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

Dan E Webster; Rebecca H Haberman; Lourdes M Perez-Chada; Meghasyam Tummalacherla; Aryton Tediarjo; Vijay Yadav; Elias Chaibub Neto; Woody MacDuffie; Michael DePhillips; Eric Sieg; Sydney Catron; Carly Grant; Wynona Francis; Marina Nguyen; Muibat Yussuff; Rochelle L Castillo; Di Yan; Andrea L Neimann; Soumya M Reddy; Alexis Ogdie; Athanassios Kolivras; Michael R Kellen; Lara M Mangravite; Solveig K Sieberts; Larsson Omberg; Joseph F Merola; Jose U Scher

doi:10.3899/jrheum.2024-0074

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. 2024 Aug 1;51(8):781-789. doi: 10.3899/jrheum.2024-0074.

Authors

Dan E Webster¹, Rebecca H Haberman², Lourdes M Perez-Chada³, Meghasyam Tummalacherla¹, Aryton Tediarjo¹, Vijay Yadav¹, Elias Chaibub Neto¹, Woody MacDuffie¹, Michael DePhillips⁴, Eric Sieg⁴, Sydney Catron², Carly Grant³, Wynona Francis³, Marina Nguyen³, Muibat Yussuff³, Rochelle L Castillo², Di Yan⁵, Andrea L Neimann⁵, Soumya M Reddy², Alexis Ogdie⁶, Athanassios Kolivras⁷, Michael R Kellen¹, Lara M Mangravite¹, Solveig K Sieberts¹, Larsson Omberg¹, Joseph F Merola⁸, Jose U Scher⁹

Affiliations

¹ D.E. Webster, PhD, M. Tummalacherla, MSE, A. Tediarjo, BS, V. Yadav, MS, E. Chaibub Neto, PhD, W. MacDuffie, MS, M.R. Kellen, PhD, L.M. Mangravite, PhD, S.K. Sieberts, PhD, L. Omberg, PhD, Sage Bionetworks, Seattle, Washington, USA.
² R.H. Haberman, MD, MSCI, S. Catron, BS, R.L. Castillo, MD, MSCI, S.M. Reddy, MD, J.U. Scher, MD, Department of Medicine, Division of Rheumatology, New York University Grossman School of Medicine and NYU Psoriatic Arthritis Center, NYU Langone Health, New York, New York, USA.
³ L.M. Perez-Chada, MD, MMSc, C. Grant, BS, W. Francis, BS, M. Nguyen, BS, M. Yussuff, BS, Department of Dermatology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
⁴ M. DePhillips, BS, E. Sieg, BS, SDP Digital, Seattle, Washington, USA.
⁵ D. Yan, MD, A.L. Neimann, MD, MSCE, Ronald O. Perelman Department of Dermatology, New York University Grossman School of Medicine, New York, New York, USA.
⁶ A. Ogdie, MD, MSCE, Department of Medicine, Division of Rheumatology, Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
⁷ A. Kolivras, MD, PhD, Departments of Dermatology and Dermatopathology, Saint-Pierre, Brugmann and Queen Fabiola Children University Hospitals, Université Libre de Bruxelles, Brussels, and UCB Pharma, Brussels, Belgium.
⁸ J.F. Merola, MD, MMSc, Department of Dermatology and Department of Medicine, Division of Rheumatology, UT Southwestern Medical Center, Dallas, Texas, USA.
⁹ R.H. Haberman, MD, MSCI, S. Catron, BS, R.L. Castillo, MD, MSCI, S.M. Reddy, MD, J.U. Scher, MD, Department of Medicine, Division of Rheumatology, New York University Grossman School of Medicine and NYU Psoriatic Arthritis Center, NYU Langone Health, New York, New York, USA; Jose.Scher@nyulangone.org.

PMID: 38879192
DOI: 10.3899/jrheum.2024-0074

Abstract

Objective: Psoriatic disease remains underdiagnosed and undertreated. We developed and validated a suite of novel, sensor-based smartphone assessments (Psorcast app) that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms of psoriatic disease.

Methods: Participants with psoriasis (PsO) or psoriatic arthritis (PsA) and healthy controls were recruited between June 5, 2019, and November 10, 2021, at 2 academic medical centers. Concordance and accuracy of digital measures and image-based machine learning models were compared to their analogous clinical measures from trained rheumatologists and dermatologists.

Results: Of 104 study participants, 51 (49%) were female and 53 (51%) were male, with a mean age of 42.3 years (SD 12.6). Seventy-nine (76%) participants had PsA, 16 (15.4%) had PsO, and 9 (8.7%) were healthy controls. Digital patient assessment of percent body surface area (BSA) affected with PsO demonstrated very strong concordance (Lin concordance correlation coefficient [CCC] 0.94 [95% CI 0.91-0.96]) with physician-assessed BSA. The in-clinic and remote target plaque physician global assessments showed fair-to-moderate concordance (CCC_erythema 0.72 [0.59-0.85]; CCC_induration 0.72 [0.62-0.82]; CCC_scaling 0.60 [0.48-0.72]). Machine learning models of hand photos taken by patients accurately identified clinically diagnosed nail PsO with an accuracy of 0.76. The Digital Jar Open assessment categorized physician-assessed upper extremity involvement, considering joint tenderness or enthesitis (AUROC 0.68 [0.47-0.85]).

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. The smartphone software and analysis pipelines from the Psorcast suite are open source and freely available.

Keywords: biomarkers; clinical validation; digital health; outcome assessment; psoriasis; psoriatic arthritis.

Publication types

Validation Study

MeSH terms

Adult
Arthritis, Psoriatic* / diagnosis
Female
Humans
Machine Learning*
Male
Middle Aged
Mobile Applications
Proof of Concept Study
Psoriasis* / diagnosis
Reproducibility of Results
Smartphone*