Keratoacanthoma and Cutaneous Squamous Cell Carcinoma With PD-1 and PD-L1 Inhibitor Use.

This cross-sectional study assesses risk of dermatological immune-related adverse events associated with immunotherapy for cancer.

Safety Signal between Azacitidine and Pericarditis.

BACKGROUND: Drug-induced pericarditis is an important cause of pericarditis and if unnoticed and unmanaged can lead to constrictive pericarditis, pericardial effusion, and cardiac tamponade. OBJECTIVE: The objective of this analysis was to determine if a significant signal exists between azacitidine use and pericarditis. METHODS: A pharmacovigilance analysis was performed using the FDA Adverse Event Database. RESULTS: 48 reports of azacitidine-induced pericarditis with azacitidine as the suspect drug were identified. The most common indications for azacitidine use in the adverse event reports were myelodysplastic syndrome (48%) and acute myelogenous leukemia (27%). Physicians reported 44% of the azacitidine-induced pericarditis reports, while other health professional reported 52% of the reports. The disproportionality analysis showed a proportional reporting ratio of 5.0, χ2 of 149.8, reporting odds ratio of 5.0, and IC025 of 1.8. Literature review found 3 case reports of azacitidine-induced pericarditis. CONCLUSION: The signal between azacitidine and pericarditis was found to be statistically significant. Clinicians should be aware of the possible risk of pericarditis when prescribing azacitidine. If there is suspicion for azacitidine-induced pericarditis, clinicians should consider discontinuation of azacitidine to improve patient's symptoms and reduce the likelihood of the development of constrictive pericarditis, pericardial effusion, and cardiac tamponade.

Risk Factors That Are Associated With Outliers in Mohs Micrographic Surgery in the National Medicare Population, 2018.

BACKGROUND: Physician variation exists in the mean number of stages performed per Mohs micrographic surgery (MMS) case. Physicians who are outliers in medical practice may be leading to a higher health care cost burden. OBJECTIVE: To identify factors that influence being a high outlier in the mean stages per MMS case. MATERIALS AND METHODS: The study comprised a retrospective analysis of 2018 data from physicians who billed Medicare Part B for Current Procedural Terminology (CPT) 17311 and 17312 (MMS of the head, neck, hands, feet, or genitalia) and/or CPT 17313 and 17314 (MMS of the trunk, arms, or legs). RESULTS: For CPT 17311 and 17312, the odds ratio for being an outlier for a physician in a solo practice relative to a multiphysician facility is 2.4 (1.6-3.8), for a physician who is not an American College of Mohs Surgery (ACMS) member relative to a ACMS member is 2.0 (1.2-3.2), and for a practice located in the West, Northeast, and South is 7.7 (2.8-21.6), 6.2 (2.1-18.6), and 1.8 (0.6-5.4), respectively, relative to in the Midwest. CONCLUSION: Physicians who are practicing solo, practicing in the West or Northeast, and are not ACMS members are more likely to be a high outlier in the mean stages per MMS case.

Artificial intelligence image recognition of melanoma and basal cell carcinoma in racially diverse populations.

BACKGROUND: Artificial intelligence (AI) image recognition models have been relatively successful in diagnosing cutaneous manifestations in individuals with light skin tone. However, when these models are tested on the same cutaneous manifestations in individuals with darker or brown skin tone, the performance of the model drops due to a paucity of such images available for model training. OBJECTIVE: The objective of this study was to improve the performance of AI models in recognizing cutaneous diseases in individuals with darker skin tone. METHODS: Unsupervised computer darkening of skin color with preservation of the dermatological disease/lesion characteristics in images of light-skinned individuals with basal cell carcinoma (BCC), and melanoma was performed. RESULTS: Training an AI model on these artificially "darkened" images as compared to training on the original "light-skinned" images resulted in a higher sensitivity, specificity, positive predictive value, negative predictive value, F1 score and area under the receiver-operating characteristic curve of the AI model in differentiating between BCC and melanoma in individuals with brown skin tone. CONCLUSION: Use of unsupervised image to image translation in medical AI image recognition models has the potential to significantly improve their accuracy in diagnosing diseases in individuals with racially diverse skin tone.

United States burden of melanoma and non-melanoma skin cancer from 1990 to 2019.

BACKGROUND: Skin cancer is the most common cancer worldwide. OBJECTIVE: To evaluate the burden of skin cancer in the US from 1990 to 2019. METHODS: Age-standardized incidence, prevalence, disability-adjusted life years (DALY), and mortality rates from skin cancer in the US were evaluated from the Global Burden of Disease 2019. RESULTS: Incidence, prevalence, DALY, and mortality rates for melanoma per 100,000 persons in 2019 were 17.0, 138, 64.8, and 2.2, respectively; for squamous cell carcinoma, rates were 262, 314, 26.6, and 0.8, respectively; and for basal cell carcinoma, rates were 525, 51.2, 0.2, and zero, respectively. Incidence and prevalence rates of melanoma and non-melanoma skin cancer (NMSC) have increased since 1990, while mortality rates have remained fairly stable. Males have had higher incidence, prevalence, DALY, and mortality rates from melanoma and NMSC every year since 1990. Incidence and prevalence of melanoma was relatively higher in the northern half of the US than in the southern half. LIMITATIONS: Global Burden of Disease is derived from estimation and mathematical modeling. CONCLUSIONS: Health care professionals can utilize differences and trends noted in this study to guide allocation of resources to reduce incidence and morbidity from skin cancer.

Sanitation, Obesity, and Low Body Mass Index as Risk Factors for Bacterial Skin Infections.

