EUVIMEDDescobrir EUVIMED
Systematische ÜbersichtOpen access

Artificial Intelligence Platform Architecture for Hospital Systems: Systematic Review

Architektur einer KI-Plattform für Krankenhaussysteme: systematische Übersichtsarbeit

Musitapa Maimaitiaili, Yiershatijiang Jiamaliding, Guangle Dai, Hui Xiao, Warisijiang Kuerbanjiang, Yuexiong Yi

Journal of Medical Internet Research · 2025-12-17 · 27 · e79788-e79788

DOI: 10.2196/79788 ↗

Auf einen Blick

Die Übersichtsarbeit ordnet 29 Studien in eine 5-Schichten-Architektur für Krankenhaus-KI ein. Die höchste Reife zeigten Anwendungs- und Datenschicht, die niedrigste die Sicherheits- und Compliance-Schicht.

Fragestellung

Welche Evidenz lässt sich auf eine 5-Schichten-Architektur für Krankenhaus-KI-Plattformen abbilden, und wie gut ist deren Anwendbarkeit?

Methode

Systematische Literaturrecherche in Web of Science, Embase, PubMed und Scopus bis Mai 2025; 29 empirische Studien wurden anhand einer 5-Schichten-Reife-Skala gemappt.

Ergebnisse

29 Studien aus 11 Ländern. Höchste Reife: Anwendung (Mittelwert 3,17; SD 0,85) und Daten (3,00; SD 0,76). Niedrigste Reife: Sicherheit/Compliance (1,69; SD 1,89).

Einschränkungen

Nicht-englische und Grauliteratur wurden ausgeschlossen; die ordinale Reifebewertung kann Kontextkomplexität vereinfachen.

Schlussfolgerung der Autor:innen

Die Synthese bestätigt eine 5-Schichten-Architektur für Krankenhaus-KI auf Basis theoretischer und empirischer Evidenz. Für nachhaltige Umsetzung sind mehr Investitionen in Infrastruktur, Datengovernance und Compliance nötig.

Kernaussagen

  • 29 Studien wurden der 5-Schichten-Architektur zugeordnet.
  • Anwendungs- und Datenschicht zeigten die höchste Reife.
  • Sicherheit und Compliance waren am wenigsten ausgereift.

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 Journal of Medical Internet Research, published online on 2025-12-17. Written by Musitapa Maimaitiaili and 5 co-authors. Institution: Department of Gynecology, Zhongnan Hospital of Wuhan University, #169, Donghu Road, Wuchang District, Wuhan, Hubei, 430071, China, 86 15671669885, 86…. Major MEDLINE topics: Artificial Intelligence, Hospital Information Systems. Cited 19 times so far (Crossref); 69 references. The full text is freely available in PubMed Central.

Auf einen BlickResumoSubjectsDados bibliográficosCiteRelated studies

Abstract (original language)

Background

The construction of artificial intelligence (AI) platforms in hospitals is the backbone of the revolution in health care. While traditional hospital information systems have facilitated digitalization, they are still limited by data silos, fragmented workflows, and insufficient clinical intelligence that impede organizations from realizing the promise of data-led decision-making.

Objective

This study aimed to derive a hospital-specific 5-layer architecture (infrastructure, data, algorithm, application, and security and compliance) and to systematically review the evidence mapped onto the 5-layer framework to assess its applicability.

Methods

A systematic literature search was performed in Web of Science, Embase, PubMed, and Scopus from inception to May 2025. The review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were screened and selected for full-text review by two independent reviewers. We included peer-reviewed empirical studies describing hospital-based AI implementations across clinical domains. Reviews, commentaries, and purely technical bench studies without hospital context and non-English literature were excluded. Quality assessment of the identified papers was conducted using the Critical Appraisal Skills Programme tool. Using a 0 to 5 point ordinal maturity scale of 5 layers, we conducted a structured mapping with quantitative mapping, weighted co-occurrence analysis, weighted Jaccard similarity, and thematic synthesis with examples.

Results

In total, 29 studies met the eligibility criteria and included work specifically in emergency, radiology, routine imaging, chronic disease, and multihospital platform work, conducted in 11 countries. On average, the application (mean 3.17, SD 0.85) and data (mean 3.00, SD 0.76) layers demonstrated the highest maturity, followed by algorithm (mean 2.79, SD 0.77) and infrastructure (mean 2.79, SD 1.70). The security and compliance layer showed the lowest and most variable maturity (mean 1.69, SD 1.89). Weighted co-occurrence and Jaccard analyses revealed strong interconnections among data, algorithm, and application (Jaccard=0.80‐0.89), forming a technical core, whereas security and compliance exhibited weak alignment (0.43‐0.46).

Conclusions

Our review excluded non-English and gray literature, which may limit comprehensiveness. The ordinal maturity scoring may still simplify the contextual complexity of hospital AI implementations. Our synthesis validates a 5-layer hospital AI platform architecture, grounded in both theoretical frameworks and empirical evidence. The findings highlight that while clinical feasibility is achievable, sustainable hospital-wide AI requires stronger investment in infrastructure, data governance, and compliance.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceHospital Information SystemsHumansAlgorithms

Author keywords

5-layer architectureAI implementation frameworkartificial intelligencehealth care digitizationhospital AI platform

Authors and institutions

  • Department of Gynecology, Zhongnan Hospital of Wuhan University, #169, Donghu Road, Wuchang District, Wuhan, Hubei, 430071, China, 86 15671669885, 86 02767813142.
  • The Second Clinical Hospital, Wuhan University, Wuhan, China.
  • Information Center, Zhongnan Hospital of Wuhan University, Wuhan, China.

Cite

APA

Maimaitiaili, M., Jiamaliding, Y., Dai, G., Xiao, H., Kuerbanjiang, W., & Yi, Y. (2025). Artificial Intelligence Platform Architecture for Hospital Systems: Systematic Review. Journal of Medical Internet Research, 27, e79788-e79788. https://doi.org/10.2196/79788

Vancouver

Maimaitiaili M, Jiamaliding Y, Dai G, Xiao H, Kuerbanjiang W, Yi Y. Artificial Intelligence Platform Architecture for Hospital Systems: Systematic Review. Journal of Medical Internet Research. 2025;27:e79788-e79788. doi:10.2196/79788

BibTeX
@article{Maimaitiaili2025,
  author = {Maimaitiaili, Musitapa and Jiamaliding, Yiershatijiang and Dai, Guangle and Xiao, Hui and Kuerbanjiang, Warisijiang and Yi, Yuexiong},
  title = {Artificial Intelligence Platform Architecture for Hospital Systems: Systematic Review},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e79788--e79788},
  doi = {10.2196/79788}
}
Start for free →