EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Detection of Anomaly-Based Intrusions in Smart Health Using Explainable AI

Saad Shakeel Abbasi, Saba Mahmood, Fatima Khalique, Mohammed Ali Alshara, Tariqullah Jan, Ruhul Amin Khalil

IEEE Access · 2026 · 14 · 73096-73113

DOI: 10.1109/access.2026.3692365 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Saad Shakeel Abbasi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of the Associate Provost for Research at United Arab Emirates University (UAEU), United Arab Emirates, Prince Sultan University (PSU), Saudi Arabia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly-based threat detection is crucial for organizations. Anomalies are deviations from the norm and can sometimes be hard to identify in contextual cases. These anomalies may arise from an insider-based malicious intrusion. Anomalies are mostly unsupervised and sometimes require expert validation to confirm their occurrence. The black-box nature of unsupervised machine learning models offers little insight into the origin and details of the anomaly. Thus, there is a need for an explanation layer in anomaly detection systems to aid decision-makers in tracking anomalies. Anomaly-based threat detection is critical for smart health scenarios. In this research, we have utilized the electronic patient record to identify unsupervised anomalies. We have suggested adding an explainability layer that utilizes unsupervised learning. The results indicated that Isolation Forest outperformed the other methods on the clustering metrics, as validated by the explainability layer. Lime and Shap are used to visually explain the anomaly’s cause using feature contributions. User-friendly, explainable captions are generated for each anomaly instance, enabling non-technical users to easily understand the results from Lime and Shap. Three metrics, fidelity, sparsity, and stability, are used to validate the explanation layer, which explains each instance of an anomaly: fidelity requires $R^{2} \ge 0.70$ , sparsity favors a smaller number of features that provide user-friendly results, and stability is high. Finally, a Lime-Shap agreement is used to validate the results for each anomaly instance across all Explanations (all seeds). The proposed scheme adds trust to unsupervised learning results, thereby increasing user confidence in the anomaly detection algorithm’s outcomes and aiding decision-makers.

Förderung

  • Office of the Associate Provost for Research at United Arab Emirates University (UAEU), United Arab Emirates
  • Prince Sultan University (PSU), Saudi Arabia

Zitieren

APA

Abbasi, S. S., Mahmood, S., Khalique, F., Alshara, M. A., Jan, T., & Khalil, R. A. (2026). Enhancing Detection of Anomaly-Based Intrusions in Smart Health Using Explainable AI. IEEE Access, 14, 73096-73113. https://doi.org/10.1109/access.2026.3692365

Vancouver

Abbasi SS, Mahmood S, Khalique F, Alshara MA, Jan T, Khalil RA. Enhancing Detection of Anomaly-Based Intrusions in Smart Health Using Explainable AI. IEEE Access. 2026;14:73096-73113. doi:10.1109/access.2026.3692365

BibTeX
@article{Abbasi2026,
  author = {Abbasi, Saad Shakeel and Mahmood, Saba and Khalique, Fatima and Alshara, Mohammed Ali and Jan, Tariqullah and Khalil, Ruhul Amin},
  title = {Enhancing Detection of Anomaly-Based Intrusions in Smart Health Using Explainable AI},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {73096--73113},
  doi = {10.1109/access.2026.3692365}
}
Kostenlos starten →