Patient portal, User-generated contents, Latent Dirichlet Allocation (LDA), Sentiment analysis, Explanatory analysis, Predictive analytics
Patient portals are positioned as a central component of patient engagement through the potential to change the physician-patient relationship and enable chronic disease self-management. The incorporation of patient portals provides the promise to deliver excellent quality, at optimized costs, while improving the health of the population. This study extends the existing literature by extracting dimensions related to the Mobile Patient Portal Use. We use a topic modeling approach to systematically analyze users’ feedback from the actual use of a common mobile patient portal, Epic's MyChart. Comparing results of Latent Dirichlet Allocation analysis with those of human analysis validated the extracted topics. Practically, the results provide insights into adopting mobile patient portals, revealing opportunities for improvement and to enhance the design of current basic portals. Theoretically, the findings inform the social-technical systems and Task-Technology Fit theories in the healthcare field and emphasize important healthcare structural and social aspects. Further, findings inform the humanization of healthcare framework, support the results of existing studies, and introduce new important design dimensions (i.e., aspects) that influence patient satisfaction and adherence to patient portal.
Digital Object Identifier (DOI)
Al-Ramahi, Mohammad A. and Noteboom, Cherie, "Mining User-generated Content of Mobile Patient Portal: Dimensions of User Experience" (2020). Computer Information Systems Faculty Publications. 3.