Abstract
The COVID-19 pandemic underscored the critical limitations of manual contact tracing, prompting a rapid shift toward digital epidemiology and artificial intelligence (AI). This research article evaluates the integration of AI-driven methodologies into contact tracing frameworks to enhance response speed, accuracy, and scalability. Using a systematic review of developments between 2019 and early 2024, the study examines the efficacy of Bluetooth Low Energy (BLE) systems, nature-inspired computing models, and generative AI in identifying transmission chains. Our analysis indicates that AI-enhanced systems significantly outperform traditional manual methods by reducing the time-to-notification and managing large-scale datasets that are otherwise uninterpretable by human tracers. Key findings highlight the role of speech emotion recognition and acoustic diagnostics (cough analysis) as supplementary screening tools integrated into tracing apps. However, the deployment of these technologies faces persistent challenges related to privacy, data sovereignty, and sociolegal integration. The results demonstrate that while AI provides a robust mechanism for pandemic mitigation, its effectiveness is contingent upon public trust and the alignment of technical architectures with constitutional rights. This paper concludes that future pandemic preparedness must adopt a hybrid model, combining high-resolution AI surveillance with sociolegal support services to address both the biological and societal impacts of infectious disease outbreaks. By synthesizing evidence from diverse global implementations, including comparative analyses of Japanese and German strategies, this research provides a roadmap for the next generation of digital public health infrastructure as of January 2024.