FROM DETECTION TO DETOX: A HYBRID MODEL OF MACHINE LEARNING AND BIBLIOTHERAPY IN DIGITAL DEMENTIA CARE

Abstract

            The increasing prevalence of digital dementia among Generation Z underscores the need for hybrid frameworks that combine technological innovation with humanities-based interventions. This paper proposes a two-step model:  Detection through machine learning algorithms analysing digital behavior patterns such as smartphone usage logs, app-switching, and typing speed; and Detox through bibliotherapy interventions designed to improve memory, reflective thinking, and mindful screen use. By situating this model within the bio-psycho-socio approachand aligning it with theAttitude, Ethics, and Communication (AETCOM) module in medical education, the study illustrates a multidisciplinary pathway for early detection, prevention, and management of digital dementia. The hybrid model bridges the gap between computational detection tools and therapeutic, non-pharmacological interventions, contributing to the global discourse on digital health and medical humanities.