Smart E-Prescription Management System using Laravel, Vue.js & OpenAI API
Authors/Creators
Description
This presentation introduces the Smart E-Prescription Management System, a graduation project developed using Laravel 12, Vue.js 3, and the OpenAI API. The system addresses critical problems in traditional paper-based prescriptions, including lost or illegible documents, missed drug interactions, and the lack of connectivity between doctors, patients, and pharmacists. The proposed solution provides a unified digital prescription platform with AI-powered drug interaction detection in real-time. Key features include a multi-role dashboard for doctors, patients, and pharmacists, prescription tracking, role-based access control, and pharmacy dispensing by patient ID. The technology stack integrates Laravel with Sanctum authentication, Vue.js for reactive dashboards, OpenFDA as the drug database source, MySQL for data storage, and Spatie packages for permissions management. Literature review results confirm that while existing ML models achieve high accuracy (AUC 0.92, 93.8% classification), none offer a real-time end-user clinical system — a gap this project directly addresses. System diagrams including a block diagram, use case diagram, and sequence diagram are presented to illustrate the architecture and workflow.
This work was conducted at Arab International University (AIU), Syria. The official website of the university is: https://www.aiu.edu.sy
Files
Files
(3.4 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:51a579e00ff32025963a9af6a549c5a9
|
3.4 MB | Download |
Additional details
References
- [1] S. Mei and K. Zhang, "A machine learning framework for predicting drug-drug interactions," Scientific Reports, vol. 11, 2021.
- [2] "Drug-drug interactions prediction based on deep learning: A review," iScience, vol. 27, 2024.
- [3] "Improved DDI prediction using ensemble deep neural networks," Informatics in Medicine Unlocked, vol. 34, 2022.
- [4] "Application of AI in DDI Prediction," J. Chem. Inf. Model., vol. 63, 2023.
- [5] "Electronic prescription system requirements: a scoping review," BMC Med. Inform. Decis. Mak., vol. 22, 2022.
- [6] "Predicting adverse drug events using ML: systematic review," Frontiers in Pharmacology, vol. 15, 2024.