Automatic smartphone sensing is a feasible approach for inferring rhythmicity, a key marker of wellbeing for individuals with BD.

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real‐world clinical practice. Relatively few retrospective studies to‐date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

a b s t r a c tIt is increasingly recognised that technology has the potential to significantly improve access, engagement, effectiveness and affordability of treatment for mental health problems. The development of such technology has recently become the subject of Human-Computer Interaction research. As an emerging area with a unique set of constraints and design concerns, there is a need to establish guidelines which encapsulate the knowledge gained from existing development projects. We present an initial set of design guidelines extracted from the literature and from a series of development projects for software to support mental health interventions. The first group of guidelines pertain to the design process itself, addressing the limitations in access to clients in mental healthcare settings, and strategies for collaborative design with therapists. The second group considers major design factors in the development of these technologies, including therapeutic models, client factors, and privacy. The third group concerns conduct of the evaluation process, and the constraints on evaluating mental healthcare technologies. We motivate and explain these guidelines with reference to concrete design projects and problems.

No abstract

Background Designing technologies that users will be interested in, start using, and keep using has long been a challenge. In the health domain, the question of technology acceptance is even more important, as the possible intrusiveness of technologies could lead to patients refusing to even try them. Developers and researchers must address this question not only in the design and evaluation of new health care technologies but also across the different stages of the user’s journey. Although a range of definitions for these stages exists, many researchers conflate related terms, and the field would benefit from a coherent set of definitions and associated measurement approaches. Objective This review aims to explore how technology acceptance is interpreted and measured in mobile health (mHealth) literature. We seek to compare the treatment of acceptance in mHealth research with existing definitions and models, identify potential gaps, and contribute to the clarification of the process of technology acceptance. Methods We searched the PubMed database for publications indexed under the Medical Subject Headings terms “Patient Acceptance of Health Care” and “Mobile Applications.” We included publications that (1) contained at least one of the terms “acceptability,” “acceptance,” “adoption,” “accept,” or “adopt”; and (2) defined the term. The final corpus included 68 relevant studies. Results Several interpretations are associated with technology acceptance, few consistent with existing definitions. Although the literature has influenced the interpretation of the concept, usage is not homogeneous, and models are not adapted to populations with particular needs. The prevalence of measurement by custom surveys suggests a lack of standardized measurement tools. Conclusions Definitions from the literature were published separately, which may contribute to inconsistent usage. A definition framework would bring coherence to the reporting of results, facilitating the replication and comparison of studies. We propose the Technology Acceptance Lifecycle, consolidating existing definitions, articulating the different stages of technology acceptance, and providing an explicit terminology. Our findings illustrate the need for a common definition and measurement framework and the importance of viewing technology acceptance as a staged process, with adapted measurement methods for each stage.