Enabling the adoption of machine learning in clinical decision support: A Total Interpretive Structural Modeling Approach
Ahmad A. Abujaber, Abdulqadir J. Nashwan, Adam Fadlalla
Abstract
It has been reported that the healthcare industry is the slowest adopter of artificial intelligence methods, particularly machine learning (ML), compared to other industries. However, ML can provide unprecedented opportunities for clinical decision-making aid that help improve treatment outcomes and enhance cost-effectiveness. This method paper aims to identify the enablers for adopting ML in supporting clinical decision-making and propose a strategic road map toward boosting the clinicians' intentions to adopt ML as a clinical decision support tool. This paper utilizes the Total Interpretive Structural Modeling (TISM) methodology and the Matrice d'impacts croisés multiplication appliquée á un classment (MICMAC) analysis to investigate the relationships and the interaction between the identified enablers and to develop a hierarchical model that helps policymakers and the other key stakeholders devise the necessary strategies to enhance the adoption of ML in supporting clinical decision making. The paper concludes that building an academic foundation, raising awareness among the clinicians and patients, building trust in machine learning, and enhancing the perceived normative congruence are among the most important enablers for boosting the clinicians' intentions to adopt machine learning in supporting clinical decision making.