi.org/10.1371/journal.pone.0347683

Vancouver

Lin X, Lv Y, Xiang Q, Cai M, Wang P. Artificial intelligence for monitoring hand hygiene compliance in healthcare settings: A scoping review. PLOS One. 2026;21(4):e0347683. doi:10.1371/journal.pone.0347683

BibTeX
@article{Lin2026,
  author = {Lin, Xinran and Lv, Yu and Xiang, Qian and Cai, Minhong and Wang, Pingping},
  title = {Artificial intelligence for monitoring hand hygiene compliance in healthcare settings: A scoping review},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0347683},
  doi = {10.1371/journal.pone.0347683}
}
Kostenlos starten →