Objectives: Pustular psoriasis (PP) is one of the most severe and chronic skin conditions. Its treatment is difficult, and measurements of its severity are highly dependent on clinicians’ experience. Pustules and brown spots are the main efflorescences of the disease and directly correlate with its activity. We propose an automated deep learning model (DLM) to quantify lesions in terms of count and surface percentage from patient photographs. Methods: In this retrospective study, two dermatologists and a student labeled 151 photographs of PP patients for pustules and brown spots. The DLM was trained and validated with 121 photographs, keeping 30 photographs as a test set to assess the DLM performance on unseen data. We also evaluated our DLM on 213 unstandardized, out-of-distribution photographs of various pustular disorders (referred to as the pustular set), which were ranked from 0 (no disease) to 4 (very severe) by one dermatologist for disease severity. The agreement between the DLM predictions and experts’ labels was evaluated with the intraclass correlation coefficient (ICC) for the test set and Spearman correlation (SC) coefficient for the pustular set. Results: On the test set, the DLM achieved an ICC of 0.97 (95% confidence interval [CI], 0.97–0.98) for count and 0.93 (95% CI, 0.92–0.94) for surface percentage. On the pustular set, the DLM reached a SC coefficient of 0.66 (95% CI, 0.60–0.74) for count and 0.80 (95% CI, 0.75–0.83) for surface percentage. Conclusions: The proposed method quantifies efflorescences from PP photographs reliably and automatically, enabling a precise and objective evaluation of disease activity.

Long-term control of SARS-CoV-2 requires effective vaccination strategies. This has been challenged by public mistrust and the spread of misinformation regarding vaccine safety. Better understanding and communication of the longer-term and comparative experiences of individuals in the general population following vaccination are required. In this population-based longitudinal study, we included 575 adults, randomly selected from all individuals presenting to a Swiss reference vaccination center, for receipt of BNT162b2, mRNA1273, or JNJ-78436735. We assessed the prevalence, onset, duration, and severity of self-reported adverse effects over 12 weeks following vaccination. We additionally evaluated participants’ perceptions of vaccines, trust in public health authorities and pharmaceutical companies, and compliance with public health measures. Most participants reported at least one adverse effect within 12 weeks following vaccination. Adverse effects were mostly mild or moderate, resolved within three days, and rarely resulted in anaphylaxis or hospitalizations. Female sex, younger age, higher education, and receipt of mRNA-1273 were associated with reporting adverse effects. Compared to JNJ-78436735 recipients, a higher proportion of mRNA vaccine recipients agreed that vaccination is important, and trusted public health authorities. Our findings provide real-world estimates of the prevalence of adverse effects following SARS-CoV-2 vaccination and highlight the importance of transparent communication to ensure the success of current or future vaccination campaigns.

Importance: Long-term control of SARS-CoV-2 requires effective vaccination strategies. This has been challenged by public mistrust and spread of misinformation regarding vaccine safety. Hence, better understanding and communication on the longer-term and comparative experiences of general population individuals following SARS-CoV-2 vaccination are required. Objective: To evaluate and compare self-reported adverse effects following SARS-CoV-2 vaccination, participants perceptions regarding vaccinations and their compliance with recommended public health measures. Design, Setting and Participants: Population-based longitudinal cohort of 575 adults, randomly selected from all individuals presenting to the reference vaccination center of the Canton of Zurich, Switzerland, for receipt of BNT162b2, mRNA1273, or JNJ-78436735. Exposures: BNT162b2, mRNA1273, or JNJ-78436735 vaccines. Main Outcomes and Measures: Primary outcomes included period prevalence, onset, duration, and severity of self-reported adverse effects over 12 weeks following vaccination with a specific focus on the proportion of participants reporting allergic reactions, menstrual irregularities, or cardiac adverse effects, or requiring hospitalization. Secondary outcomes included risk factors associated with reporting adverse effects, perception of vaccine importance, trust in public health authorities and pharmaceutical companies, and compliance with recommended public health measures. Results: 454 (79.0%) participants reported at least one adverse effect during 12 weeks after vaccination. Prevalence was highest among mRNA-1273 recipients (88.7% vs. 77.3% after BNT162b2, 69.1% after JNJ-78436735). Most adverse effects were systemic (72%), occurred within 24 hours (67.9%), and resolved in less than three days (76.3%). 85.2% were reported as mild or moderate. Allergic reactions were reported by 0.3% of participants, hospitalizations by 0.7%, cardiac adverse effects by 1.4%. Menstrual irregularities were reported by 9% of female participants younger than 50 years. Female sex, younger age, higher education, and receipt of mRNA-1273 were associated with reporting adverse effects. Compared to JNJ-78436735 recipients, a higher proportion of mRNA vaccine recipients agreed that vaccination is important (87.5% vs. 28.5%), and trusted public health authorities (80.2% vs. 30.3%) and pharmaceutical companies (71.7% vs. 23.6%). Conclusions and Relevance: Our population-based cohort provided real-world data on self-reported adverse effects following SARS-CoV-2 vaccination and highlights the importance of transparent communication regarding adverse effects and building trust in public health authorities to ensure successful future vaccination campaigns.