Enhancing Data Quality in Health Research: Performance Insights of a Clinical NLP Algorithm for Diverse Medical Domains
This study presents performance insights into our clinical Natural Language Processing (NLP) pipeline. We have developed multilingual transformer-based models, trained on in-house curated data, for concept recognition, normalization and attribute extraction such as negation and temporality.
Authors: Clara L. Oeste, Jana Van Canneyt, Alina Kramchaninova, Lucas Sterckx, Narges Farokhshad, Iege Bassez, Shahbaz Pervaiz, Geert Van Gorp, Dries Hens
• Our clinical NLP pipeline significantly enhances real-world data (RWD) quality and integrity by enriching OMOP-CDM datasets with unstructured data.
• Initial out-of-the-box (OOTB) metrics demonstrate promising results, with subsequent validation across diverse medical domains validating its effectiveness for continuous data enrichment.
• Its successful implementation in studies leading to peer-reviewed scientific manuscripts underscores its role in supporting large-scale, cross-institutional research initiatives, contributing to evidence-based medical insights.
Complete the form above to download the poster and discover the methods used and the results obtained.
• Our clinical NLP pipeline significantly enhances real-world data (RWD) quality and integrity by enriching OMOP-CDM datasets with unstructured data.
• Initial out-of-the-box (OOTB) metrics demonstrate promising results, with subsequent validation across diverse medical domains validating its effectiveness for continuous data enrichment.
• Its successful implementation in studies leading to peer-reviewed scientific manuscripts underscores its role in supporting large-scale, cross-institutional research initiatives, contributing to evidence-based medical insights.
Complete the form above to download the poster and discover the methods used and the results obtained.
