The purpose of this study is to understand variation in the symptoms of psoriasis and psoriatic arthritis using simple, scalable smartphone-based measurements. This study uses an iPhone app to record these symptoms through questionnaires and sensors.
Psoriatic disease exhibits a spectrum of symptoms and can transition from psoriasis (PsO), largely affecting the skin, to psoriatic arthritis (PsA) involving widespread musculoskeletal inflammation. Early detection of the PsO-to-PsA transition and rapid administration of effective treatment is essential, as a delay in diagnosing PsA by as little as 6 months can lead to irreversible joint damage. This "ticking clock" paradigm drives the need for frequent monitoring and effective therapeutic intervention as early as possible to attenuate or possibly prevent disease progression. Using a suite of smartphone-based measurements in an app called Psorcast (psoriasis forecasts), we aim to aggregate weekly, symptom measurements from participants in a remote, longitudinal observational study to map the trajectories of treatment response and disease progression. In this study, we will explore measurements of psoriatic disease activity at least an order of magnitude more frequently (weekly vs. quarterly) than standard clinical practice or clinical trial designs. This study is not meant to provide a medical diagnosis, treatment, or medical advice. It is meant to provide a scalable, inexpensive, non-invasive and frequent measure and tracking of psoriasis and psoriatic arthritis for research purposes.
Study Type
OBSERVATIONAL
Enrollment
1,000
At enrollment, participants are asked to complete a baseline health history, family history, and a participant-reported symptom inventory.
Participants are asked to draw the location and size of psoriasis they currently experience. Participants are provided a body template onto which they can draw on their screen. Investigators estimate the percentage of body area affected.
Participants are asked to take a picture of a representative psoriasis plaque and indicate the location of the plaque. They are asked to take a picture of the same area over time. The investigators are developing computer vision algorithms to assess the plaque.
Participants are asked to take pictures of the back of each hand and the top of each foot. These photos can be used to assess finger and toe swelling as well as psoriatic nail involvement. The investigators are developing computer vision algorithms to assess psoriatic nail involvement and digit swelling.
Participants are asked to internally and externally rotate the phone as it rests on a flat surface. Participants perform each direction (internal and external) and each arm (left and right) in turn. Gyroscope sensors measure the degree of rotation.
Participants are asked to walk in a straight line for 30 seconds. Gait is measured by gyroscope and accelerometer sensors. The investigators examine step-dependent and sequence-dependent features from these sensors. The investigators apply feature selection and classifier algorithms to analyze these data.
Participants complete all described behavioral interventions via a dedicated iPhone app, Psorcast.
Sage Bionetworks
Seattle, Washington, United States
RECRUITINGResults of participant self-assessment surveys
Results of participant self-assessment surveys will be analyzed using descriptive statistics. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Body surface area and location from the Psoriasis Draw assessment
The investigators will quantify body surface area and psoriasis area hotspots across the cohort. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Computer vision features from Psoriasis Area Photo assessment
The investigators apply visual processing and classifier algorithms to analyze the images from the Psoriasis Area Photo assessments. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Computer vision features from Finger/Toe Photos
The investigators apply visual processing and classifier algorithms to segment nails and joints from hand and foot photos. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Gyroscope and accelerometer sensor measurements from Digital Jar Open assessment
The investigators examine rotational features from gyroscope and accelerometer sensors. The investigators apply feature selection and classifier algorithms to analyze these data. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Gyroscope and accelerometer sensor measurements from 30-sec Walk assessment
The investigators examine step-dependent and sequence-dependent features from gyroscope and accelerometer sensors. The investigators apply feature selection and classifier algorithms to analyze these data. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
Quantification and distribution of self-reported painful joints
The investigators will quantify the self-reported painful joints and, in particular, compare to measurements from the 30-sec Walk and Digital Jar Open to identify correlations. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
App usage data for assessment of participant engagement
App usage data is used to gauge participant engagement throughout the study period. These results may also be compared with other intervention results.
Time frame: Through study completion, an average of 2 years
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.