Popis: |
Medical rehabilitation face the ongoing challenge of designing the initiation and implementation of measures in needs-based manner [1–4]. In this context, diagnostic results serve as a basis for treatment planning, process and outcome measurement, and quality assurance [5,6]. However, there is a growing demand for more economical and resource-saving assessments to optimize the quality and acceptance of diagnostics [1]. Traditional patient-reported outcome measurements (PROMs) have inherent limitations, including potential sources of bias [7]. PROMs rely on self-reported information from patients, which can be influenced by subjective perceptions, recall bias, and social desirability bias [7–11]. This introduces a level of subjectivity and potential inaccuracy into the measurement process. Furthermore, the dynamics and fluctuations of mental states and disorders [12] cannot be depicted by singular or irregular measurements, which is often the case for classical PROMs. To overcome these limitations, there is a need for objective and fine-grained measurements that are ideally passive and unobtrusive. In this regard, smart sensing or digital phenotyping approaches have the potential to make a significant contribution to future healthcare [13,14]. Smart sensing or digital phenotyping involves utilizing sensor data from digital devices, such as smartphones or smartwatches, to infer the health status of an individual [15–19]. First studies show promising results in terms of monitoring and predicting symptoms while minimizing the burden on patients [17,19–26]. By continuously monitoring health parameters, smart sensing has the potential to provide valuable additions to monitoring systems, early warning mechanisms, and decision support systems [13]. The present study investigates the extent to which smart sensing is suitable for assessing mental health in a medical rehabilitation aftercare setting. |