Exploring experiences of Faculty of Health Sciences students on interprofessional collaboration in the healthcare settings in the Khomas region, Namibia.

In contemporary society, the persistent intensification of social pressure and the acceleration of life rhythms have elevated mental health issues to a primary global concern. Mental health disorders are now highly prevalent worldwide, with an estimated 1 billion individuals living with mental disorders; among these, anxiety and depression are recognised as the most common conditions (WHO, ). According to the World Health Organization (WHO), depression currently affects an estimated 280 million people worldwide, representing 5% of all adults and 5.7% of adults aged 60 years and older (WHO, ). Furthermore, the WHO projects that by 2030, depression will rank as the leading cause of the global disease burden, underscoring the urgent need for scalable clinical interventions (Mathers & Loncar, ). Additionally, data from the WHO indicate a global prevalence of mental disorders of approximately 14% among adolescents (aged 10–19 years) (WHO, ). These conditions not only severely impair individuals’ quality of life but also pose substantial threats to social stability and economic development. At the individual level, these conditions disrupt critical psychosocial development, leading to emotional difficulties, diminished social adaptability, and reduced academic or employment prospects (Duggal & Bagasrawala, ; Stelmach et al., ). Societally, untreated mental health issues severely impair social functioning and escalate the risk of antisocial behaviours, such as substance abuse (Burns & Birrell, ). Moreover, this crisis imposes a substantial financial burden through significant medical costs and immense pressure on public sectors (Ziebold et al., ). Collectively, these cascading developmental, societal, and economic impacts underscore the urgent need for targeted interventions. However, despite this escalating demand, traditional mental health services are frequently hindered by severe resource constraints, uneven accessibility, and enduring social stigma, creating a significant gap between patient needs and service delivery. From a structural perspective, pervasive financial constraints within the mental health sector directly undermine the availability of essential resources, infrastructure, and medications (Essien & Asamoah, ). Consequently, in low- and middle-income countries (LMICs) and underserved regions, many healthcare facilities fundamentally lack the necessary infrastructure to deliver effective care (Atewologun et al., ; Essien & Asamoah, ). Simultaneously, the crisis of human resource shortages is equally severe, particularly in LMICs; there is a substantial global deficit of trained mental health professionals, a predicament further exacerbated by inadequate training opportunities and suboptimal workforce management (Atewologun et al., ). Beyond these systemic infrastructural and human resource constraints, the social stigma surrounding mental illness deters individuals from actively seeking help, thereby further widening the real-world treatment gap (Qin & Hsieh, ). Against this backdrop, Artificial Intelligence (AI) has emerged as a transformative solution to bridge this gap, fundamentally reshaping multiple domains of mental health care. Specifically, AI applications have expanded across diverse clinical domains, including diagnosis, treatment selection, active intervention, and the prediction of treatment outcomes. First, in diagnosis, Natural Language Processing (NLP) techniques are increasingly employed for sentiment analysis to assist in early depression screening (Kumar et al., ). Second, regarding treatment selection, machine learning algorithms are utilised to analyse clinical data and formulate personalised treatment plans (Khude & Shende, ). Third, in active intervention, emotionally intelligent conversational agents are being investigated for delivering tailored cognitive-behavioural support (Manole et al., ). Finally, for the prediction of treatment outcomes, advanced machine learning frameworks demonstrate significant potential in anticipating patient responses to specific therapies, thereby minimising traditional trial-and-error approaches (Karpiel et al., ). However, the rapid and diverse proliferation of these specific clinical applications has paradoxically created a highly fragmented knowledge base. Because AI is being simultaneously deployed across such disparate domains, the global literature has expanded exponentially but often in isolated silos.