Quantum-classical deep learning hybrid architecture with graphene-printed low-cost capacitive sensor for essential tremor detection.

This study presents a novel hardware and software architecture combining capacitive sensors, quantum-inspired algorithms, and deep learning applied to the detection of Essential Tremor. At the core of this architecture are graphene-printed capacitive sensors, which provide a cost-effective and efficient solution for tremor data acquisition. These sensors, known for their flexibility and precision, are specifically calibrated to monitor tremor movements across various fingers. A distinctive feature of this study is the incorporation of quantum-inspired computational filters-namely, Quantvolution and QuantClass-into the deep learning framework. This integration offers improved processing capabilities, facilitating a more nuanced analysis of tremor patterns. Initial findings indicate greater stability in loss variability; however, further research is necessary to confirm these effects across broader datasets and clinical environments. The approach highlights a promising application of quantum-inspired methods within healthcare diagnostics.