Editorial: Digital Health Technologies for Shared Decision Making
Current and emerging digital health technologies (DHTs) offer numerous opportunities to support and advance traditional approaches to shared decision making (SDM). The key challenge lies in determining where, when, and how to best utilize DHTs to enhance SDM-related processes and outcomes. This Research Topic “Digital Health Technologies for Shared Decision Making” presents a collection of articles addressing this challenge.
DHTs can help understand, reach, and support patients across their healthcare journey (1–3). Höppchen et al. examine how suitably designed DHTs can improve patient engagement in cardiac rehabilitation. They discuss barriers and facilitators to patient engagement across various healthcare stages, from awareness to SDM, and present implications for DHT design and implementation.
Complex treatment pathways present multiple key moments for SDM, where patient preferences, values, and experiences significantly influence treatment courses (4). Göcking et al. apply patient journey mapping to identify preference-sensitive moments during intensive care treatment. They consider strategic DHT implementation to align patient care with patient needs, values, and preferences.
Patient Decision Aids (PtDAs) are a strategy for facilitating alignment between patient care and patient needs. Sedlokova et al. evaluate analogue and digital PtDAs for depression treatment selection, comparing their strengths and weaknesses in promoting patient engagement in SDM.
Human factors like depression and anxiety influence how patients process information and make decisions, impacting digital health tool design (7). Fanio et al. report on designing a PtDA for anxious patients with atrial fibrillation, incorporating specific features to create a supportive digital environment.
Supporting collaboration between patients and healthcare professionals is crucial for effective SDM (10). Wurhofer et al. examine a digital tool for collaborative planning in cardiac rehabilitation, identifying opportunities to support collaboration before, during, and after SDM.
Artificial intelligence (AI) and DHTs can enhance SDM in various ways. Singh et al. develop and evaluate an interactive approach for integrating patient preferences into SDM consultations, informing the development of an AI-based personalized Health Recommender System. Eiskjaer et al. present a tool using predictive analytics to generate evidence-based insights into treatment options for spinal disorders, personalizing SDM. Lin et al. evaluate an opponent model-based approach to SDM, simulating the interactive process of distilling patient preferences into actionable insights.
The integration of AI-enhanced DHTs in SDM raises ethical challenges. Spitale et al. create AI models to extract and classify patient case reports on assisted suicide, examining the potential and dilemmas of using AI to help physicians navigate complex ethical issues.
In summary, the contributions to this Research Topic aim to develop an evidence-led understanding of how DHTs can facilitate effective SDM support. They highlight the complexities of tailoring DHTs to diverse human factors and integrating them into broader SDM solutions and healthcare practices. Research is needed to form a body of practical design and implementation knowledge about enhancing SDM-related processes and outcomes using DHTs.
