Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: May 18, 2018
Open Peer Review Period: May 19, 2018 - Jun 21, 2018
Date Accepted: Aug 10, 2018
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Identification of Primary Medication Concerns Regarding Thyroid Hormone Replacement Therapy From Online Patient Medication Reviews: Text Mining of Social Network Data
Background:
Patients with hypothyroidism report poor health-related quality of life despite having undergone thyroid hormone replacement therapy (THRT). Understanding patient concerns regarding levothyroxine can help improve the treatment outcomes of THRT.
Objective:
This study aimed to (1) identify the distinctive themes in patient concerns regarding THRT, (2) determine whether patients have unique primary medication concerns specific to their demographics, and (3) determine the predictability of primary medication concerns on patient treatment satisfaction.
Methods:
We collected patient reviews from WebMD in the United States (1037 reviews about generic levothyroxine and 1075 reviews about the brand version) posted between September 1, 2007, and January 30, 2017. We used natural language processing to identify the themes of medication concerns. Multiple regression analyses were conducted in order to examine the predictability of the primary medication concerns on patient treatment satisfaction.
Results:
Natural language processing of the patient reviews of levothyroxine posted on a social networking site produced 6 distinctive themes of patient medication concerns related to levothyroxine treatment: how to take the drug, treatment initiation, dose adjustment, symptoms of pain, generic substitutability, and appearance. Patients had different primary medication concerns unique to their gender, age, and treatment duration. Furthermore, treatment satisfaction on levothyroxine depended on what primary medication concerns the patient had.
Conclusions:
Natural language processing of text content available on social media could identify different themes of patient medication concerns that can be validated in future studies to inform the design of tailored medication counseling for improved patient treatment satisfaction.
Citation
Per the author's request the PDF is not available.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.