TY - GEN
T1 - Natural language processing based machine learning model using cardiac MRI reports to identify hypertrophic cardiomyopathy patients
AU - Sundaram, Divaakar Siva Baala
AU - Arunachalam, Shivaram P.
AU - Damani, Devanshi N.
AU - Farahani, Nasibeh Z.
AU - Enayati, Moein
AU - Pasupathy, Kalyan S.
AU - Arruda-Olson, Adelaide M.
N1 - Publisher Copyright:
© 2021 by ASME.
PY - 2021
Y1 - 2021
N2 - Hypertrophic Cardiomyopathy (HCM) is the most common genetic heart disease in the US and is known to cause sudden death (SCD) in young adults. While significant advancements have been made in HCM diagnosis and management, there is a need to identify HCM cases from electronic health record (EHR) data to develop automated tools based on natural language processing guided machine learning (ML) models for accurate HCM case identification to improve management and reduce adverse outcomes of HCM patients. Cardiac Magnetic Resonance (CMR) Imaging, plays a significant role in HCM diagnosis and risk stratification. CMR reports, generated by clinician annotation, offer rich data in the form of cardiac measurements as well as narratives describing interpretation and phenotypic description. The purpose of this study is to develop an NLP-based interpretable model utilizing impressions extracted from CMR reports to automatically identify HCM patients. CMR reports of patients with suspected HCM diagnosis between the years 1995 to 2019 were used in this study. Patients were classified into three categories of yes HCM, no HCM and, possible HCM. A random forest (RF) model was developed to predict the performance of both CMR measurements and impression features to identify HCM patients. The RF model yielded an accuracy of 86% (608 features) and 85% (30 features). These results offer promise for accurate identification of HCM patients using CMR reports from EHR for efficient clinical management transforming health care delivery for these patients.
AB - Hypertrophic Cardiomyopathy (HCM) is the most common genetic heart disease in the US and is known to cause sudden death (SCD) in young adults. While significant advancements have been made in HCM diagnosis and management, there is a need to identify HCM cases from electronic health record (EHR) data to develop automated tools based on natural language processing guided machine learning (ML) models for accurate HCM case identification to improve management and reduce adverse outcomes of HCM patients. Cardiac Magnetic Resonance (CMR) Imaging, plays a significant role in HCM diagnosis and risk stratification. CMR reports, generated by clinician annotation, offer rich data in the form of cardiac measurements as well as narratives describing interpretation and phenotypic description. The purpose of this study is to develop an NLP-based interpretable model utilizing impressions extracted from CMR reports to automatically identify HCM patients. CMR reports of patients with suspected HCM diagnosis between the years 1995 to 2019 were used in this study. Patients were classified into three categories of yes HCM, no HCM and, possible HCM. A random forest (RF) model was developed to predict the performance of both CMR measurements and impression features to identify HCM patients. The RF model yielded an accuracy of 86% (608 features) and 85% (30 features). These results offer promise for accurate identification of HCM patients using CMR reports from EHR for efficient clinical management transforming health care delivery for these patients.
KW - Cardiac MRI
KW - Electronic health records (EHR)
KW - Hypertrophic cardiomyopathy (HCM)
KW - Machine learning
KW - Natural language processing (NLP)
UR - http://www.scopus.com/inward/record.url?scp=85107221586&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107221586&partnerID=8YFLogxK
U2 - 10.1115/DMD2021-1076
DO - 10.1115/DMD2021-1076
M3 - Conference contribution
AN - SCOPUS:85107221586
T3 - Proceedings of the 2021 Design of Medical Devices Conference, DMD 2021
BT - Proceedings of the 2021 Design of Medical Devices Conference, DMD 2021
PB - American Society of Mechanical Engineers
T2 - 2021 Design of Medical Devices Conference, DMD 2021
Y2 - 12 April 2021 through 15 April 2021
ER -