Details

<p>Introduction.-&nbsp;A Deep Learning Approach for TUG and SPPB Score Prediction of (Pre–) Frail Older Adults on Real–Life IMU Data.-&nbsp;Detecting Impending Malnutrition of (Pre–) Frail Older Adults in Domestic Smart Home Environments.-&nbsp;Using Sensor Graphs for Monitoring the Effect on the Performance of the OTAGO Exercise Program in Older Adults.- Unsupervised Statistical Concept Drift Detection for Behaviour Abnormality Detection.- A System for Monitoring the Functional Status of Older Adults&nbsp;in Daily Life.-&nbsp;General Discussion.</p>

<p><strong>Björn Friedrich's</strong> research is focused on decision support using machine learning in medicine to empower older adults aging in place.</p>

<p>Functional decline in older adults can lead to an increased need of assistance or even moving to a nursing home. Utilising home automation, power and wearable sensors, the system developed by the author continuously keeps track of the functional status of older adults through monitoring their daily life and allows health care professionals to create individualised rehabilitation programmes based on the changes in the older adult’s functional capacity and performance in daily life. The system uses the taxonomy of the International Classification of Functioning, Disability and Health (ICF) by the World Health Organization (WHO). It links sensor data to fve ICF items from three ICF categories and measures their change over time. The system successfully passed the first pre-clinical validation step on the real-world data of the OTAGO study, a 10-month randomised pilot intervention study with 20 (pre-)frail older adults (aged ≥ 75 years). Since this research is in an early stage further clinical studies are needed to fully validate the system.</p>

<p><strong>About the author</strong></p>

<p><strong>Björn Friedrich's</strong> research is focused on decision support using machine learning in medicine to empower older adults aging in place.</p>