Patient-led skin cancer teledermatology without dermoscopy during the COVID-19 pandemic: important lessons for the development of future patient-facing teledermatology and artificial intelligence-assisted -self-diagnosis.

MySkinSelfie is a mobile phone application for skin self-monitoring, enabling secure sharing of patient-captured images with healthcare providers. This retrospective study assessed MySkinSelfie's role in remote skin cancer assessment at two centres for urgent (melanoma and squamous cell carcinoma) and nonurgent skin cancer referrals, investigating the feasibility of using patient-captured images without dermoscopy for remote diagnosis. The total number of lesions using MySkinSelfie was 814, with a mean patient age of 63 years. Remote consultations reduced face-to-face appointments by 90% for basal cell carcinoma and by 63% for referrals on a 2-week waiting list. Diagnostic concordance (consultant vs. histological diagnosis) rates of 72% and 83% were observed for basal cell carcinoma (n = 107) and urgent skin cancers (n = 704), respectively. Challenges included image quality, workflow integration and lack of dermoscopy. Higher sensitivities were observed in recent artificial intelligence algorithms employing dermoscopy. While patient-captured images proved useful during the COVID-19 pandemic, further research is needed to explore the feasibility of widespread patient-led dermoscopy to enable direct patient-to-artificial intelligence diagnostic assessment.

A real-world retrospective observational study exploring NHS resource use in England for the management of moderate-to-severe atopic dermatitis in secondary care for children and adolescents.

PURPOSE: To describe secondary care health care resource utilization (HCRU) for children and adolescents with atopic dermatitis (AD). PATIENTS AND METHODS: This UK chart review of patients with moderate-to-severe AD was conducted in four National Health Service hospitals. Cohorts were defined by age (children 6-11 years, adolescents 12-17) at first consultation. Eligible patients were selected consecutively, starting with the most recently consulting patient. At least 12 months' data were abstracted from medical records. Data were collected on HCRU, demographics/clinical characteristics, treatment, and patient-reported outcomes. RESULTS: Data were abstracted for 55 patients. Most patients (80%) had severe AD at first referral, a mean (SD) of 3.2 (10.7) patient-reported flare episodes/patient/year-of-observation, and 18.5 (16.7) tests/scans/procedures/patient/year. Mean (SD) observation duration was 3.6 (1.8) years. Patients had tried mean (SD) 7.9 (5.3) treatments/patient/year of observation. Topical corticosteroids (TCS; 24.5% of prescriptions) were most frequently prescribed. Mean (SD) use of emollients/moisturizers, TCS, systemic corticosteroids, and systemic immunosuppressants was 30.9 (21.3), 21.1 (23.4), 1.7 (8.3), and 7.8 (8.2) months. There was a mean (SD) of 5.3 (2.9) consultations/patient/year-of-observation; 116 (10.7%) for flare. Most hospitalizations (87.5%) were for children; the 8/55 (15%) hospitalized patients (mean 2.0 hospitalizations/patient during observation period) spent 6.2 (SD: 5.1) nights in hospital/hospitalization. Earliest mean (SD) Children's Dermatology Life Quality Index score was 15.3 (7.2); latest was 12.9 (7.5). CONCLUSION: Children and adolescents with moderate-to-severe AD had a high HCRU burden and small changes in quality of life, indicating that current treatments may provide suboptimal AD control in most cases.