Patient-Centric Edge Intelligence For Hospital Monitoring: Embedded Anomaly Detection, Ethical Governance And Selective Telemetry

Rahul Reddy Hanumanthgari¹

---

ABSTRACT

Modern hospitals use patient monitoring systems that generate substantial data streams and send them to the cloud, facing challenges such as data streams, costs, privacy issues, and latency that are directly linked to cloud-based analysis or architecture. Our project addresses the limitations of existing systems by enabling local inference and embedded anomaly detection with ethical governance and selective telemetry. This paper presents a patient-centric edge intelligence framework integrated into devices that feature anomaly detection, selective telemetry, and governance-aware selection. The architecture operates by embedding intelligence at the edge to detect clinically relevant anomalies locally, and by escalating complex data scenarios to the cloud only when necessary. The evaluation strategy focuses on hospital monitoring scenarios, emphasizing latency reduction, bandwidth efficiency, and privacy preservation. Our paper presents a novel illustration of how edge intelligence can enhance patient care, reduce reliance on cloud computing, and support the ethical deployment of AI in future clinical environments.

Keywords: Edge Intelligence, Patient-Centric AI, Hospital Monitoring, Anomaly Detection, Ethical AI, Selective Telemetry, Healthcare IoT

How to cite this article: Hanumanthgari RR. Patient-Centric Edge Intelligence for Hospital Monitoring: Embedded Anomaly Detection, Ethical Governance and Selective Telemetry. Int J Drug Deliv Technol. 2026;16(11s): 593-600. DOI: 10.25258/ijddt.16.11s.59

Source of support: Nil.

Conflict of interest: None