[HTML][HTML] Comparison of BERT implementations for natural language processing of narrative medical documents

A Turchin, S Masharsky, M Zitnik - Informatics in Medicine Unlocked, 2023 - Elsevier
Abstract Background and objectives Bidirectional Encoder Representations from
Transformers (BERT) word embedding models have been successfully used for many …

Impact of possible errors in natural language processing-derived data on downstream epidemiologic analysis

Z Lan, A Turchin - JAMIA open, 2023 - academic.oup.com
Objective To assess the impact of potential errors in natural language processing (NLP) on
the results of epidemiologic studies. Materials and Methods We utilized data from three …

EXIST: EXamining rIsk of excesS adiposiTy—Machine learning to predict obesity‐related complications

A Turchin, FJ Morrison, M Shubina… - Obesity Science & …, 2024 - Wiley Online Library
Background Obesity is associated with an increased risk of multiple conditions, ranging from
heart disease to cancer. However, there are few predictive models for these outcomes that …

Shaping the Future of Healthcare With BERT in Clinical Text Analytics

AK Chaudhari - Future of AI in Biomedicine and Biotechnology, 2024 - igi-global.com
Over the last two decades, electronic health records (EHRs) have evolved as a crucial
repository for patient health data, encompassing both structured and unstructured …

[PDF][PDF] Informatics in Medicine Unlocked

A Turchin, S Masharsky, M Zitnik - zitniklab.hms.harvard.edu
ABSTRACT Background and objectives: Bidirectional Encoder Representations from
Transformers (BERT) word embedding models have been successfully used for many …