Sex differences in adverse events from systemic treatments for psoriasis: A decade of insights from the Swiss Psoriasis Registry (SDNTT).

BACKGROUND: Psoriasis is a disease that often requires prolonged systemic treatment. It is important to determine the safety of available therapies. There is currently little insight into sex-specific differences in the safety of systemic psoriasis therapies. OBJECTIVES: To examine the real-world, long-term safety of systemic psoriasis therapies with sex stratification in drug-related adverse events (ADRs). METHODS: Ten-year data from adults with moderate-to-severe psoriasis requiring systemic treatment (conventional systemic therapies [CST], biologics) were obtained from the Swiss psoriasis registry (SDNTT). ADRs were categorized according to the international terminology Medical Dictionary for Regulatory Activities (MedDRA). Safety was assessed by calculating event rates per 100 patient-years (PY). We used descriptive statistics for patient and disease characteristics, and binomial and t-tests to compare treatment groups and sex. RESULTS: In total, 791 patients (290 females) were included with a mean age of 46 years. 358 (45%) received CSTs and 433 (55%) biologics; both groups had similar baseline characteristics except for more joint involvement in patients using biologics (26.86% vs. 14.8%, p < 0.0001). CSTs were associated with a 2.2-fold higher ADR rate (40.43/100 PY vs. 18.22/100 PY, p < 0.0001) and an 8.0-fold higher drug-related discontinuation rate than biologics (0.16/PY vs. 0.02/PY, p < 0.0001). Trends showed non-significant higher serious adverse event rates per 100 PY for biologics (8.19, CI 6.87-9.68) compared to CSTs (7.08, CI 5.39-9.13) (p = 0.3922). Sex stratification revealed a significantly higher overall ADR rate for all treatments in females (1.8-fold for CSTs [57.30/100 PY vs. 31.69/100 PY] and 2.0-fold for biologics [27.36/100 PY vs. 13.9/100 PY], p < 0.0001), and drug-related discontinuation rates for most CSTs in females. CONCLUSION: Females were associated with a significantly higher rate of ADRs and drug-related discontinuation rates. Sex stratification should be taken into consideration when designing studies in the patient-tailored management of psoriasis.

Saliency-Enhanced Content-Based Image Retrieval for Diagnosis Support in Dermatology Consultation: Reader Study.

BACKGROUND: Previous research studies have demonstrated that medical content image retrieval can play an important role by assisting dermatologists in skin lesion diagnosis. However, current state-of-the-art approaches have not been adopted in routine consultation, partly due to the lack of interpretability limiting trust by clinical users. OBJECTIVE: This study developed a new image retrieval architecture for polarized or dermoscopic imaging guided by interpretable saliency maps. This approach provides better feature extraction, leading to better quantitative retrieval performance as well as providing interpretability for an eventual real-world implementation. METHODS: Content-based image retrieval (CBIR) algorithms rely on the comparison of image features embedded by convolutional neural network (CNN) against a labeled data set. Saliency maps are computer vision-interpretable methods that highlight the most relevant regions for the prediction made by a neural network. By introducing a fine-tuning stage that includes saliency maps to guide feature extraction, the accuracy of image retrieval is optimized. We refer to this approach as saliency-enhanced CBIR (SE-CBIR). A reader study was designed at the University Hospital Zurich Dermatology Clinic to evaluate SE-CBIR's retrieval accuracy as well as the impact of the participant's confidence on the diagnosis. RESULTS: SE-CBIR improved the retrieval accuracy by 7% (77% vs 84%) when doing single-lesion retrieval against traditional CBIR. The reader study showed an overall increase in classification accuracy of 22% (62% vs 84%) when the participant is provided with SE-CBIR retrieved images. In addition, the overall confidence in the lesion's diagnosis increased by 24%. Finally, the use of SE-CBIR as a support tool helped the participants reduce the number of nonmelanoma lesions previously diagnosed as melanoma (overdiagnosis) by 53%. CONCLUSIONS: SE-CBIR presents better retrieval accuracy compared to traditional CBIR CNN-based approaches. Furthermore, we have shown how these support tools can help dermatologists and residents improve diagnosis accuracy and confidence. Additionally, by introducing interpretable methods, we should expect increased acceptance and use of these tools in routine consultation.