An automated data verification approach for improving data quality in a clinical registry.
Journal:
Computer methods and programs in biomedicine
Published Date:
Nov 1, 2019
Abstract
BACKGROUND AND OBJECTIVE: The quality of data is crucial for clinical registry studies as it impacts credibility. In the regular practice of most such studies, a vulnerability arises from researchers recording data on paper-based case report forms (CRFs) and further transcribing them onto registry databases. To ensure the quality of data, verifying data in the registry is necessary. However, traditional manual data verification methods are time-consuming, labor-intensive and of limited-effect. As paper-based CRFs and electronic medical records (EMRs) are two sources for verification, we propose an automated data verification approach based on the techniques of optical character recognition (OCR) and information retrieval to identify data errors in a registry more efficiently.
Authors
Keywords
Algorithms
Automation
Coronary Artery Disease
Data Accuracy
Databases, Factual
Electronic Health Records
Humans
Information Storage and Retrieval
Language
Machine Learning
Medical Informatics
Natural Language Processing
Pattern Recognition, Automated
Programming Languages
Registries
Regression Analysis
Reproducibility of Results