{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:53:03Z","timestamp":1791175983615,"version":"4.1.0"},"reference-count":14,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>The current trend involving the use of paper-based medical prescriptions and the exchange of such by the social media is a major problem in automated and accurate text extraction in healthcare processes. This paper suggests a complete smart pipeline to digitize the images of medical prescriptions with lightweight deep learning-based classification, specialized Optical Character Recognition (OCR) engines, and comparative benchmarking of results using a large language model (LLM). The web scraped images of medical prescriptions are initially processed through a GhostNetV2 classifier to differentiate between handwritten and digital medical prescriptions. According to this choice, digital images are sent to PaddleOCR, and handwritten images are considered in Tesseract OCR so that each image could be processed by the best suitable recognition engine. The OCR outputs from both branches are benchmarked against GPT-4o (OpenAI) as an independent baseline to assess competitive performance and provide error-rate context. Experimental analysis shows that the suggested adaptive routing strategy is characterized by the fact that it has a high classification rate and the character and word error rates are significantly lower than those single-OCR techniques. The system is competitive with, though does not exceed, the raw accuracy of a state-of-the-art LLM-based OCR baseline (GPT-4o), while offering practical advantages in cost, transparency, and on-premises deployability that the black-box, per-call LLM baseline does not. The findings verify that the combination of lightweight classifiers and multi-OCR decision routing and multi-LLM-aided comparative benchmarking offers a scalable and robust solution to real-world medical prescriptions digitization, which adds to better automation, accuracy, and safety in healthcare information processing.<\/jats:p>","DOI":"10.3389\/fmed.2026.1856485","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:36:11Z","timestamp":1791174971000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid deep learning\u2013based OCR model for handwritten medical prescriptions"],"prefix":"10.3389","volume":"13","author":[{"given":"Omar Z.","family":"Ameer","sequence":"first","affiliation":[{"name":"College of Pharmacy, Alfaisal University","place":["Riyadh, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmood Hameed","family":"Majeed","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, College of Engineering, Al-Nahrain University","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Safa L.","family":"Kailan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, College of Engineering, Al-Nahrain University","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saif Mohamed Baraa","family":"Alsabti","sequence":"additional","affiliation":[{"name":"Technical College of Engineering, Al-Bayan University","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali M.","family":"Elhenidy","sequence":"additional","affiliation":[{"name":"Computer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University","place":["Mansoura, Egypt"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.24018\/ejai.2025.4.6.79","article-title":"Enhancing optical character recognition (OCR) accuracy in healthcare prescription processing using artificial neural networks","volume":"4","author":"Srikanth Reddy","year":"2025","journal-title":"EJAI"},{"key":"B2","author":"Ullah","year":"2025"},{"key":"B3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10032-025-00525-x","article-title":"Exploring the effectiveness of data-centric AI approaches to developing a prescription recognition system","volume":"29","author":"Kim","year":"2025","journal-title":"IJDAR"},{"key":"B4","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.visinf.2021.07.002","article-title":"Algorithms for rapid digitalization of prescriptions","volume":"5","author":"Gupta","year":"2021","journal-title":"Visual Informatics"},{"key":"B5","article-title":"Transforming images to insights: ocr-driven sentiment analysis for medical data classification","volume":"103","author":"Sreya","year":"2025","journal-title":"Journal of Theoretical and Applied Information Technology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"128623","DOI":"10.1016\/j.eswa.2025.128623","article-title":"Deep prescription understanding and low-cost medication dispensing and management for elderly care","volume":"293","author":"Ghazal","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B7","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s10791-025-09619-w","article-title":"Medicine image classification using deep learning: highlighting the MedNet-Mobil hybrid model","volume":"28","author":"Saqib","year":"2025","journal-title":"Discov Computing"},{"key":"B8","first-page":"4510","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"B9","author":"Singh","year":"2025"},{"key":"B10","unstructured":"Rubyat\n              A\n            \n            \n              Rahman\n              B\n            \n            \n              Zaman\n              MFU\n            \n          \n          IUB\n          Design and early-stage development of a handwritten prescription interpretation app for Bangladeshi citizens\n          \n          2025"},{"key":"B11","doi-asserted-by":"publisher","first-page":"9969","DOI":"10.52202\/068431-0724","article-title":"Ghostnetv2: enhance cheap operation with long-range attention","volume":"35","author":"Tang","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"B12","doi-asserted-by":"publisher","first-page":"14907","DOI":"10.1007\/s00521-025-11207-4","article-title":"GY-YOLO: ghost separable YOLO for pedestrian detection","volume":"37","author":"Elhenidy","year":"2025","journal-title":"Neural Comput & Applic"},{"key":"B13","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s42452-025-07991-2","article-title":"Bio-inspired underwater robotic vehicle for marine exploration and AI-powered fish detection","volume":"8","author":"Sameh","year":"2026","journal-title":"Discov Appl Sci"},{"key":"B14","first-page":"6023","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1856485\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:36:15Z","timestamp":1791174975000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1856485\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":14,"alternative-id":["10.3389\/fmed.2026.1856485"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1856485","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"article-number":"1856485"}}