Open Access

ARTICLE

HealthyBrain: A Scalable Microservices-Based Smart Healthcare System for Remote Patient Monitoring

Shounak Mandal¹, Subhadip Pati^1,#, Nirmallyadeb Ray^1,#, Bipasha Guha Roy^2,#, Priyanka Saha³, Deepsubhra Guha Roy^2,*

1 Department of Computer Science and Business Systems, Institute of Engineering & Management, Kolkata, India
2 IEM Centre of Excellence for Cloud Computing & IoT, Department of CSE (AIML), Institute of Engineering & Management, University of Engineering and Management, Kolkata, India
3 Department of CSE (AIML), Brainware University, Kolkata, India

* Corresponding Author: Deepsubhra Guha Roy. Email:
# These authors contributed equally to this work

Digital Engineering and Digital Twin 2026, 4, 27-47. https://doi.org/10.32604/dedt.2026.081859

Received 10 March 2026; Accepted 14 May 2026; Issue published 14 August 2026

Abstract

HealthyBrain is a scalable, interoperable, and intelligent Remote Patient Monitoring (RPM) platform built on Internet of Things (IoT) technologies and a modular microservices architecture. The system integrates wearable IoT devices, MQTT (Message Queuing Telemetry Transport)-based lightweight messaging, and high-throughput real-time data streaming via Apache Kafka. Edge-side preprocessing enables low-latency analytics, while machine learning-based anomaly detection models facilitate early identification of critical health events. To ensure clinical interoperability, the platform adheres to the HL7 FHIR (Fast Healthcare Interoperability Resources) standard for electronic health record exchange. The system’s novel contribution lies in the unified integration of edge intelligence, standards-compliant streaming pipelines, and production-grade DevOps automation—a combination not addressed holistically by prior work. Container orchestration through Kubernetes provides horizontal scalability, self-healing, and seamless rolling deployments, while CI/CD (Continuous Integration and Continuous Delivery) automation via Jenkins ensures reliable and reproducible software delivery. The anomaly detection module employs an ensemble of machine learning models, including Random Forest, XGBoost, and LSTM-trained on physiological time-series data to classify health anomalies with high precision. Security is enforced using Transport Layer Security (TLS 1.3) for data in transit and JSON Web Token (JWT)-based authentication for Application Programming Interface (API) access control, with role-based access control (RBAC) governing inter-service permissions. A simulation of 100 virtual patients over a 24-h period demonstrates real-time responsiveness with end-to-end latency below 2 s, anomaly detection accuracy of 96%, and a throughput of approximately 1.2 million sensor readings per day. The platform addresses key limitations of existing Remote Patient Monitoring (RPM) systems by combining lightweight edge filtering, decoupled event-driven streaming, first-class HL7 FHIR interoperability, and Kubernetes-native CI/CD in a single cohesive framework. A comparative evaluation against baseline approaches demonstrates the system’s superior performance in latency, scalability, and detection accuracy. HealthyBrain is designed to be device-agnostic, supporting BLE, Zigbee, and LoRaWAN (low-power wireless communication protocols), and is population-scalable from rural clinics to large urban hospitals. The architecture provides a robust foundation for next-generation digital healthcare infrastructure, with future extensions targeting federated learning, blockchain-based audit trails, and clinical-grade Intensive Care Unit (ICU) monitoring.

---

Keywords

---