TY - JOUR
T1 - Identification of Prediabetes Discussions in Unstructured Clinical Documentation
T2 - Validation of a Natural Language Processing Algorithm
AU - Schwartz, Jessica L.
AU - Tseng, Eva
AU - Maruthur, Nisa M.
AU - Rouhizadeh, Masoud
N1 - Publisher Copyright:
© 2022 JMIR Publications Inc.. All right reserved.
PY - 2022/2/1
Y1 - 2022/2/1
N2 - Background: Prediabetes affects 1 in 3 US adults. Most are not receiving evidence-based interventions, so understanding how providers discuss prediabetes with patients will inform how to improve their care. Objective: This study aimed to develop a natural language processing (NLP) algorithm using machine learning techniques to identify discussions of prediabetes in narrative documentation. Methods: We developed and applied a keyword search strategy to identify discussions of prediabetes in clinical documentation for patients with prediabetes. We manually reviewed matching notes to determine which represented actual prediabetes discussions. We applied 7 machine learning models against our manual annotation. Results: Machine learning classifiers were able to achieve classification results that were close to human performance with up to 98% precision and recall to identify prediabetes discussions in clinical documentation. Conclusions: We demonstrated that prediabetes discussions can be accurately identified using an NLP algorithm. This approach can be used to understand and identify prediabetes management practices in primary care, thereby informing interventions to improve guideline-concordant care.
AB - Background: Prediabetes affects 1 in 3 US adults. Most are not receiving evidence-based interventions, so understanding how providers discuss prediabetes with patients will inform how to improve their care. Objective: This study aimed to develop a natural language processing (NLP) algorithm using machine learning techniques to identify discussions of prediabetes in narrative documentation. Methods: We developed and applied a keyword search strategy to identify discussions of prediabetes in clinical documentation for patients with prediabetes. We manually reviewed matching notes to determine which represented actual prediabetes discussions. We applied 7 machine learning models against our manual annotation. Results: Machine learning classifiers were able to achieve classification results that were close to human performance with up to 98% precision and recall to identify prediabetes discussions in clinical documentation. Conclusions: We demonstrated that prediabetes discussions can be accurately identified using an NLP algorithm. This approach can be used to understand and identify prediabetes management practices in primary care, thereby informing interventions to improve guideline-concordant care.
KW - chronic disease management
KW - machine learning
KW - natural language processing
KW - physician-patient communication
KW - prediabetes
KW - prediabetes discussions
KW - prediabetes management
UR - http://www.scopus.com/inward/record.url?scp=85126472411&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126472411&partnerID=8YFLogxK
U2 - 10.2196/29803
DO - 10.2196/29803
M3 - Article
C2 - 35200154
AN - SCOPUS:85126472411
SN - 2291-9694
VL - 10
JO - JMIR Medical Informatics
JF - JMIR Medical Informatics
IS - 2
M1 - e29803
ER -