Systemic sclerosis & Raynaud's
Development of a measuring app for systemic sclerosis-related digital ulceration (SALVE: Scleroderma App for Lesion VErification)
Authors' conclusion
Even patients with significant hand disability were able to use the app. Automated measurement of finger lesions could be valuable as an outcome measure in clinical trials.
Study context
- Population
- Patients with SSc-related digital lesions19 completed
- Participants
- 25 patients
- Comparison
- Manual vs automated measurement of SSc-related digital lesion area
- Outcome
- Lesion area
- Follow-up
- Day 1
Methodological detailssmartphone app, daily photographs for 30 days, manual and automated (machine learning) lesion measurement
- Smartphone app
- Daily photographs for 30 days
- Manual and automated (machine learning) lesion measurement
Main finding
As reported in the abstract
| Group | Value | Decrease per day | Decrease over 30 days |
|---|---|---|---|
| Manual | mean 11.6 (SD 16.0) mm² | 0.08 mm² | 2.4 mm² |
| Automated | mean 13.9 (SD 16.7) mm² | 0.1 mm² | 3.0 mm² |
Value
Manualmean 11.6 (SD 16.0) mm²
Automatedmean 13.9 (SD 16.7) mm²
Decrease per day
Manual0.08 mm²
Automated0.1 mm²
Decrease over 30 days
Manual2.4 mm²
Automated3.0 mm²
- Correlation of average gradients of manual and automated measurements over 30 days (r)
- 0.81
- Manual measurements on average lower than automated ones, with wide limits of agreement
- 40%
Further findings
Baseline Pain score
- Mean (SD) baseline Pain score
- 5.7 (2.4)
- Indicating high lesion- and disease-related morbidity
Baseline Hand Disability in Systemic Sclerosis-Digital Ulcers (HDISS-DU)
- Mean (SD) baseline HDISS-DU
- 2.2 (0.9)
- Indicating high lesion- and disease-related morbidity
Images used in the analysis
- Total images used
- 506
- Mean (SD) number of used images per lesion
- 18.7 (8.3)
Original publication
Development of a measuring app for systemic sclerosis-related digital ulceration (SALVE: Scleroderma App for Lesion VErification). Rheumatology (Oxford). Published 19 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →