Optimizing Healthcare Delivery with a Generative AI-Based Chatbot Platform: A Systematic Review

Córdova-Berona H.A.; Nuñez Diaz L.A.; Vargas Calderon A.C.; Briones-Zuñiga J. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2025) · DOI: 10.18687/leird2025.1.1.828

Resumen

Limited access to healthcare is a major challenge for global health systems, with over 70% of facilities in developing countries lacking adequate technological infrastructure. The scarcity of evidence on the effective implementation of generative AI-based chatbots exacerbates this issue, hindering service optimization. This systematic review analyzes how generative artificial intelligence chatbot platforms optimize healthcare delivery. A review was conducted using PICO components and the PRISMA protocol, selecting 40 articles from Scopus, Web of Science, and EBSCOhost (2020-2024). The results indicate that limitations were addressed through relational agents, gamified chatbots with OMO (Online-Merge-Offline) strategies, culturally-appropriate adaptive systems, and empathetic frameworks. Effectiveness was validated through experimental studies, showing improvements of 95% in continuous availability, 90% in geographical coverage, 85% in response time, and 78% in adherence compared to the traditional 60%. Mental health emerged as the most effective sector, with 30% of successful implementations. In conclusion, generative AI chatbots are effective tools for overcoming traditional access barriers, with variations across sectors. The quality of implementation is more important than the specific chatbot type, where cultural adaptation and personalization determine sustainable success. It is suggested that large-scale studies be developed in low- and middle-income countries, and that these systems be integrated with medical IoT technologies. © LEIRD 2025.All rights reserved.

Instituciones: Universidad Tecnológica del Perú