Implementation and Evaluation of an AI-Based Healthcare Chatbot Using PHP and OpenAI API | IJCT Volume 13 – Issue 2 | IJCT-V13I2P5
International Journal of Computer Techniques
ISSN 2394-2231
Author
J.Gopinath, Dr.S. Selvakani, Mrs.K. Vasumathi
Abstract
This research presents the design and implementation of MEDI-BOT, an intelligent healthcare chatbot system engineered to bridge the gap between patient inquiries and preliminary clinical analysis. In the current healthcare landscape, the increasing burden on medical facilities necessitates automated yet reliable tools for symptom triage and patient management. MEDI-BOT addresses this by utilizing the PHP Laravel framework as a robust backend and the OpenAI API (leveraging Large Language Models) as the core intelligence engine. The system introduces a multi-modular architecture that includes secure user authentication, real-time conversational AI, and a persistent medical history repository. AI-powered chatbots, in particular, have emerged as effective tools for providing real-time health information, preliminary symptom assessment, and patient engagement through natural language interaction. This paper presents the development and evaluation of an AI-powered healthcare chatbot system implemented using PHP and the OpenAI API.
Keywords
Automatic Artificial Intelligence, Healthcare Chatbot, Natural Language Processing, Machine Learning, Automatic Diagnosis, Virtual Assistant, Symptom Checker, Medical Chatbot, Health Informatics, Patient Engagement
Conclusion
The development of MEDI-BOT successfully demonstrates that AI-powered healthcare tools can be both intelligent and secure. By combining the PHP Laravel framework with OpenAI’s Large Language Models, we have created a system that provides instant, data-driven medical guidance while strictly adhering to the Intelligent Data Privacy Model. The implementation of AES-256 encryption within a relational database ensures that patient confidentiality is never compromised, fulfilling the primary objective of modern digital health systems.
References
[1] Grochowski, K., & Cabaj, K. (2018). Practical Problems of Internet Threats Analyses. This research provides the foundation for automated analysis in high-risk data environments, informing the bot’s threat-detection logic. [2] Oberheide, J., & Cooke, E. (2020). Cloud AV: N-Version Antivirus in the Network Cloud. This study justifies the offloading of intensive symptom analysis to a cloud-based intelligence layer (OpenAI)maintain local system performance. [3] Wang, X., Yang, Y., & Zeng, Y. (2019). Accurate Mobile Malware Detection and Classification in the Cloud. Highlights the necessity of cloud-integrated architectures for resource-heavy analysis, supporting MEDI-BOT’s API-driven design. [4] Watson, M. R., & Shirazi, S. N. (2019). Malware Detection cloud Computing Infrastructures. Focuses on anomaly detection and resilience, which informed the implementation of the Laravel middleware security layer. [5] Johnson, A., & Smith, B. (2023). Leveraging Large Language Models for Medical Symptom Analysis. An evaluation of GPT-based models in clinical settings, establishing the reliability standards for MEDI-BOT’s diagnostic responses. [6] Wang, S., & Zhang, Y. (2021). Natural Language Processing for Healthcare Applications. Explores the challenges of medical jargon processing, providing the basis for the “System Prompt” engineering used in the AI module. [7] Martinez, E., & Chen, H. (2022). The Role of Chatbots in Patient-Centered Healthcare Delivery. A study on user trust and UX design, which led to the inclusion of the sidebar chat history and patient profile features. [8] Gupta, R., & Varma, K. S. (2021). Performance Optimization of PHP-Based Frameworks in Healthcare Web Services. This paper details the use of Laravel for managing sensitive EHR (Electronic Health Records) and its efficiency in API handling. [9] Thompson, L., & Wright, K. (2022). Security Protocols and SQL Encryption for Relational Databases in E-Health. Specifically covers the implementation of AES encryption within MySQL databases for patient privacy. [10] Roberts, M. L. (2020). Design and Implementation of Automated Reporting Systems in Telemedicine. Provides technical insights into HTML-to-PDF conversion logic for creating downloadable clinical summaries.
How to Cite This Paper
J.Gopinath, Dr.S. Selvakani, Mrs.K. Vasumathi (2026). Implementation and Evaluation of an AI-Based Healthcare Chatbot Using PHP and OpenAI AP. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
