Spondyloarthritis & psoriatic arthritis

Clinical Validation of Digitally Acquired Clinical Data and Machine Learning Models for Remote Measurement of Psoriasis and Psoriatic Arthritis: A Proof-of-Concept Study

J RheumatolPublished Diagnostic accuracy study

Authors' conclusion

The Psorcast digital assessments achieved significant clinical validity, although they require further validation in larger cohorts before use in evidence-based medicine or clinical trial settings.

Study context

Population
Participants with PsO or psoriatic arthritis (PsA) and healthy controls, 2 academic medical centers, June 5, 2019 to November 10, 2021 (mean age 42.3 years)51 female, 53 male
Participants
104 participants
Comparison
Smartphone-based digital assessments (Psorcast app) and image-based machine learning models vs analogous clinical measures by trained rheumatologists and dermatologists
  • PsAn = 79
  • PsOn = 16
  • Healthy controlsn = 9
Outcome
Concordance and accuracy of digital measures vs clinical measures
Methodological detailsproof-of-concept, 2 academic medical centers
  • Proof-of-concept
  • 2 academic medical centers

Performance

As reported in the abstract

Digital patient-assessed % body surface area (BSA) with PsO vs physician-assessed BSA, Lin CCC
0.94 (95% CI 0.91-0.96)
In-clinic vs remote target plaque PGA, CCC erythema (0.59-0.85)
0.72
In-clinic vs remote target plaque PGA, CCC induration (0.62-0.82)
0.72
In-clinic vs remote target plaque PGA, CCC scaling (0.48-0.72)
0.60
Machine learning models of patient hand photos identifying clinically diagnosed nail PsO, accuracy
0.76
Digital Jar Open assessment categorising physician-assessed upper extremity involvement (joint tenderness or enthesitis), AUROC (0.47-0.85)
0.68

Original publication

Clinical Validation of Digitally Acquired Clinical Data and Machine Learning Models for Remote Measurement of Psoriasis and Psoriatic Arthritis: A Proof-of-Concept Study. J Rheumatol. Published 15 June 2024. doi:10.3899/jrheum.2024-0074

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.