Combining Deep Neural Network and PLS-SEM to Predict Patients’ Continuity with Telemedicine

Abstract

This study aims to adapt the Expectation Disconfirmation Theory and Technology Adoption Model to unveil provocative roles in patients’ satisfaction cognitions and subsequent continuity behaviors pertaining to telemedicine services in rural Bangladesh. A quantitative research model is developed and validated using a two-staged deep neural network and partial least squares structural equation modeling approach. The findings of this study provide evidence that five salient determinants; expectations, disconfirmation, performance, usefulness, and ease of use dominantly contribute to predicting patients’ satisfaction concerning continuity with telemedicine. This contributes to health informatics and behavioral literature by clarifying the complex interplay between patients’ satisfaction and determinants of continuity behavior in telemedicine’s domain. The findings provide novel insights into predictions of complex patients’ attitudes toward telemedicine continuity, and dynamic changes in adoption trends thereby assisting health professionals, global health experts, policymakers, and IS community in making higher quality informed decisions for people-centered future models of care.