EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Health Security inequalities in Non-EU European Countries: A Cross-National Comparative Assessment Using an Integrated MCDM-Machine Learning Approach

Mijahed Nasser Aljober, Adel A Nasser iD, Abed Saif Ahmed Alghawli iD, Amani A K Elsayed

F1000Research · 2025

DOI: 10.12688/f1000research.163662.2 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift F1000Research, 2025. Verfasst von Mijahed Nasser Aljober und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, Modern Specialized University, Sana'a, Yemen. Hauptthemen laut MEDLINE: Machine Learning, Global Health, Health Status Disparities. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deanship of Scientific Research, Prince Sattam bin Abdulaziz University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

In an increasingly interconnected world, the effectiveness of health security (HeS) is pivotal in shaping informed health policies and enhancing public health outcomes. This study aims to analyses HeS in 27 non-EU European countries, identifying key priorities and trends, benchmarking against African and Eastern Mediterranean regions (EMR), and ranking and clustering health security performance to inform targeted interventions.

Methods

Utilizing 2019, 2021, and aggregated 2017–2021 data from six Global Health Security Index indicators, this study applied an integrated Entropy-CoCoSo-K-means framework. The Entropy method was employed to identify health security (HeS) priorities and trends in Non-EU countries, enabling cross-regional comparisons with African and EMR regions to highlight priority shifts and disparities. The Entropy-CoCoSo (Combined Compromise Solution) model generated dynamic rankings, while K-means clustering categorized countries into five risk clusters (high to dangerous). This integration facilitated cross-national dynamic rankings and cluster analyses, informing targeted interventions across Non-EU countries.

Results

Entropy analysis reveals that detection and reporting emerged as the most critical indicator (weight: 0.388), reflecting disparities in surveillance. The risk environment remains minimally influential (0.067), highlighting consistent vulnerabilities to external threats. Compliance with norms shows a sharp rise (0.091 → 0.123), indicating emerging regulatory gaps or uneven adherence to health standards post-2019. Cross-regional comparisons highlighted a focus on detection and reporting in non-EU countries versus an emphasis on prevention in Africa and healthcare infrastructure prioritization in the EMR. Ranking and clustering revealed stark disparities: Armenia, Norway, and the UK consistently ranked “High,” In contrast, Andorra, Monaco, San Marino, and Tajikistan (Cluster 5: “Dangerous”) exhibited systemic weaknesses.

Conclusion

This study underscores the need for tailored policies to address non-EU Europe’s evolving HeS challenges. Harmonizing surveillance systems, scaling preventive measures, and bridging compliance gaps are critical. Regional collaboration and resource reallocation to low-performing nations are essential to mitigate disparities.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningGlobal HealthHealth Status DisparitiesHumansEuropeAfricaEntropy

Stichwörter der Autor:innen

CoCoSoEntropy weighting methodK-meansMCDMNon-EU European Countriesclusteringhealth security

Autor:innen und Institutionen

  • Department of Artificial Intelligence, Modern Specialized University, Sana'a, Yemen.
  • Department of Information Systems and Computer Science, Sa'adah University, Sa'adah, Yemen.
  • Department of Computer Science, College of Sciences and Humanities, Prince Sattam bin Abdulaziz University, Al Kharj, Riyadh Province, 16700, Saudi Arabia.

ORCID-Profile: Adel A Nasser, Abed Saif Ahmed Alghawli

Förderung

  • Deanship of Scientific Research, Prince Sattam bin Abdulaziz University

Zitieren

APA

Aljober, M. N., Nasser, A. A., Alghawli, A. S. A., & Elsayed, A. A. K. (2025). Health Security inequalities in Non-EU European Countries: A Cross-National Comparative Assessment Using an Integrated MCDM-Machine Learning Approach. F1000Research. https://doi.org/10.12688/f1000research.163662.2

Vancouver

Aljober MN, Nasser AA, Alghawli ASA, Elsayed AAK. Health Security inequalities in Non-EU European Countries: A Cross-National Comparative Assessment Using an Integrated MCDM-Machine Learning Approach. F1000Research. 2025. doi:10.12688/f1000research.163662.2

BibTeX
@article{Aljober2025,
  author = {Aljober, Mijahed Nasser and Nasser, Adel A and Alghawli, Abed Saif Ahmed and Elsayed, Amani A K},
  title = {Health Security inequalities in Non-EU European Countries: A Cross-National Comparative Assessment Using an Integrated MCDM-Machine Learning Approach},
  journal = {F1000Research},
  year = {2025},
  doi = {10.12688/f1000research.163662.2}
}
Kostenlos starten →