Comparing Decentralized Learning Methods for Health Data Models to Nondecentralized Alternatives: Protocol for a Systematic Review.

BACKGROUND: Considering the soaring health-related costs directed toward a growing, aging, and comorbid population, the health sector needs effective data-driven interventions while managing rising care costs. While health interventions using data mining have become more robust and adopted, they often demand high-quality big data. However, growing privacy concerns have hindered large-scale data sharing. In parallel, recently introduced legal instruments require complex implementations, especially when it comes to biomedical data. New privacy-preserving technologies, such as decentralized learning, make it possible to create health models without mobilizing data sets by using distributed computation principles. Several multinational partnerships, including a recent agreement between the United States and the European Union, are adopting these techniques for next-generation data science. While these approaches are promising, there is no clear and robust evidence synthesis of health care applications. OBJECTIVE: The main aim is to compare the performance among health data models (eg, automated diagnosis and mortality prediction) developed using decentralized learning approaches (eg, federated and blockchain) to those using centralized or local methods. Secondary aims are comparing the privacy compromise and resource use among model architectures. METHODS: We will conduct a systematic review using the first-ever registered research protocol for this topic following a robust search methodology, including several biomedical and computational databases. This work will compare health data models differing in development architecture, grouping them according to their clinical applications. For reporting purposes, a PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 flow diagram will be presented. CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies)-based forms will be used for data extraction and to assess the risk of bias, alongside PROBAST (Prediction Model Risk of Bias Assessment Tool). All effect measures in the original studies will be reported. RESULTS: The queries and data extractions are expected to start on February 28, 2023, and end by July 31, 2023. The research protocol was registered with PROSPERO, under the number 393126, on February 3, 2023. With this protocol, we detail how we will conduct the systematic review. With that study, we aim to summarize the progress and findings from state-of-the-art decentralized learning models in health care in comparison to their local and centralized counterparts. Results are expected to clarify the consensuses and heterogeneities reported and help guide the research and development of new robust and sustainable applications to address the health data privacy problem, with applicability in real-world settings. CONCLUSIONS: We expect to clearly present the status quo of these privacy-preserving technologies in health care. With this robust synthesis of the currently available scientific evidence, the review will inform health technology assessment and evidence-based decisions, from health professionals, data scientists, and policy makers alike. Importantly, it should also guide the development and application of new tools in service of patients' privacy and future research. TRIAL REGISTRATION: PROSPERO 393126; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=393126. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/45823.

Mental Health Professionals' Attitudes Toward Digital Mental Health Apps and Implications for Adoption in Portugal: Mixed Methods Study.

BACKGROUND: Digital health apps are among the most visible facets of the ongoing digital transition in health care, with mental health-focused apps as one of the main therapeutic areas. However, concerns regarding their scientific robustness drove regulators to establish evaluation procedures, with Germany's Digitale Gesundheitsanwendungen program pioneering in app prescription with costs covered by statutory health insurance. Portugal gathers a set of conditions and requirements that position it as an excellent test bed for digital health apps. Its daunting mental health landscape reinforces the potential interest in new interventions. To understand if they would be acceptable, we need to understand the supply side's attitudes and perceptions toward them, that is, those of psychiatrists and psychologists. OBJECTIVE: This study aims to understand the attitudes and expectations of psychiatrists and psychologists toward digital mental health apps (DMHAs) in the Portuguese context, as well as perceived benefits, barriers, and actions to support their adoption. METHODS: We conducted a 2-stage sequential mixed methods study. Stage 1 consisted of a cross-sectional web survey adapted to the Portuguese context that was delivered to mental health professionals and psychologists. Stage 2 complemented the insights of the web survey results with a key opinion leader analysis. RESULTS: A total of 160 complete survey responses were recorded, most of which were from psychologists. This is the most extensive study on mental health professionals' attitudes and perceptions of DMHAs in Portugal. A total of 87.2% (136/156) of the respondents supported the opportunity to prescribe DMHAs. Increased health literacy (139/160, 86.9%), wider adherence to treatment (137/160, 85.6%), and proper disease management (127/160, 79.4%) were the most frequently agreed upon benefits of DMHAs. However, only less than half (68/156, 43.6%) of the respondents planned to prescribe or recommend DMHAs, with psychologists being more favorable than psychiatrists. Professionals faced substantial barriers, such as a lack of information on DMHAs (154/160, 96.3%), the level of initial training effort (115/160, 71.9%), and the need for adjustments of clinical processes and records (113/160, 70.6%). Professionals reported that having more information on the available apps and their suitability for health objectives (151/160, 94.4%), more scientific evidence of the validity of the apps as a health intervention (147/160, 91.9%), and established recommendations of apps by specific clinical guidelines or professional societies (145/160, 90.6%) would be essential to foster adoption. CONCLUSIONS: More information about DMHAs regarding their clinical validity and how they work is necessary so that such an intervention can be adopted in Portugal. Recommendations from professional and scientific societies, as well as from governmental bodies, are strongly encouraged. Although the benefits of and the barriers to using these apps are consensual, more evidence, along with further promotion of mental health professionals' digital literacy, is needed. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/41040.