BACKGROUND: Bacterial skin infections can cause significant disability and can lead to mortality with inadequate treatment. OBJECTIVE: To determine whether sanitation and body mass index (BMI) are statistically significant risk factors for the incidence and prognosis of bacterial skin infections. METHODS: Country-level data regarding the age-standardized rates of incidence, prevalence, and years lived with disability (YLD) from bacterial skin infection per 100 000 persons from the Global Burden of disease dataset, and country-level data on age-standardized prevalence of obesity (BMI ≥30) and low BMI (BMI <18.5) from World Health Organization Global Health Observatory data repository were analyzed. Regression models were created to examine the effects of sanitation, obesity, and low BMI on the burden of bacterial skin infections. RESULTS: The percentage of population using basic sanitation services was positively associated with incidence, prevalence, and YLD from bacterial skin infections (P < .05). After controlling for sanitation, in countries with more than 50% of the population using basic sanitation services, obesity was positively associated with incidence, prevalence, and YLD from bacterial skin infections (P < .05). In countries with less than or equal to 50% of the population using basic sanitation services, low BMI was positively associated with incidence, prevalence, and YLD from bacterial skin infections (P < .05). CONCLUSIONS: Improving sanitation access in all countries, reducing the percentage of obese population in countries with good sanitation/hygiene techniques, and addressing malnutrition in countries with poor sanitation/hygiene techniques may help to reduce the burden of bacterial skin infections.

Performance of Artificial Intelligence Imaging Models in Detecting Dermatological Manifestations in Higher Fitzpatrick Skin Color Classifications.

BACKGROUND: The performance of deep-learning image recognition models is below par when applied to images with Fitzpatrick classification skin types 4 and 5. OBJECTIVE: The objective of this research was to assess whether image recognition models perform differently when differentiating between dermatological diseases in individuals with darker skin color (Fitzpatrick skin types 4 and 5) than when differentiating between the same dermatological diseases in Caucasians (Fitzpatrick skin types 1, 2, and 3) when both models are trained on the same number of images. METHODS: Two image recognition models were trained, validated, and tested. The goal of each model was to differentiate between melanoma and basal cell carcinoma. Open-source images of melanoma and basal cell carcinoma were acquired from the Hellenic Dermatological Atlas, the Dermatology Atlas, the Interactive Dermatology Atlas, and DermNet NZ. RESULTS: The image recognition models trained and validated on images with light skin color had higher sensitivity, specificity, positive predictive value, negative predictive value, and F1 score than the image recognition models trained and validated on images of skin of color for differentiation between melanoma and basal cell carcinoma. CONCLUSIONS: A higher number of images of dermatological diseases in individuals with darker skin color than images of dermatological diseases in individuals with light skin color would need to be gathered for artificial intelligence models to perform equally well.

Pyoderma gangrenosum adverse event with Rituximab use: A postmarketing pharmacovigilance analysis.

Rituximab is a monoclonal antibody that is used for the treatment of certain malignancies and autoimmune conditions. Pyoderma gangrenosum is a rare painful ulcer that can be fatal in some cases and can also reoccur after treatment. The objective of this paper was to analyze whether a statistically significant signal exists between Rituximab and pyoderma gangrenosum in the Food and Drug Administration Adverse Event Reporting System (FAERS). A disproportionality analysis was carried out on cases from January 1, 2004 to March 31, 2019 in the FAERS. Frequentist methods of relative reporting ratio, reporting odds ratio (ROR), and proportional reporting ratio (PRR) and the Bayesian-based IC025 metric were used in order to assess the adverse event signal. Thirty-two cases were found in FAERS in which the drug Rituximab was administered and pyoderma gangrenosum was reported as an adverse event. The lower 95% CI of the information component was 0.97, the lower 95% CI of ROR was 2.18, the PRR was 3.09 and Chi-squared was 42.16, which indicates a statistically significant signal. The signal is supported by six case reports in the literature that describe a total of 14 patients who developed pyoderma gangrenosum after Rituximab administration. When administering Rituximab, clinicians should monitor for the occurrence of symptoms representing pyoderma gangrenosum.

Disproportionality analysis of bullous pemphigoid adverse events with PD-1 inhibitors in the FDA adverse event reporting system.

Objectives: Bullous pemphigoid, an autoimmune dermatological disease, may be associated with the use of a relatively new anti-cancer drug class, PD-1 inhibitors, which includes pembrolizumab and nivolumab. This paper analyzes the signals between PD-1 inhibitors and bullous pemphigoid based upon the reported real-world data. Methods: A pharmacovigilance analysis was performed on the publicly available Adverse Event Reporting System database of Food and Drug Administration. Disproportionality ratios were used to examine a signal between PD-1 inhibitors and bullous pemphigoid. A heat map was generated to depict the signal between PD -1 inhibitor use and skin toxicity adverse events. Results: The analysis indicated that there is a significant signal (PRR = 13.82 [95% CI: 9.99-19.11], Chi-squared with Yates' correction = 420.48) between pembrolizumab use and bullous pemphigoid and that there is a significant signal (PRR = 13.19 [95% CI: 10.57-16.46], Chi-squared with Yates' correction = 869.71) between nivolumab use and bullous pemphigoid. The signals remained statistically significant after stratifying for sex and age for both pembrolizumab and nivolumab. The signal is supported by 35 case reports in which there was evidence of PD-1 inhibitor use and a pemphigoid adverse event. Conclusion: When prescribing PD-1 inhibitors, physicians should monitor closely for symptoms of bullous pemphigoid.