TY - JOUR
T1 - Understanding the patient perspective of epilepsy treatment through text mining of online patient support groups
AU - He, Kai
AU - Hong, Na
AU - Lapalme-Remis, Samuel
AU - Lan, Yangyang
AU - Huang, Ming
AU - Li, Chen
AU - Yao, Lixia
N1 - Funding Information:
Funding for this study for Mayo Clinic authors were provided by the Center for Clinical and Translational Science, Mayo Clinic ( UL1TR002377 ) from the National Institutes of Health/National Center for Advancing Translational Sciences and the National Library of Medicine ( 5K01LM012102 ).
Funding Information:
Funding for this study for Mayo Clinic authors were provided by the Center for Clinical and Translational Science, Mayo Clinic (UL1TR002377) from the National Institutes of Health/National Center for Advancing Translational Sciences and the National Library of Medicine (5K01LM012102).Funding for this study for Xi'an Jiaotong University authors were provided by The Fundamental Theory and Applications of Big Data with Knowledge Engineering (2016YFB1000903), Project of China Knowledge Centre for Engineering Science and Technology, Innovation team of Ministry of Education of China (IRT-17R86), Innovative Research Group of the National Natural Science Foundation of China (61721002), Ministry of Education-Research Foundation of China Mobile Communication Corp (MCM20160404), and National Science Foundation of China (6177051795).
Funding Information:
Funding for this study for Xi'an Jiaotong University authors were provided by The Fundamental Theory and Applications of Big Data with Knowledge Engineering ( 2016YFB1000903 ), Project of China Knowledge Centre for Engineering Science and Technology , Innovation team of Ministry of Education of China ( IRT-17R86 ), Innovative Research Group of the National Natural Science Foundation of China ( 61721002 ), Ministry of Education-Research Foundation of China Mobile Communication Corp ( MCM20160404 ), and National Science Foundation of China ( 6177051795 ).
Publisher Copyright:
© 2019 The Authors
PY - 2019/5
Y1 - 2019/5
N2 - Objective: Epilepsy is among the most common chronic neurologic diseases. There is a need for more data on patient perspectives of treatment to guide patient-centered care initiatives. Patients with epilepsy share their experiences on social media anonymously, but little is known about those discussions. Our aim was to learn what patients with epilepsy discuss regarding their condition and identify treatment-related themes from online patient support groups. Methods: A total of 355,838 posts were collected from three online support groups for patients with epilepsy through a crawling script, and an analytical pipeline was built to identify patient conversation content through leveraging of multiple text mining methods. Results were also displayed by network visualization methods. Results: Patients with epilepsy sought information about medical treatments, shared their treatment experiences, and sought help from other posters. Key themes related to treatments included the search for optimal personalized treatment strategies as well as identifying and coping with adverse effects. Significance: This study showed the feasibility of learning about concerns of patients with epilepsy, especially treatment issues, through text mining methods. However, some manual selection and filtering were necessary to ensure quality results for the treatment analysis. Providers should be aware of online discussions and use analyses of such discussions to help guide effective patient engagement during care.
AB - Objective: Epilepsy is among the most common chronic neurologic diseases. There is a need for more data on patient perspectives of treatment to guide patient-centered care initiatives. Patients with epilepsy share their experiences on social media anonymously, but little is known about those discussions. Our aim was to learn what patients with epilepsy discuss regarding their condition and identify treatment-related themes from online patient support groups. Methods: A total of 355,838 posts were collected from three online support groups for patients with epilepsy through a crawling script, and an analytical pipeline was built to identify patient conversation content through leveraging of multiple text mining methods. Results were also displayed by network visualization methods. Results: Patients with epilepsy sought information about medical treatments, shared their treatment experiences, and sought help from other posters. Key themes related to treatments included the search for optimal personalized treatment strategies as well as identifying and coping with adverse effects. Significance: This study showed the feasibility of learning about concerns of patients with epilepsy, especially treatment issues, through text mining methods. However, some manual selection and filtering were necessary to ensure quality results for the treatment analysis. Providers should be aware of online discussions and use analyses of such discussions to help guide effective patient engagement during care.
KW - Epilepsy treatment
KW - Patient concern
KW - Social media
KW - Text mining
UR - http://www.scopus.com/inward/record.url?scp=85062900115&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062900115&partnerID=8YFLogxK
U2 - 10.1016/j.yebeh.2019.02.002
DO - 10.1016/j.yebeh.2019.02.002
M3 - Article
C2 - 30893617
AN - SCOPUS:85062900115
SN - 1525-5050
VL - 94
SP - 65
EP - 71
JO - Epilepsy and Behavior
JF - Epilepsy and Behavior
ER -