@article{DavidsonDuekingZinneretal.2020,
  author    = {Davidson, Padraig and D{\"u}king, Peter and Zinner, Christoph and Sperlich, Billy and Hotho, Andreas},
  title     = {Smartwatch-Derived Data and Machine Learning Algorithms Estimate Classes of Ratings of Perceived Exertion in Runners: A Pilot Study},
  series = {Sensors},
  volume    = {20},
  journal   = {Sensors},
  number    = {9},
  issn      = {1424-8220},
  doi       = {10.3390/s20092637},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205686},
  year      = {2020},
  abstract  = {The rating of perceived exertion (RPE) is a subjective load marker and may assist in individualizing training prescription, particularly by adjusting running intensity. Unfortunately, RPE has shortcomings (e.g., underreporting) and cannot be monitored continuously and automatically throughout a training sessions. In this pilot study, we aimed to predict two classes of RPE (≤15 "Somewhat hard to hard" on Borg's 6-20 scale vs. RPE >15 in runners by analyzing data recorded by a commercially-available smartwatch with machine learning algorithms. Twelve trained and untrained runners performed long-continuous runs at a constant self-selected pace to volitional exhaustion. Untrained runners reported their RPE each kilometer, whereas trained runners reported every five kilometers. The kinetics of heart rate, step cadence, and running velocity were recorded continuously ( 1 Hz ) with a commercially-available smartwatch (Polar V800). We trained different machine learning algorithms to estimate the two classes of RPE based on the time series sensor data derived from the smartwatch. Predictions were analyzed in different settings: accuracy overall and per runner type; i.e., accuracy for trained and untrained runners independently. We achieved top accuracies of 84.8 \% for the whole dataset, 81.8 \% for the trained runners, and 86.1 \% for the untrained runners. We predict two classes of RPE with high accuracy using machine learning and smartwatch data. This approach might aid in individualizing training prescriptions.},
  language  = {en}
}
@article{MeierKaehlerBergenetal.2020,
  author    = {Meier, Sandra M. and K{\"a}hler, Anna K. and Bergen, Sarah E. and Sullivan, Patrick F. and Hultman, Christina M. and Mattheisen, Manuel},
  title     = {Chronicity and Sex Affect Genetic Risk Prediction in Schizophrenia},
  series = {Frontiers in Psychiatry},
  volume    = {11},
  journal   = {Frontiers in Psychiatry},
  issn      = {1664-0640},
  doi       = {10.3389/fpsyt.2020.00313},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-205677},
  year      = {2020},
  abstract  = {Schizophrenia (SCZ) is a severe mental disorder with immense personal and societal costs; identifying individuals at risk is therefore of utmost importance. Genomic risk profile scores (GRPS) have been shown to significantly predict cases-control status. Making use of a large-population based sample from Sweden, we replicate a previous finding demonstrating that the GRPS is strongly associated with admission frequency and chronicity of SCZ. Furthermore, we were able to show a substantial gap in prediction accuracy between males and females. In sum, our results indicate that prediction accuracy by GRPS depends on clinical and demographic characteristics.},
  language  = {en}
}
@article{HessMengSchulteetal.2020,
  author    = {Heß, Verena and Meng, Karin and Schulte, Thomas and Neuderth, Silke and Bengel, J{\"u}rgen and Faller, Hermann and Schuler, Michael},
  title     = {Prevalence and predictors of cancer patients' unexpressed needs in the admission interview of inpatient rehabilitation},
  series = {Psycho-Oncology},
  volume    = {29},
  journal   = {Psycho-Oncology},
  number    = {10},
  doi       = {10.1002/pon.5450},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-228369},
  pages     = {1549 -- 1556},
  year      = {2020},
  abstract  = {Objective The admission interview in oncological inpatient rehabilitation might be a good opportunity to identify cancer patients' needs present after acute treatment. However, a relevant number of patients may not express their needs. In this study, we examined (a) the proportion of cancer patients with unexpressed needs, (b) topics of unexpressed needs and reasons for not expressing needs, (c) correlations of not expressing needs with several patient characteristics, and (d) predictors of not expressing needs. Methods We enrolled 449 patients with breast, prostate, and colon cancer at beginning and end of inpatient rehabilitation. We obtained self-reports about unexpressed needs and health-related variables (quality of life, depression, anxiety, adjustment disorder, and health literacy). We estimated frequencies and conducted correlation and ordinal logistic regression analyses. Results A quarter of patients stated they had "rather not" or "not at all" expressed all relevant needs. Patients mostly omitted fear of cancer recurrence. Most frequent reasons for not expressing needs were being focused on physical consequences of cancer, concerns emerging only later, and not knowing about the possibility of talking about distress. Not expressing needs was associated with several health-related outcomes, for example, emotional functioning, adjustment disorder, fear of progression, and health literacy. Depression measured at the beginning of rehabilitation showed only small correlations and is therefore not sufficient to identify patients with unexpressed needs. Conclusions A relevant proportion of cancer patients reported unexpressed needs in the admission interview. This was associated with decreased mental health. Therefore, it seems necessary to support patients in expressing needs.},
  language  = {en}
}