Clinical validation of digital biomarkers and machine learning models for remote measurement of psoriasis and psoriatic arthritis

Abstract

AbstractBackgroundPsoriasis and psoriatic arthritis are common immune-mediated inflammatory conditions that primarily affect the skin, joints and entheses and can lead to significant disability and worsening quality of life. Although early recognition and treatment can prevent the development of permanent damage, psoriatic disease remains underdiagnosed and undertreated due in part to the disparity between disease prevalence and relative lack of access to clinical specialists in dermatology and rheumatology. Remote patient self-assessment aided by smartphone sensor technology may be able to address these gaps in care, however, these innovative disease measurements require robust clinical validation.MethodsWe developed smartphone-based assessments, collectively named the Psorcast suite, that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms of psoriatic disease. The image and motion sensor data collected by these assessments was processed to generate digital biomarkers or machine learning models to detect psoriatic disease phenotypes. To evaluate these digital endpoints, a cross-sectional, in-clinic validation study was performed with 92 participants across two specialized academic sites consisting of healthy controls and participants diagnosed with psoriasis and/or psoriatic arthritis.FindingsIn the domain of skin disease, digital patient assessment of percent body surface area (BSA) affected with psoriasis demonstrated very strong concordance (CCC = 0·94, [95%CI = 0·91–0·96]) with physician-assessed BSA. Patient-captured psoriatic plaque photos were remotely assessed by physicians and compared to in-clinic Physician Global Assessment parameters for the same plaque with fair to moderate concordance (CCCerythema=0·72 [0·59–0·85]; CCCinduration=0·72 [0·62–0·82]; CCCscaling=0·60 [0·48–0·72]). Arm range of motion was measured by the Digital Jar Open assessment to classify physician-assessed upper extremity involvement with joint tenderness or enthesitis, demonstrating an AUROC = 0·68 (0·47–0·85). Patient-captured hand photos were processed with object detection and deep learning models to classify clinically-diagnosed nail psoriasis with an accuracy of 0·76, which is on par with remote physician rating of nail images (avg. accuracy = 0·63) with model performance maintaining accuracy when raters were too unsure or image quality was too poor for a remote assessment.InterpretationThe Psorcast digital assessments, performed by patient self-measurement, achieve significant clinical validity when compared to in-person physical exams. These assessments should be considered appropriately validated for self-monitoring and exploratory research applications, particularly those that require frequent, remote disease measurements. However, further validation in larger cohorts will be necessary to demonstrate robustness and generalizability across populations for use in evidence-based medicine or clinical trial settings. The smartphone software and analysis pipelines from the Psorcast suite are open source and available to the scientific community.FundingThis work is funded by the Psorcast Digital Biomarker Consortium consisting of Sage Bionetworks, Psoriasis and Psoriatic Arthritis Centers for Multicenter Advancement Network (PPACMAN), Novartis, UCB, Pfizer, and Janssen Pharmaceuticals. J.U.S work was supported by the Snyder Family Foundation and the Riley Family Foundation.Research in contextEvidence before this studyNo systematic literature review was performed. Patient self-measurement with smartphone sensors has been shown to be clinically valid for assessing signs and symptoms such as tremor, gait, physical activity, or range of motion across multiple disease indications. While smartphone-based applications have been developed for digitally tracking psoriatic disease, they have largely focused on questionnaire-based patient reported outcomes.Added value of this studyTo our knowledge, Psorcast is the first application using ubiquitous smartphone sensor technology for patients to remotely measure their psoriatic disease phenotypes, including detection of nail psoriasis and a continuous variable outcome measure of joint tenderness and enthesitis based on range of motion. This study not only developed a suite of novel, smartphone sensor-based assessment that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms, but provides clinical validation of these measures.Implications of all the available evidenceThe developed Psorcast suite of measurements can serve as groundwork for patient-driven, remote measurement of psoriatic disease. The use and continued development of this technology opens up new possibilities for both clinical care and research endeavors on a large scale. Psorcast measurements are currently being validated for their ability to assess disease changes longitudinally, allowing for more frequent symptom monitoring in clinical trials, more granular insight into the time course of medication action, and possible identification of responders from non-responders to specific therapies.