The PostStroke-Manager - combining mobile, digital and sensor-based technology with personal assistance: protocol of the feasibility study.

INTRODUCTION: Post stroke management has moved into the focus as it represents the only way to secure acute treatment effects in the long term. Due to individual courses, post stroke management appears rather challenging and is hindered by existing barriers between treatment sectors. As a novel concept, the PostStroke-Manager combines digital and sensor-based technology with personal assistance to enable intersectoral cooperation, best possible reduction of stroke-related disability, optimal secondary prevention, and detection of physical and psychological comorbidities. METHODS: This prospective single-center observational study aims to investigate the feasibility of the PostStroke-Manager concept in an outpatient setting. Ninety patients who have suffered an ischemic or hemorrhagic stroke or transient ischemic attack will be equipped with a tablet and mobile devices recording physical activity, blood pressure, and electrocardiographic signals. Through a server-based platform, patients will be connected with the primary care physician, a stroke pilot and, if necessary, other specialists who will use web-based platforms. Via the tablet, patients will have access to an application with 10 newly designed components including, for instance, a communication tool, medication schedule, medical records platform, and psychometric screenings (e.g., depression, anxiety symptoms, quality of life, adherence, cognitive impairment). During the 1-year follow-up period, clinical visits are scheduled at three-month intervals. In the interim, communication will be secured by an appropriate tool that includes text messenger, audio, and video telephony. As the primary endpoint, feasibility will be measured by a 14-item questionnaire that addresses digital components, technical support, and personal assistance. The PostStroke-Manager will be judged feasible if at least 50% of these aspects are rated positively by at least 75% of patients. Secondary endpoints include feedback from professionals and longitudinal analyses on clinical and psychometric parameters. PERSPECTIVE: This study will answer the question of whether combined digital and personal support is a feasible approach to post stroke management. Furthermore, the patient perspective gained regarding digital support may help to specify future applications. This study will also provide information regarding the potential use of remote therapies and mobile devices in situations with limited face-to-face contacts. TRIAL REGISTRATION: German Register for Clinical Trials ( DRKS00023213 .), registered 27 April 2021.

Analysis of Biomedical Longitudinal Multisensor Data: Extracting Interpretable Features by Context* *.

Longitudinal quotidian acquisition of personal data over weeks and months has been increasingly facilitated in the last few years. Smartwatches and smartphones serve as platforms containing a variety of sensors, able to capture a multitude of individual biomedical and behavioral aspects. This development enables new analytic pathways in medicine and health care. Due to data of this type being increasingly ascertainable, efficient analyses become crucial. For instance, determining meaningful, individualized patterns from such multimodal, longitudinal time series can be very time and resource consuming. To this end, interpretable and robust parameters need to be extracted. In this paper, we explore a general approach to context based parameter estimation and illustrate its ability to be utilized for determining individualized and interpretable biosignal and behavioral patterns.

Analysis of Physiological and Activity Data Specific to Locations Obtained through Geographical Clustering.

This paper presents methods for the investigation and visualization of spatial, physical and physiological data acquired by wearable sensors. Several clustering methods and descriptive statistics are combined. Based on graph theory, an individual network was constructed depending on daily physiological and activity data. By using such networks, clusters and day-to-day differences can be utilized to present physiological status and activity. One possible application is the usage of these subject-specific location and activity based influences in diagnostic and therapy such as of cardiac diseases.