Rethinking Anatomy: How to Overcome Challenges of Medical Education's Evolution.

INTRODUCTION: Due to scientific and technological development, Medical Education has been readjusting its focus and strategies. Medical curriculum has been adopting a vertical integration model, in which basic and clinical sciences coexist during medical instruction. This context favours the introduction of new complementary technology-based pedagogical approaches. Thus, even traditional core sciences of medical curriculum, like Anatomy, are refocusing their teaching/learning paradigm. MATERIAL AND METHODS: We performed a bibliographic review aiming to reflect on Medical Education's current pedagogical trend, by analysing the advantages of the introduction and diversification of pedagogical approaches in Anatomy Education. RESULTS: Anatomy Education's status quo is characterized by: less available teaching time, increasing demands from radiology and endoscopy imaging and other invasive and non-invasive medical techniques, increasing number of medical students and other logistical restrains exposed by the current Medical Education scenario. The traditional learning approach, mainly based on cadaveric dissection, is drifting to complementary newer technologies - such as 3D models or 2D/3D digital imaging - to examine the anatomy of the human body. Also, knowledge transfer is taking different channels, as learning management systems, social networks and computer-assisted learning and assessment are assuming relevant roles. DISCUSSION: The future holds promising approaches for education models. The development of Artificial Intelligence, Virtual Reality and Learning Analytics could provide analytic tools towards a real-time and personalized learning process. CONCLUSION: A reflection on Anatomy Education, as a comprehensive model, allows us to understand Medical Education's complexity. Therefore, the present Medical Education context favours a blended learning approach, in which multi-modality pedagogical strategies may become the landmark.

Introdução: A Educação Médica, face ao desenvolvimento científico e tecnológico, reajustou o enfoque. Progressivamente, o programa curricular em Medicina tem adotado o modelo vertical. Neste modelo, ciências básicas e clínicas coexistem ao longo da formação médica. Este contexto favorece a introdução de novas abordagens pedagógicas de base tecnológica. De facto, áreas de conhecimento tradicionais, como Anatomia, igualmente refocalizaram o seu paradigma de ensino. Material e Métodos: Nesse sentido, realizamos uma revisão bibliográfica com objetivo de refletir a tendência pedagógica atual da Educação Médica, analisando as vantagens da introdução/diversificação de abordagens pedagógicas em Anatomia. Resultados: O status quo da Anatomia é caracterizado por menor tempo disponível para o ensino, pela expansão da imagiologia radiológica e endoscópica, bem como, de outras técnicas médicas invasivas/não-invasivas, pelo aumento do número de estudantes e por restrições logísticas inerentes ao presente contexto da Educação Médica. A abordagem pedagógica tradicional, alicerçada na disseção cadavérica, vem sendo complementada por novas tecnologias auxiliares (modelos 3D ou imagiologia digital 2D/3D) ao estudo anatómico. Também, a transmissão de conhecimento vem adotando diferentes vias. Assim, os Sistemas Gestores de Aprendizagem, redes sociais ou plataformas de aprendizagem/avaliação virtuais assumem papéis relevantes. Discussão: O futuro reserva metodologias educativas promissoras. O desenvolvimento de Inteligência Artificial, da Realidade Virtual e a aplicação dos princípios de Learning Analytics favorece a disponibilização de ferramentas analíticas ao processo de aprendizagem em tempo-real, personalizando-o. Conclusão: A reflexão sobre a Educação em Anatomia, como modelo compreensivo, permite perceber a complexidade da Educação Médica. Assim, o presente contexto favorece a perspectiva de blended learning, sustentada em estratégias pedagógicas multimodais.