Disease Identification from Illegible Medical Prescriptions Using OCR and NLP Techniques

Title

Disease Identification from Illegible Medical Prescriptions Using OCR and NLP Techniques

Creator

Kokatnoor, Sujatha Arun

Description

Medical prescriptions that are challenging to interpret present significant issues for the healthcare industry because they increase the possibility of errors in patient care and medication administration. This study presents an efficient workflow that uses Optical Character Recognition (OCR) technology, specifically, Tesseract OCR, along with a preprocessing step to extract text from handwritten prescriptions. The preprocessing stage uses grayscale conversion, noise reduction, and contrast enhancement to increase the accuracy of OCR. Significant results from experiments on a publicly accessible dataset show that preprocessing greatly improves performance, lowering the error rate from 34.7 to 18.3% and raising average accuracy from 65.3 to 81.7%. The enhanced accuracy outweighs the modest increase in processing time (from 0.8 to 1.2s), emphasizing the potential of using these techniques in practical healthcare applications. The studys findings also demonstrated the successful analysis of the text using Natural Language Processing (NLP) and Clinical Bidirectional Encoder Representations from Transformers (ClinicalBERT) techniques by identifying four distinct diseases, Common Cold, Diabetes Mellitus, Bronchitis, and disease caused by Anemia, as validated by a medical professional. This demonstrates the systems potential to improve health care processes by automatically digitizing handwritten prescriptions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Source

Lecture Notes in Electrical Engineering;Volume;1461 LNEE;pp.545-557

Date

01-01-2026

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Contrast enhancement; Contrast-limited adaptive histogram equalization (CLAHE); Disease identification; Healthcare automation; Image preprocessing; Medical prescriptions; Natural language processing (NLP); Noise reduction; Optical character recognition (OCR); Tesseract

Coverage

Kokatnoor S.A., Department of Computer Science and Engineering, School of Engineering and Technology, Christ University, Karnataka, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 18761100; ISBN: 978-981969723-6;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-96-9724-3_40

https://www.scopus.com/pages/publications/105030158896?origin=resultslist