Thanh Thieu1, Jonathan Camacho Maldonado2, Pei-Shu Ho2, Min Ding3, Alex Marr2, Diane Brandt4, Denis Newman-Griffis5, Ayah Zirikly2, Leighton Chan2, Elizabeth Rasch2. 1. Oklahoma State University, Stillwater, OK, United States. Electronic address: tthieu@okstate.edu. 2. National Institutes of Health Clinical Center, Bethesda, MD, United States. 3. National Institute of Standards and Technology, Gaithersburg, MD, United States. 4. Social Security Advisory Board, Washington, DC, United States. 5. National Institutes of Health Clinical Center, Bethesda, MD, United States; Ohio State University, Columbus, OH, United States.
Abstract
BACKGROUND: Secondary use of Electronic Health Records (EHRs) has mostly focused on health conditions (diseases and drugs). Function is an important health indicator in addition to morbidity and mortality. Nevertheless, function has been overlooked in accessing patients' health status. The World Health Organization (WHO)'s International Classification of Functioning, Disability and Health (ICF) is considered the international standard for describing and coding function and health states. We pioneer the first comprehensive analysis and identification of functioning concepts in the Mobility domain of the ICF. RESULTS: Using physical therapy notes at the National Institutes of Health's Clinical Center, we induced a hierarchical order of mobility-related entities including 5 entities types, 3 relations, 8 attributes, and 33 attribute values. Two domain experts manually curated a gold standard corpus of 14,281 nested entity mentions from 400 clinical notes. Inter-annotator agreement (IAA) of exact matching averaged 92.3 % F1-score on mention text spans, and 96.6 % Cohen's kappa on attributes assignments. A high-performance Ensemble machine learning model for named entity recognition (NER) was trained and evaluated using the gold standard corpus. Average F1-score on exact entity matching of our Ensemble method (84.90 %) outperformed popular NER methods: Conditional Random Field (80.4 %), Recurrent Neural Network (81.82 %), and Bidirectional Encoder Representations from Transformers (82.33 %). CONCLUSIONS: The results of this study show that mobility functioning information can be reliably captured from clinical notes once adequate resources are provided for sequence labeling methods. We expect that functioning concepts in other domains of the ICF can be identified in similar fashion.
BACKGROUND: Secondary use of Electronic Health Records (EHRs) has mostly focused on health conditions (diseases and drugs). Function is an important health indicator in addition to morbidity and mortality. Nevertheless, function has been overlooked in accessing patients' health status. The World Health Organization (WHO)'s International Classification of Functioning, Disability and Health (ICF) is considered the international standard for describing and coding function and health states. We pioneer the first comprehensive analysis and identification of functioning concepts in the Mobility domain of the ICF. RESULTS: Using physical therapy notes at the National Institutes of Health's Clinical Center, we induced a hierarchical order of mobility-related entities including 5 entities types, 3 relations, 8 attributes, and 33 attribute values. Two domain experts manually curated a gold standard corpus of 14,281 nested entity mentions from 400 clinical notes. Inter-annotator agreement (IAA) of exact matching averaged 92.3 % F1-score on mention text spans, and 96.6 % Cohen's kappa on attributes assignments. A high-performance Ensemble machine learning model for named entity recognition (NER) was trained and evaluated using the gold standard corpus. Average F1-score on exact entity matching of our Ensemble method (84.90 %) outperformed popular NER methods: Conditional Random Field (80.4 %), Recurrent Neural Network (81.82 %), and Bidirectional Encoder Representations from Transformers (82.33 %). CONCLUSIONS: The results of this study show that mobility functioning information can be reliably captured from clinical notes once adequate resources are provided for sequence labeling methods. We expect that functioning concepts in other domains of the ICF can be identified in similar fashion.
Authors: Ozlem Uzuner; Andreea Bodnari; Shuying Shen; Tyler Forbush; John Pestian; Brett R South Journal: J Am Med Inform Assoc Date: 2012-02-24 Impact factor: 4.497
Authors: Sameer Pradhan; Noémie Elhadad; Brett R South; David Martinez; Lee Christensen; Amy Vogel; Hanna Suominen; Wendy W Chapman; Guergana Savova Journal: J Am Med Inform Assoc Date: 2014-08-21 Impact factor: 4.497
Authors: Steven J Skube; Elizabeth A Lindemann; Elliot G Arsoniadis; Mari Akre; Elizabeth C Wick; Genevieve B Melton Journal: AMIA Jt Summits Transl Sci Proc Date: 2018-05-18
Authors: Vera C Kaelin; Mina Valizadeh; Zurisadai Salgado; Julia G Sim; Dana Anaby; Andrew D Boyd; Natalie Parde; Mary A Khetani Journal: Front Rehabil Sci Date: 2022
Authors: Carel G M Meskers; Sabina van der Veen; Jenia Kim; Caroline J W Meskers; Quirine T S Smit; Stella Verkijk; Edwin Geleijn; Guy A M Widdershoven; Piek T J M Vossen; Marike van der Leeden Journal: Ann Med Date: 2022-12 Impact factor: 4.709