Validation of smartphone-derived metrics for prolonged unobtrusive monitoring of rest-activity patterns, fatigue andsleepiness in sleep-disordered patients.
- Conditions
- chronic insomnia disordersleep related breathing disorders circadian rhythm disorder nonrestorative sleepprimary hypersomnia
- Registration Number
- NL-OMON22867
- Lead Sponsor
- none
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Pending
- Sex
- Not specified
- Target Recruitment
- 200
Inclusion Criteria
Sleep disordered patiënts referred to Kempenhaeghe
A minimum 18 year of age
Able to read and speak Dutch
Regular use of smartphone on a daily basis
Exclusion Criteria
Cognitive impairments that make use of smartphones and/or completion of questionnaires difficult or unreliable.
Other somatic disorders that can cause fatigue and/or excessive daytime sleepiness.
Study & Design
- Study Type
- Observational non invasive
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Primary Objectives:<br>• Investigate whether and to what extent smartphone interaction metrics can unobtrusively monitor rest-activity patterns in patients suffering from sleep disorders.<br>• Investigate whether and to what extent fatigue and sleepiness during the wake phase can be monitored and quantified objectively by means of smartphone-derived keystroke dynamics features among patients suffering from sleep disorders.
- Secondary Outcome Measures
Name Time Method Secondary Objective:<br>• Investigate whether and to what extent smartphone derived metrics based on keyboard interactions (potentially complemented with health kit and sensor data) are sensitive (responsive) to changes in clinical status. Sensitivity to changes will be investigated in the following: rest-activity patterns, fatigue-related complaints during the wake phase, and excessive daytime sleepiness due to clinical interventions as part of care as usual,<br><br>Tertiary / Exploratory Objective(s):<br>• Investigate the accuracy of machine learning methods to differentiate between participants with different clinical sleep diagnoses (e.g., insomnia or circadian rhythm sleep disorders) based on Neurocast platform metrics.<br>• Investigate whether and to what extent Neurocast platform metrics can be used to assess pre-sleep arousal and/or predict sleep quality and insomnia severity.<br>• Assess user experiences with the Neurocast platform.