The global aging population poses an urgent challenge in ensuring the safety and well-being of elderly individuals. With the rapid development of technologies such as the Internet of Medical Things (IoMT), new avenues for digital healthcare services (DHS) offer promising solutions to support elder-care safety. Simultaneously, society stands at the threshold of a transformative era characterized by the immersive and interconnected 3D landscape of the Metaverse, reshaping how people live, work, and socialize. While fully realizing a comprehensive digital Metaverse landscape remains a vision with various challenges and open questions, a lightweight metaverse version is within reach. This paper proposes an innovative Fuzzy Neural Network (FNN) enhanced Image-based Action Recognition (FIAR) system in Microverse — an edge-scale IoMT Metaverse designed for DHS. Utilizing adaptive FNNs, FIAR enhances the adaptability of the multi-sensor fusion process to accommodate varying input modes and quantities of input sources to reduce decision uncertainty and learn fuzzy relationships among multiple data streams. An experimental study confirms the feasibility of the Microverse framework and FIAR’s capacity to deliver accurate and rapid responses, validating its effectiveness in safeguarding independently living elderly individuals.