TY - JOUR
T1 - Automated detection of sudden unexpected death in epilepsy risk factors in electronic medical records using natural language processing
AU - Barbour, Kristen
AU - Hesdorffer, Dale C.
AU - Tian, Niu
AU - Yozawitz, Elissa G.
AU - McGoldrick, Patricia E.
AU - Wolf, Steven
AU - McDonough, Tiffani L.
AU - Nelson, Aaron
AU - Loddenkemper, Tobias
AU - Basma, Natasha
AU - Johnson, Stephen B.
AU - Grinspan, Zachary M.
N1 - Publisher Copyright:
Wiley Periodicals, Inc. © 2019 International League Against Epilepsy
PY - 2019/6
Y1 - 2019/6
N2 - Objective: Sudden unexpected death in epilepsy (SUDEP) is an important cause of mortality in epilepsy. However, there is a gap in how often providers counsel patients about SUDEP. One potential solution is to electronically prompt clinicians to provide counseling via automated detection of risk factors in electronic medical records (EMRs). We evaluated (1) the feasibility and generalizability of using regular expressions to identify risk factors in EMRs and (2) barriers to generalizability. Methods: Data included physician notes for 3000 patients from one medical center (home) and 1000 from five additional centers (away). Through chart review, we identified three SUDEP risk factors: (1) generalized tonic–clonic seizures, (2) refractory epilepsy, and (3) epilepsy surgery candidacy. Regular expressions of risk factors were manually created with home training data, and performance was evaluated with home test and away test data. Performance was evaluated by sensitivity, positive predictive value, and F-measure. Generalizability was defined as an absolute decrease in performance by <0.10 for away versus home test data. To evaluate underlying barriers to generalizability, we identified causes of errors seen more often in away data than home data. To demonstrate how small revisions can improve generalizability, we removed three “boilerplate” standard text phrases from away notes and repeated performance. Results: We observed high performance in home test data (F-measure range = 0.86-0.90), and low to high performance in away test data (F-measure range = 0.53-0.81). After removing three boilerplate phrases, away performance improved (F-measure range = 0.79-0.89) and generalizability was achieved for nearly all measures. The only significant barrier to generalizability was use of boilerplate phrases, causing 104 of 171 errors (61%) in away data. Significance: Regular expressions are a feasible and probably a generalizable method to identify variables related to SUDEP risk. Our methods may be implemented to create large patient cohorts for research and to generate electronic prompts for SUDEP counseling.
AB - Objective: Sudden unexpected death in epilepsy (SUDEP) is an important cause of mortality in epilepsy. However, there is a gap in how often providers counsel patients about SUDEP. One potential solution is to electronically prompt clinicians to provide counseling via automated detection of risk factors in electronic medical records (EMRs). We evaluated (1) the feasibility and generalizability of using regular expressions to identify risk factors in EMRs and (2) barriers to generalizability. Methods: Data included physician notes for 3000 patients from one medical center (home) and 1000 from five additional centers (away). Through chart review, we identified three SUDEP risk factors: (1) generalized tonic–clonic seizures, (2) refractory epilepsy, and (3) epilepsy surgery candidacy. Regular expressions of risk factors were manually created with home training data, and performance was evaluated with home test and away test data. Performance was evaluated by sensitivity, positive predictive value, and F-measure. Generalizability was defined as an absolute decrease in performance by <0.10 for away versus home test data. To evaluate underlying barriers to generalizability, we identified causes of errors seen more often in away data than home data. To demonstrate how small revisions can improve generalizability, we removed three “boilerplate” standard text phrases from away notes and repeated performance. Results: We observed high performance in home test data (F-measure range = 0.86-0.90), and low to high performance in away test data (F-measure range = 0.53-0.81). After removing three boilerplate phrases, away performance improved (F-measure range = 0.79-0.89) and generalizability was achieved for nearly all measures. The only significant barrier to generalizability was use of boilerplate phrases, causing 104 of 171 errors (61%) in away data. Significance: Regular expressions are a feasible and probably a generalizable method to identify variables related to SUDEP risk. Our methods may be implemented to create large patient cohorts for research and to generate electronic prompts for SUDEP counseling.
KW - electronic health records
KW - generalized tonic–clonic seizures
KW - natural language processing
KW - patient education
KW - sudden unexpected death in epilepsy
UR - http://www.scopus.com/inward/record.url?scp=85066128201&partnerID=8YFLogxK
U2 - 10.1111/epi.15966
DO - 10.1111/epi.15966
M3 - Article
C2 - 31111463
AN - SCOPUS:85066128201
SN - 0013-9580
VL - 60
SP - 1209
EP - 1220
JO - Epilepsia
JF - Epilepsia
IS - 6
ER -