External authors:

• Monica Stambuk Castellano ( Pontificia Universidad Catolica de Chile )
• Ignacio Contreras-McKay ( Pontificia Universidad Catolica de Chile )
• Emilio Farfan ( Pontificia Universidad Catolica de Chile )
• Oscar Inzunza ( Pontificia Universidad Catolica de Chile )
• Nicolas E. Ottone ( Universidad de La Frontera )
• Mariano del Sol ( Universidad de La Frontera )
• Carlos Alario-Hoyo ( Universidad Carlos III de Madrid )
• Macarena Soto Alvarado ( Pontificia Universidad Catolica de Chile )
• R. Shane Tubbs ( University of Queensland , Tulane University , Tulane University , Tulane University , Tulane University , St Georges Univ , Ochsner Health System , Ochsner Health System )

Abstract:

Gamification has appeared as an alternative educational methodology to traditional tools. Specifically, in anatomy teaching, multiple technological applications have emerged in response to the difficulties of accessing cadaveric material; however, there is insufficient information about the effects of these applications on the performance achieved by students, or about to the best way to adapt learning to meet their educational needs. In this study, we investigated how teaching human anatomy through a mobile gamified technological tool containing recommendation systems can be combined with a virtual assistant to improve the learning and academic performance of medical students in the Anatomy Department at the Universidad de La Frontera in Temuco, Chile and the Anatomy Department at the Pontificia Universidad Catolica de Chile. In total, 131 students participated in the experiment, which was divided into two case studies. The main findings led to the conclusion that gamified components support students in learning anatomy. In addition, the predictions and recommendations provided by the virtual assistant enabled the academic aspects that the students needed to improve to be extracted adequately. Future work is expected to support adaptive learning by incorporating new artificial intelligence in education elements that can generate personalized scenarios for studying anatomy based on the application.