🔗 This dataset was used in the following publication:

A. R. Mia, M. A. -A. -S. Chowdhury, A. A. Mamun, A. M. Ruddra and N. T. Tanny, "**A Deep Neural Network Approach with Pioneering Local Dataset to Recognize Doctor's Handwritten Prescription in Bangladesh**," 2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems (iCACCESS), Dhaka, Bangladesh, 2024.

DOI: 10.1109/ACCESS.2024.10499631

💊 Prescription Word Dataset for Machine Learning

This dataset was created by extracting and processing prescription images to support educational research and experimentation in machine learning models, particularly for text recognition and classification in healthcare contexts.

📸 Dataset Creation Process

To transform the prescription images into a structured dataset suitable for machine learning, a specialized word detection algorithm was employed. This code segmented the prescription images into individual words, converting the data into a format that facilitates accurate recognition by ML models.

• Word segmentation was the first crucial step.
• Each word was manually screened to retain only pharmaceutical terms.
• All non-drug terms were discarded.
• Manual labelling was performed by multiple team members independently to ensure accuracy.

📊 Dataset Details

• Total Words Extracted: 4,680
• File Format: Excel (.xlsx) and CSV (.csv)
• Number of Classes (Medicines): 78

📚 Drug Names Included

Beklo, Maxima, Leptic, Esoral, Omastin, Esonix, Canazole, Fixal, Progut, Diflu, Montair, Flexilax, Maxpro, Vifas, Conaz, Fexofast, Fenadin, Telfast, Dinafex, Ritch, Renova, Flugal, Axodin, Sergel, Nexum, Opton, Nexcap, Fexo, Montex, Exium, Lumona, Napa, Azithrocin, Atrizin, Monas, Nidazyl, Metsina, Baclon, Rozith, Bicozin, Ace, Amodis, Alatrol, Napa Extend, Rivotril, Montene, Filmet, Aceta, Tamen, Bacmax, Disopan, Rhinil, Flamyd, Metro, Zithrin, Candinil, Lucan-R, Backtone, Bacaid, Etizin, Az, Romycin, Azyth, Cetisoft, Dancel, Tridosil, Nizoder, Ketoral, Ketocon, Ketotab, Ketozol, Denixil, Provair, Odmon, Baclofen, MKast, Trilock, Flexibac.

These classes represent commonly prescribed pharmaceutical names likely to appear in handwritten prescriptions.

🧪 Usage

This dataset is ideal for:

• Text classification
• Optical character recognition (OCR)
• Named entity recognition (NER)
• Deep learning model training and evaluation

⚠️ Note: This dataset is free to use for educational and research purposes only.

either printed or handwritten

Medical Prescription Handwritten Words

This dataset contains images of individual handwritten medical words extracted from prescription notes. It is designed for training and evaluating handwriting recognition models in the healthcare domain.

  Structure

images/: Contains 40+ handwritten word images (e.g., Amoxicillin.png, Cold.png, Tablet.png, 0.png, etc.) data.csv: Maps each image file to its corresponding label (word)

  Example Use Cases

OCR (Optical… See the full description on the dataset page: https://huggingface.co/datasets/avi-kai/Medical_Prescription_Handwritten_Words.

Here are a few use cases for this project:

1. Medical Transcription Assistant: This computer vision model can be used in transcription services, helping transcribe handwritten prescriptions into digital text. Doctors, pharmacists, and healthcare professionals can use such transcriptions for digital record-keeping, data analysis, sharing medical information, and patient follow-ups.

2. Medicine Inventory Management: The model can help pharmacies automate their drug inventory management. By identifying medicines names in prescriptions, the software can update inventory data in real time, ensuring that stocks are always updated and adequate.

3. Drug Interaction Analysis: The model can be applied in an application that identifies potential drug interactions for a given patient's multiple prescriptions. By recognizing the names of medicines, it could cross-check them with a database of known drug interactions, alerting the pharmacist or patient about potential risks.

4. Telemedicine Applications: This model can be useful in telemedicine scenarios where patients send images of their prescriptions. It can analyze the prescription, identify the drug names, and forward the information to online pharmacies for home deliveries or to doctors/nurses for tele-consultations.

5. Pharma Market Research: Companies can use this model to analyze prescriptions to understand the most commonly prescribed drugs, aiding in market research and trending analysis in pharmaceutical industries.

This dataset comprises a diverse range of medical prescription images obtained from various sources. The prescriptions featured in the dataset exhibit illegible handwriting, commonly encountered in medical practices. These images serve as invaluable resources for developing and evaluating algorithms aimed at enhancing handwriting recognition technologies within the medical domain. Researchers, data scientists, and machine learning enthusiasts can utilize this dataset to train and test models for accurately deciphering illegible medical handwriting, thereby improving patient safety and healthcare efficiency.

Here are a few use cases for this project:

1. Healthcare Automation: The model can be used to digitize handwritten medical prescriptions thus reducing manual transcription errors and streamlining the process in pharmacies and hospitals.

