Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194296,
        author = {Shreyash Purushottam Ghanekar and Sarvesh Sanjay Dhule and Kanad Prasad Kulkarni and Swapnil Ananda Badave and Sumitra Jakhete},
        title = {A Comprehensive Literature Survey on Automated Prescription Digitization: OCR Techniques, Deep Learning Approaches, and Medical Information Retrieval Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8216-8221},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194296},
        abstract = {Handwritten medical prescriptions remain a persistent challenge in healthcare systems due to illegible handwriting, inconsistent prescription formats, and frequent use of non- standard abbreviations. These issues often lead to medication errors, delays in dispensing, and increased workload for pharma- cists and healthcare professionals. Recent advances in computer vision, optical character recognition (OCR), deep learning, and biomedical natural language processing have enabled the development of automated systems capable of converting handwritten prescriptions into structured digital records.
This paper presents a comprehensive literature survey of automated prescription digitization systems, focusing on OCR techniques, deep learning–based handwriting recognition models, and medical information extraction frameworks. The study analyzes traditional OCR engines such as Tesseract, modern deep learning models including CNN-RNN architectures and transformers, object detection models such as YOLOv5 for region localization, and biomedical language models such as BioBERT for entity recognition.
Furthermore, this review discusses common architectural approaches found in recent studies for integrating image pre- processing, text detection, OCR, entity extraction, and drug knowledge base validation into unified healthcare automation pipelines. The survey highlights current challenges including handwriting variability, dataset limitations, OCR errors, and the lack of standardized evaluation benchmarks. The insights provided in this paper aim to guide researchers and developers in understanding the current state-of-the-art and identifying open gaps in prescription digitization technologies.},
        keywords = {Prescription digitization, Literature Survey, OCR, Deep Learning, YOLOv5, BioBERT, Natural Language Processing, Healthcare automation},
        month = {March},
        }