@article{KraftBirkReichertetal.2020,
  author    = {Kraft, Robin and Birk, Ferdinand and Reichert, Manfred and Deshpande, Aniruddha and Schlee, Winfried and Langguth, Berthold and Baumeister, Harald and Probst, Thomas and Spiliopoulou, Myra and Pryss, R{\"u}diger},
  title     = {Efficient processing of geospatial mHealth data using a scalable crowdsensing platform},
  series = {Sensors},
  volume    = {20},
  journal   = {Sensors},
  number    = {12},
  issn      = {1424-8220},
  doi       = {10.3390/s20123456},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-207826},
  year      = {2020},
  abstract  = {Smart sensors and smartphones are becoming increasingly prevalent. Both can be used to gather environmental data (e.g., noise). Importantly, these devices can be connected to each other as well as to the Internet to collect large amounts of sensor data, which leads to many new opportunities. In particular, mobile crowdsensing techniques can be used to capture phenomena of common interest. Especially valuable insights can be gained if the collected data are additionally related to the time and place of the measurements. However, many technical solutions still use monolithic backends that are not capable of processing crowdsensing data in a flexible, efficient, and scalable manner. In this work, an architectural design was conceived with the goal to manage geospatial data in challenging crowdsensing healthcare scenarios. It will be shown how the proposed approach can be used to provide users with an interactive map of environmental noise, allowing tinnitus patients and other health-conscious people to avoid locations with harmful sound levels. Technically, the shown approach combines cloud-native applications with Big Data and stream processing concepts. In general, the presented architectural design shall serve as a foundation to implement practical and scalable crowdsensing platforms for various healthcare scenarios beyond the addressed use case.},
  language  = {en}
}
@article{KraftSchleeStachetal.2020,
  author    = {Kraft, Robin and Schlee, Winfried and Stach, Michael and Reichert, Manfred and Langguth, Berthold and Baumeister, Harald and Probst, Thomas and Hannemann, Ronny and Pryss, R{\"u}diger},
  title     = {Combining Mobile Crowdsensing and Ecological Momentary Assessments in the Healthcare Domain},
  series = {Frontiers in Neuroscience},
  volume    = {14},
  journal   = {Frontiers in Neuroscience},
  number    = {164},
  issn      = {1662-453X},
  doi       = {10.3389/fnins.2020.00164},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-200220},
  year      = {2020},
  abstract  = {The increasing prevalence of smart mobile devices (e.g., smartphones) enables the combined use of mobile crowdsensing (MCS) and ecological momentary assessments (EMA) in the healthcare domain. By correlating qualitative longitudinal and ecologically valid EMA assessment data sets with sensor measurements in mobile apps, new valuable insights about patients (e.g., humans who suffer from chronic diseases) can be gained. However, there are numerous conceptual, architectural and technical, as well as legal challenges when implementing a respective software solution. Therefore, the work at hand (1) identifies these challenges, (2) derives respective recommendations, and (3) proposes a reference architecture for a MCS-EMA-platform addressing the defined recommendations. The required insights to propose the reference architecture were gained in several large-scale mHealth crowdsensing studies running for many years and different healthcare questions. To mention only two examples, we are running crowdsensing studies on questions for the tinnitus chronic disorder or psychological stress. We consider the proposed reference architecture and the identified challenges and recommendations as a contribution in two respects. First, they enable other researchers to align our practical studies with a baseline setting that can satisfy the variously revealed insights. Second, they are a proper basis to better compare data that was gathered using MCS and EMA. In addition, the combined use of MCS and EMA increasingly requires suitable architectures and associated digital solutions for the healthcare domain.},
  language  = {en}
}
@article{UnnikrishnanSchleicherShahetal.2020,
  author    = {Unnikrishnan, Vishnu and Schleicher, Miro and Shah, Yash and Jamaludeen, Noor and Pryss, Ruediger and Schobel, Johannes and Kraft, Robin and Schlee, Winfried and Spiliopoulou, Myra},
  title     = {The effect of non-personalised tips on the continued use of self-monitoring mHealth applications},
  series = {Brain Sciences},
  volume    = {10},
  journal   = {Brain Sciences},
  number    = {12},
  issn      = {2076-3425},
  doi       = {10.3390/brainsci10120924},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-219435},
  year      = {2020},
  abstract  = {Chronic tinnitus, the perception of a phantom sound in the absence of corresponding stimulus, is a condition known to affect patients' quality of life. Recent advances in mHealth have enabled patients to maintain a 'disease journal' of ecologically-valid momentary assessments, improving patients' own awareness of their disease while also providing clinicians valuable data for research. In this study, we investigate the effect of non-personalised tips on patients' perception of tinnitus, and on their continued use of the application. The data collected from the study involved three groups of patients that used the app for 16 weeks. Groups A \& Y were exposed to feedback from the start of the study, while group B only received tips for the second half of the study. Groups A and Y were run by different supervisors and also differed in the number of hospital visits during the study. Users of Group A and B underwent assessment at baseline, mid-study, post-study and follow-up, while users of group Y were only assessed at baseline and post-study. It is seen that the users in group B use the app for longer, and also more often during the day. The answers of the users to the Ecological Momentary Assessments are seen to form clusters where the degree to which the tinnitus distress depends on tinnitus loudness varies. Additionally, cluster-level models were able to predict new unseen data with better accuracy than a single global model. This strengthens the argument that the discovered clusters really do reflect underlying patterns in disease expression.},
  language  = {en}
}