This research introduces an AmI-based framework for Smart Hospital Rooms (SHRs) which makes use of algorithmic reasoning to support smart patient monitoring and adaptive healthcare environments. The essence of the system is a rule-based context inference engine implemented in the PyKnow framework, which processes real-time multimodal sensor data, including heart rate, oxygen saturation, ambient temperature, humidity, and patient activity, and infers clinically meaningful states. These states, Health Emergency, Patient Sleeping, and Room Unoccupied, are utilized to fire automated actuation responses like turning alarms on, changing environment controls, or alerting caregivers. The system embeds an edge-based IoT architecture supported by secure MQTT communication, voice command through Amazon Alexa, and a real-time video stream via ESP32-CAM. It logs and visualizes data via InfluxDB and Grafana, facilitating ongoing monitoring and analysis. A centralized server interface enables multi-room and ICU-level deployment. Experimental evaluation illustrates the system’s reliability, context accuracy, and scalability deployment potential in intelligent healthcare environments.