TY - JOUR
T1 - Assessment of Natural Language Processing Methods for Ascertaining the Expanded Disability Status Scale Score From the Electronic Health Records of Patients With Multiple Sclerosis
T2 - Algorithm Development and Validation Study
AU - Yang, Zhen
AU - Pou-Prom, Chloé
AU - Jones, Ashley
AU - Banning, Michaelia
AU - Dai, David
AU - Mamdani, Muhammad
AU - Oh, Jiwon
AU - Antoniou, Tony
N1 - Funding Information:
JO reports grants from MS Society of Canada, The Barford and Love MS Fund of St. Michael’s Hospital Foundation, National MS Society, Brain Canada, Biogen-Idec, Roche, and EMD-Serono; and personal fees for consulting or speaking from Biogen-Idec, EMD-Serono, Roche, Sanofi-Genzyme, Novartis, and Celgene.
Funding Information:
This study was funded by grants from St. Michael’s Hospital Foundation and Li Ka Shing Foundation, and an unrestricted research grant from Roche (Canada).
Publisher Copyright:
© Zhen Yang, Chloé Pou-Prom, Ashley Jones, Michaelia Banning, David Dai, Muhammad Mamdani, Jiwon Oh, Tony Antoniou. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 12.01.2022. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.
PY - 2022/1
Y1 - 2022/1
N2 - Background: The Expanded Disability Status Scale (EDSS) score is a widely used measure to monitor disability progression in people with multiple sclerosis (MS). However, extracting and deriving the EDSS score from unstructured electronic health records can be time-consuming. Objective: We aimed to compare rule-based and deep learning natural language processing algorithms for detecting and predicting the total EDSS score and EDSS functional system subscores from the electronic health records of patients with MS. Methods: We studied 17,452 electronic health records of 4906 MS patients followed at one of Canada’s largest MS clinics between June 2015 and July 2019. We randomly divided the records into training (80%) and test (20%) data sets, and compared the performance characteristics of 3 natural language processing models. First, we applied a rule-based approach, extracting the EDSS score from sentences containing the keyword “EDSS.” Next, we trained a convolutional neural network (CNN) model to predict the 19 half-step increments of the EDSS score. Finally, we used a combined rule-based–CNN model. For each approach, we determined the accuracy, precision, recall, and F-score compared with the reference standard, which was manually labeled EDSS scores in the clinic database. Results: Overall, the combined keyword-CNN model demonstrated the best performance, with accuracy, precision, recall, and an F-score of 0.90, 0.83, 0.83, and 0.83 respectively. Respective figures for the rule-based and CNN models individually were 0.57, 0.91, 0.65, and 0.70, and 0.86, 0.70, 0.70, and 0.70. Because of missing data, the model performance for EDSS subscores was lower than that for the total EDSS score. Performance improved when considering notes with known values of the EDSS subscores. Conclusions: A combined keyword-CNN natural language processing model can extract and accurately predict EDSS scores from patient records. This approach can be automated for efficient information extraction in clinical and research settings.
AB - Background: The Expanded Disability Status Scale (EDSS) score is a widely used measure to monitor disability progression in people with multiple sclerosis (MS). However, extracting and deriving the EDSS score from unstructured electronic health records can be time-consuming. Objective: We aimed to compare rule-based and deep learning natural language processing algorithms for detecting and predicting the total EDSS score and EDSS functional system subscores from the electronic health records of patients with MS. Methods: We studied 17,452 electronic health records of 4906 MS patients followed at one of Canada’s largest MS clinics between June 2015 and July 2019. We randomly divided the records into training (80%) and test (20%) data sets, and compared the performance characteristics of 3 natural language processing models. First, we applied a rule-based approach, extracting the EDSS score from sentences containing the keyword “EDSS.” Next, we trained a convolutional neural network (CNN) model to predict the 19 half-step increments of the EDSS score. Finally, we used a combined rule-based–CNN model. For each approach, we determined the accuracy, precision, recall, and F-score compared with the reference standard, which was manually labeled EDSS scores in the clinic database. Results: Overall, the combined keyword-CNN model demonstrated the best performance, with accuracy, precision, recall, and an F-score of 0.90, 0.83, 0.83, and 0.83 respectively. Respective figures for the rule-based and CNN models individually were 0.57, 0.91, 0.65, and 0.70, and 0.86, 0.70, 0.70, and 0.70. Because of missing data, the model performance for EDSS subscores was lower than that for the total EDSS score. Performance improved when considering notes with known values of the EDSS subscores. Conclusions: A combined keyword-CNN natural language processing model can extract and accurately predict EDSS scores from patient records. This approach can be automated for efficient information extraction in clinical and research settings.
KW - Machine learning
KW - Multiple sclerosis
KW - Natural language processing
UR - http://www.scopus.com/inward/record.url?scp=85123022174&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123022174&partnerID=8YFLogxK
U2 - 10.2196/25157
DO - 10.2196/25157
M3 - Article
C2 - 35019849
AN - SCOPUS:85123022174
SN - 2291-9694
VL - 10
JO - JMIR Medical Informatics
JF - JMIR Medical Informatics
IS - 1
M1 - e25157
ER -