TY - GEN
T1 - Understanding Reasons for Medication Nonadherence
T2 - 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017
AU - Xie, Jiaheng
AU - Zeng, Daniel Dajun
AU - Liu, Xiao
AU - Fang, Xiao
N1 - Funding Information:
This study is supported by National Institutes of Health (grant #1R01DA037378-01) and National Science Foundation (grant #IIS-1553109 and IIS-1552860).
PY - 2018
Y1 - 2018
N2 - Medication nonadherence (MNA) refers to the behavior when patients do not fill prescriptions. To take proactive measures and prevent harmful outcomes, the stakeholders need to understand patients’ reasons for MNA. Current studies attempt to provide one-size-fits-all solutions to the “average patients� and utilize survey or experiment design with small sample sizes to obtain a snapshot of this issue. To address these issues, we develop a semantically enhanced deep learning approach to detecting patient and drug-specific reasons for MNA using health social media data. Our model reached a precision of 86.43%, a recall of 92.53%, and an F1- score of 89.38%. This study contributes to information systems research by designing a deep-learning-based framework for detecting tailored reasons for MNA in real time. The framework is generalizable to understand motivations of various human behaviors. We also contribute to healthcare IT by discovering previously unknown MNA reasons from online health IT platforms.
AB - Medication nonadherence (MNA) refers to the behavior when patients do not fill prescriptions. To take proactive measures and prevent harmful outcomes, the stakeholders need to understand patients’ reasons for MNA. Current studies attempt to provide one-size-fits-all solutions to the “average patients� and utilize survey or experiment design with small sample sizes to obtain a snapshot of this issue. To address these issues, we develop a semantically enhanced deep learning approach to detecting patient and drug-specific reasons for MNA using health social media data. Our model reached a precision of 86.43%, a recall of 92.53%, and an F1- score of 89.38%. This study contributes to information systems research by designing a deep-learning-based framework for detecting tailored reasons for MNA in real time. The framework is generalizable to understand motivations of various human behaviors. We also contribute to healthcare IT by discovering previously unknown MNA reasons from online health IT platforms.
KW - Deep learning
KW - Healthcare information systems
KW - Medication nonadherence
KW - Precision medicine
UR - http://www.scopus.com/inward/record.url?scp=85126503932&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126503932&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85126503932
SN - 9780996683159
T3 - ICIS 2017: Transforming Society with Digital Innovation
BT - ICIS 2017
PB - Association for Information Systems
Y2 - 10 December 2017 through 13 December 2017
ER -