Novel tinnitus diagnosis: biology and technology for public health management

Tinnitus, characterized by the perception of ringing or buzzing in the ears, significantly affects millions globally and negatively impacts their quality of life. Current management strategies vary in effectiveness, underscoring the need for precise, comprehensive diagnostic methods. This study introduces a Quantum Machine Learning (QML) solution for public health management in tinnitus detection, specifically targeting noise-exposed and hypertensive laborers. The proposed Tinnitus Detection-Diagnostic Support System (TDDSS) aims to improve public health management by accurately classifying tinnitus based on behavior, severity, and type, thus determining whether an individual is affected. Leveraging the synergies between advanced quantum mechanics and machine learning techniques, this approach promises enhanced system efficiency, automation, simultaneous data processing capabilities from different sensors, and diagnostic accuracy. Experimental comparisons reveal that the Quantum Neural Network (QNN) significantly outperforms Traditional Machine Learning (TML) algorithms. The experimental results showed that the quantum neural network outperforms (with 99% accuracy) highest among all when compared with the other commonly used traditional machine learning algorithms.