Editorial: Special Issue on Digital Psychiatry

Abstract

Despite a growing recognition of mental health challenges worldwide, there remains a significant gap between the demand for and the availability of mental health services. The WHO estimates that globally, up to 71% of individuals with severe mental illnesses such as psychosis receive no treatment, and access is even more limited in low-income countries. Barriers such as stigma, resource shortages, and insufficiently trained professionals may exacerbate this issue [1, 2].

Given the limited resources available, a recent report by the World Health Organization stated that “the use of mobile and wireless technologies (mhealth) to support the achievement of health objectives has the potential to transform the face of health service delivery across the globe” [3]. On a global scale, it is not feasible to propose that practices based entirely on in-person care will ever be able to meet the demand and need for treatment. Thus, even before the emergence of the COVID-19 pandemic, there was growing interest in the potential role of new technologies to extend care.

The rapid advancement and integration of technology is transforming mental health care delivery, accessibility, and research methodologies. Digital tools, including wearable devices, telepsychiatric platforms, smartphone apps, virtual reality (VR), and electronic health record data are reshaping the landscape of clinical practice, research, and patient engagement [4]. Similarly, digital phenotyping, artificial intelligence (AI), and advanced machine learning methods offer deeper, real-time insights into patients' behaviors and symptoms, potentially leading to earlier diagnoses, prediction models, and more personalized treatment plans [5, 6]. AI-enabled programs can analyze and contextualize data to provide information or automatically trigger actions without human interference, where machine-learning methods learn insights and recognize patterns from data.

These innovations address critical challenges in mental health care, particularly the pervasive gap between the demand for treatment and the limited capacity of traditional systems to meet this need. Furthermore, digital solutions may empower patients to actively engage in their treatment through tools for self-monitoring, psychoeducation, and immersive, engaging interventions that may enhance their therapeutic experience.

The term “digital phenotyping” has been defined as the “moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices” [7, 8]. Although not unanimous, some authors [9] divide digital phenotyping into two subgroups, called “active data” and “passive data.” Active data refer to data that requires active input from the users to be generated, whereas passive data, such as sensor data and phone usage patterns, are collected without requiring any active participation from the users. In the case of passive data or “objective” data, these data inputs can be seen as digital footprints or data traces arising as a “by-product” from interactions with technology. Self-monitored data (active data) could be collected in a fine-grained manner to promote empowerment and insight into course of illness and potential early warning signs of deterioration. Digital phenotyping refers to approaches in which personal data gathered from mobile devices and sensors is analyzed to provide health information on physiological functions or behavioral indicators [9, 10]. In mental health research, interest in digital phenotyping has increased dramatically during the last years, but attracted great interest when Tom Insel (leader of NIMH until 2015) claimed, that using and exploring further into digital phenotyping has the potential to overcome some of the challenges in mental health [11]. An important aspect of innovative digital intervention tools is the just-in-time adaptive intervention (JITAI), which holds enormous potential for promoting change in behavior. A JITAI covers an intervention design that adapts the provision of support (e.g., the type, content, timing, and frequency) over time to the specific individual [12]. Continuous data streams of digital phenotyping (active and/or passive) enable detection of transitions and potential relapse. By using digital phenotyping of the dynamics of an individual's internal state and context in real time JITAI offers support flexibly [13], enabling micro interventions during the times most needed.

VR is another advancement in mental health care that shows great promise for enhancing non-pharmacological interventions for various mental disorder [14]. By creating highly realistic and immersive environments, VR enables individuals to engage with scenarios designed to evoke cognitive, emotional, behavioral, and physiological responses. This technology offers a safe, controlled setting where individuals can confront and manage symptoms, facilitating therapeutic interventions aimed at improving functioning and quality of life. Through real-time therapist-controlled visual and auditory stimuli, VR allows for highly individualized, gradual, and fine-tuned exposure to distressing triggers. It is generally regarded as a safe intervention with minimal side effects, such as motion sickness or dizziness [15]. Initially employed primarily in the treatment of anxiety disorders, recent research has expanded its application to severe mental illnesses, including schizophrenia spectrum disorders. Studies suggest that VR-based therapies may provide significant benefits for individuals whose symptoms are resistant to pharmacological treatments [16]. Additionally, VR and other digitally based intervention may hold particular appeal for younger patients who are often familiar with and proficient in using digital platforms. This familiarity may enhance their willingness and receptiveness to incorporating digital interventions as part of their treatment. Consequently, these interventions have the potential not only to improve adherence but also expanding access to a broader target group.

While these advancements present promising opportunities, they also underscore the need for robust research to optimize integration into clinical practice. Digital psychiatry stands at the intersection of innovation and necessity, bridging the divide between mental health needs and the capacity of traditional systems to address them effectively.

The manuscripts included in this Special Issue on “Digital Psychiatry” span diverse topics, reflecting the multidisciplinary nature of digital psychiatry. From digital phenotyping methods and advanced methods for data analyses to studies on integrating digital treatment interventions into everyday clinical practice, these contributions underscore the promise of technology to complement and enhance traditional approaches. Some examples of the included manuscripts follow below.

Concerning digital phenotyping, a study by Ambrosen et al. investigated the use of automated computer vision of facial expressions during interviews in 46 patients with first-episode psychosis. Interestingly, they found that facial expressions during interviews were associated with negative symptoms and initial antipsychotic treatment response. Another interesting study by Dalal et al. investigated the application of natural language processing (NLP) to speech samples with the potential elucidate even the most subtle deviations in language in 147 participants including healthy individuals, patients with first-episode psychosis, clinical high-risk state individuals and patients with schizophrenia. They found that patterns of speech deviations in early and established stages of schizophrenia are distinguishable from each other.

Concerning the use of sophisticated data analyses, an interesting study by Eder et al. investigated the use of a transdiagnostic model using and comparing decision tree classifiers, logistic regression, XGboost, and a support vector machine to predict weight gain of ≥ 5% of body weight during the first 4 weeks of treatment with psychotropic drugs in 103 psychiatric inpatients. The study underscored the potential use of electronic health record data in personalizing treatment and follow-up.

Concerning digital interventions, a large-scale study conducted by Alvarez-Jimenez et al. with 5.702 participants examined the effectiveness of a moderated online social therapy platform (blended intervention) within Australian youth mental health services. They found participants to engage consistently with the platform over several weeks and demonstrating significant improvements in depression and anxiety levels. Berkhof et al. explored baseline factors that characterize treatment responders in their study on VR-based cognitive behavioral therapy for patients with paranoia. They found that higher baseline safety behaviors and higher age were associated with better outcomes in reducing social anxiety. This addresses a significant gap in the literature by shedding light on patient characteristics that may predict who benefit most from a novel intervention. A meta-analysis by Zeka et al. investigated the current evidence on immersive VR interventions in treating a wide range of prominent mental health disorders. Their findings highlight the promising potential of VR-interventions in addressing conditions such as alcohol use, schizophrenia, and anxiety, but highlight the need for methodological rigor in future research to enhance reliability of these findings.

By bridging the gap between technological advancements and clinical application, we hope this Special Issue will inspire clinicians and researchers to collaborate and innovate in ways that ensure digital psychiatry reaches its full potential—empowering patients and practitioners alike in improving mental health outcomes.