https://www.nvpublicationhouse.com/index.php/nvlajast en-US Nvpubhouse Library for American Journal of Applied Science and Technology https://www.nvpublicationhouse.com/index.php/nvlajast/article/view/1359 <p>Purpose: The automotive industry is undergoing a paradigm shift from traditional, reactive maintenance schedules to proactive, data-driven health monitoring. This article synthesizes the current body of research on the digital technologies underpinning this transformation. It aims to provide a comprehensive overview of how On-Board Diagnostics (OBD), the Internet of Things (IoT), telematics, and Artificial Intelligence (AI) are converging to create integrated vehicle health inspection systems.</p> <p>Methods: This study employs a systematic review and synthesis of 20 peer-reviewed articles published between 2018 and 2021. The selected literature focuses on key technological pillars, including predictive maintenance algorithms, telematics data utilization, IoT sensor integration, and AI-driven diagnostics. The analysis framework categorizes findings into three primary themes: foundational technologies, data analytics and intelligence, and practical applications and impacts.</p> <p>Findings: The synthesis reveals a multi-layered technological ecosystem. Foundational technologies like OBD-II and advanced IoT sensors provide the raw data stream (1, 16, 19). This data is transmitted via telematics systems for analysis (3, 13, 15). The core of the digital shift lies in the application of AI, machine learning, and big data analytics to translate this data into actionable, predictive insights, enabling the anticipation of component failures before they occur (2, 4, 12, 20). Key applications include significant improvements in the efficiency and cost-effectiveness of fleet management (7, 14, 17) and enhanced safety and reliability for individual vehicle owners.</p> <p>Conclusion: The integration of digital diagnostics represents a fundamental evolution in vehicle maintenance. While the potential for proactive and predictive health monitoring is substantial, significant challenges remain, particularly concerning data security (9), system standardization, and implementation costs. Future research should focus on refining predictive models, enhancing cybersecurity protocols, and developing scalable, cost-effective solutions to accelerate industry-wide adoption.</p> Dr. Amina R. El-Sharif Prof. Lucas M. Granger Copyright (c) 2025 Dr. Amina R. El-Sharif, Prof. Lucas M. Granger https://creativecommons.org/licenses/by/4.0 2025-10-01 2025-10-01 5 10 1 8