2. Historical Document Digitization: This model could be utilized for transcribing old handwritten medical documents for research purposes.

3. Handwriting Analysis Tool: The model can be used for general handwriting analysis purposes, for example in educational institutions to improve handwriting recognition or in forensic analysis.

4. OCR Software Improvement: This model can be integrated with OCR (Optical Character Recognition) software to enhance its performance in recognizing and interpreting handwritten text, capitalizing on the diverse range of characters available.

5. Medical Informatics Studies: Researchers using digital health records for epidemiological studies can utilize this model to extract data from handwritten prescriptions or doctor's notes.

Dataset

This dataset was created by Danial Afridi

Released under MIT

Contents

chaithanyakota/100-handwritten-medical-records dataset hosted on Hugging Face and contributed by the HF Datasets community

This Doctor Handwriting Dataset contains 90 high-quality handwritten medical prescription samples collected manually from 30 different doctors in Nawabshah, Pakistan. Each medicine name is written by 3 doctors, offering diverse handwriting styles and variations. This dataset is ideal for researchers and developers working on handwriting recognition, optical character recognition (OCR) for medical prescriptions, and AI models focused on medical handwriting analysis. It provides valuable real-world data to train and evaluate machine learning models for decoding doctor's handwritten notes and improving healthcare AI systems.

AI OCR to extract data from medical prescriptions. Fast, accurate, and integrable via API/SDK to automate medical document processing.

OCR AI to extract all fields from Health benefits certificate of coverage (PDF/image). Convert to data or Excel via API or SDK. Reliable and customizable.

Dataset

This dataset was created by Chhavi Mohitkar

Released under MIT

Contents

Medical Prescription Reader - Handwritten Text Recognition

Computerized Physician Order Entry Market Outlook

According to our latest research, the global Computerized Physician Order Entry (CPOE) market size in 2024 stands at USD 2.84 billion, driven by the increasing digitization of healthcare systems and the growing emphasis on patient safety. The market is projected to achieve a CAGR of 6.9% from 2025 to 2033, reaching a forecasted value of USD 5.69 billion by the end of the period. The robust growth of the CPOE market is primarily attributed to the rising adoption of advanced healthcare IT solutions, regulatory mandates for error reduction, and the need for streamlined clinical workflows to enhance healthcare delivery and outcomes globally.

One of the most significant growth factors for the Computerized Physician Order Entry market is the global push towards minimizing medication errors and enhancing patient safety. CPOE systems facilitate electronic entry of medical practitioner instructions for the treatment of patients, which eliminates issues associated with handwritten prescriptions such as illegibility and transcription errors. This digitization not only reduces adverse drug events but also ensures standardized care protocols are followed. Furthermore, the integration of CPOE with decision support systems offers real-time alerts and clinical guidelines, further reducing the risk of errors and improving compliance with best practices. As healthcare providers and regulatory bodies continue to prioritize patient safety, the demand for CPOE systems is expected to rise steadily.

Another key driver of the CPOE market is the growing implementation of healthcare IT infrastructure, particularly in emerging economies. Governments and private organizations are investing heavily in digital health initiatives to improve the efficiency and effectiveness of healthcare delivery. The adoption of electronic health records (EHRs) and their integration with CPOE solutions has become increasingly prevalent, enabling seamless information exchange across healthcare settings. Additionally, the rising prevalence of chronic diseases, aging populations, and the need for coordinated care are pushing healthcare organizations to adopt comprehensive digital tools like CPOE to optimize clinical workflows and resource utilization. The increasing focus on interoperability and data analytics further amplifies the value proposition of CPOE systems in modern healthcare environments.

The evolution of reimbursement policies and regulatory frameworks is also catalyzing the uptake of CPOE solutions. In many regions, healthcare providers are incentivized to adopt electronic prescribing and order entry systems through government programs and quality improvement initiatives. For instance, in the United States, the Centers for Medicare & Medicaid Services (CMS) meaningful use program has played a pivotal role in accelerating the implementation of CPOE in hospitals and clinics. Similarly, other countries are introducing legislation and standards to promote the use of digital health technologies for improved patient outcomes and cost efficiencies. These regulatory measures, combined with the growing awareness of the benefits offered by CPOE, are expected to sustain market growth over the forecast period.

From a regional perspective, North America currently dominates the CPOE market, owing to its advanced healthcare infrastructure, high adoption rates of health IT solutions, and strong regulatory support. However, the Asia Pacific region is anticipated to witness the fastest growth during the forecast period, driven by increasing investments in healthcare modernization, expanding healthcare access, and rising awareness among providers regarding the importance of reducing medical errors. Europe also holds a significant share, supported by favorable government policies and a well-established healthcare ecosystem. Meanwhile, Latin America and the Middle East & Africa are gradually emerging as promising markets, as digital transformation initiatives gain momentum in these regions.

Component Analy