RxScan: An AI-Powered OCR and Machine Learning Framework for Medicine Safety and Drug Interaction Analysis
Author
Smita Mangesh Junnarkar ,Suhani Shukla
Abstract
Medication safety is an important concern because users may have difficulty interpreting medicine labels, understanding side effects, identifying precautions, or recognizing possible interactions between medicines. This paper presents RxScan, an AI-powered medicine safety platform that combines Optical Character Recognition (OCR), a structured real-medicine dataset, and machine learning based safety analysis in a web-based application. The system allows a user to upload a photograph of a medicine strip, extracts the medicine name using OCR, and retrieves relevant information such as composition, uses, side effects, warnings, precautions, and dosage-related information from the medicine dataset. RxScan further provides a personalized safety-checking module in which user information such as age, gender, pregnancy status where applicable, medical conditions, allergies, and current medicines can be considered. An interaction module compares the identified medicine with existing medicines entered by the user and presents possible drug-drug interactions together with their severity and a simple explanation. The system also generates an understandable compatibility or safety score and can display suitable alternatives from the dataset with an appropriate medical disclaimer. The proposed framework is intended as an informational and decision-support tool and does not replace professional medical advice, diagnosis, or prescription.
Keywords
RxScan, Optical Character Recognition, OCR, Medicine Safety, Drug Interaction, Machine Learning, Medicine Dataset, Personalized Healthcare.
DOI : https://doi.org/10.5281/zenodo.23180952
Full Text:
References
[1] World Health Organization, “Medication Without Harm: WHO Global Patient Safety Challenge on Medication Safety,” World Health Organization, Geneva, 2017.
[2] World Health Organization, “Medication Safety in High-risk Situations,” World Health Organization, Geneva, 2019.
[3] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
[4] R. Smith, “An overview of the Tesseract OCR engine,” in Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR), 2007, pp. 629–633.
[5] D. S. Wishart et al., “DrugBank 5.0: A major update to the DrugBank database for 2018,” Nucleic Acids Research, vol. 46, no. D1, pp. D1074–D1082, 2018.
[6] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees. Belmont, CA: Wadsworth International Group, 1984.
[7] World Health Organization, “Global Patient Safety Action Plan 2021–2030: Towards Eliminating Avoidable Harm in Health Care,” World Health Organization, Geneva, 2021.