To save content items to your account,
please confirm that you agree to abide by our usage policies.
If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account.
Find out more about saving content to .
To save content items to your Kindle, first ensure email@example.com
is added to your Approved Personal Document E-mail List under your Personal Document Settings
on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part
of your Kindle email address below.
Find out more about saving to your Kindle.
Note you can select to save to either the @free.kindle.com or @kindle.com variations.
‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi.
‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.
Digital biomarkers of mental health, created using data extracted from everyday technologies including smartphones, wearable devices, social media and computer interactions, have the opportunity to revolutionise mental health diagnosis and treatment by providing near-continuous unobtrusive and remote measures of behaviours associated with mental health symptoms. Machine learning models process data traces from these technologies to identify digital biomarkers. In this editorial, we caution clinicians against using digital biomarkers in practice until models are assessed for equitable predictions (‘model equity’) across demographically diverse patients at scale, behaviours over time, and data types extracted from different devices and platforms. We posit that it will be difficult for any individual clinic or large-scale study to assess and ensure model equity and alternatively call for the creation of a repository of open de-identified data for digital biomarker development.
Mobile phones can replace traditional self-monitoring tools through cell phone-based ecological momentary assessment (CEMA) of lifestyle behaviours and camera phone-based images of meals, i.e. photographic food records (PFR). Adherence to mobile self-monitoring needs to be evaluated in real-world treatment settings. Towards this goal, we examine CEMA and PFR adherence to the use of a mobile app designed to help mothers self-monitor lifestyle behaviours and stress.
In 2012, forty-two mothers recorded CEMA of diet quality, exercise, sleep, stress and mood four times daily and PFR during meals over 6 months in Los Angeles, California, USA.
A purposive sample of mothers from mixed ethnicities.
Adherence to recording CEMA at least once daily was higher compared with recording PFR at least once daily over the study period (74 v. 11 %); adherence to both types of reports decreased over time. Participants who recorded PFR for more than a day (n 31) were more likely to be obese v. normal- to overweight and to have higher blood pressure, on average (all P<0·05). Based on random-effects regression, CEMA and PFR adherence was highest during weekdays (both P<0·01). Additionally, PFR adherence was associated with older age (P=0·04). CEMA adherence was highest in the morning (P<0·01). PFR recordings occurred throughout the day.
Variations in population and temporal characteristics should be considered for mobile assessment schedules. Neither CEMA nor PFR alone is ideal over extended periods.
The rapid explosion of mobile phones over the last decade has enabled a new sensing paradigm – participatory sensing – where individuals act as sensors by using their mobile phones for data collection. Participatory sensing relies on the sensing capabilities of mobile phones, many of which have the ability to detect location, capture images and audio, the networking support provided by cellular and WiFi infrastructure, and the spatial and temporal coverage along with interpretive abilities provided by the individuals that carry and operate mobile phones. If successfully coordinated, participants involved in data collection using their mobile phones can open up new possibilities uniquely relevant to the interests of individuals, groups, and communities as they seek to understand the social and physical processes of the world around them. Responsibly realizing a vision of sensing that is widespread and participatory poses critical technology challenges. To support mobile participatory sensing applications, the future Internet architecture must provide network services that enable applications to select, task, and coordinate mobile users based on measures of coverage, capabilities, and participation and performance patterns; attestation mechanisms that enable sensor data consumers to assess trustworthiness of the data they access; and privacy and auditing mechanisms that enable sensor sources to control sharing and disclosure of data.
Mobile Participatory Sensing Vision
Individuals Carrying Mobile Phones as Sensors
Embedded wireless sensing provides scientists and engineers unique insights into the physical and biological processes of the natural and “built” environments.
Email your librarian or administrator to recommend adding this to your organisation's collection.