Background-Merkel cell carcinoma (MCC) is an aggressive skin cancer with a mortality of 33%. Advanced disease at diagnosis is a poor prognostic factor, suggesting that earlier detection may improve outcome. No systematic analysis has been published to define the clinical features that are characteristic of MCC.

IMPORTANCEThe use of artificial intelligence (AI) is expanding throughout the field of medicine. In dermatology, researchers are evaluating the potential for direct-to-patient and clinician decision-support AI tools to classify skin lesions. Although AI is poised to change how patients engage in health care, patient perspectives remain poorly understood.OBJECTIVE To explore how patients conceptualize AI and perceive the use of AI for skin cancer screening. DESIGN, SETTING, AND PARTICIPANTSA qualitative study using a grounded theory approach to semistructured interview analysis was conducted in general dermatology clinics at the Brigham and Women's Hospital and melanoma clinics at the Dana-Farber Cancer Institute. Forty-eight patients were enrolled. Each interview was independently coded by 2 researchers with interrater reliability measurement; reconciled codes were used to assess code frequency. The study was conducted from May 6 to July 8, 2019.MAIN OUTCOMES AND MEASURES Artificial intelligence concept, perceived benefits and risks of AI, strengths and weaknesses of AI, AI implementation, response to conflict between human and AI clinical decision-making, and recommendation for or against AI.RESULTS Of 48 patients enrolled, 26 participants (54%) were women; mean (SD) age was 53.3 (21.7) years. Sixteen patients (33%) had a history of melanoma, 16 patients (33%) had a history of nonmelanoma skin cancer only, and 16 patients (33%) had no history of skin cancer. Twenty-four patients were interviewed about a direct-to-patient AI tool and 24 patients were interviewed about a clinician decision-support AI tool. Interrater reliability ratings for the 2 coding teams were κ = 0.94 and κ = 0.89. Patients primarily conceptualized AI in terms of cognition. Increased diagnostic speed (29 participants [60%]) and health care access (29 [60%]) were the most commonly perceived benefits of AI for skin cancer screening; increased patient anxiety was the most commonly perceived risk (19 [40%]). Patients perceived both more accurate diagnosis (33 [69%]) and less accurate diagnosis (41 [85%]) to be the greatest strength and weakness of AI, respectively. The dominant theme that emerged was the importance of symbiosis between humans and AI (45 [94%]). Seeking biopsy was the most common response to conflict between human and AI clinical decision-making (32 [67%]). Overall, 36 patients (75%) would recommend AI to family members and friends. CONCLUSIONS AND RELEVANCEIn this qualitative study, patients appeared to be receptive to the use of AI for skin cancer screening if implemented in a manner that preserves the integrity of the human physician-patient relationship.

of the lower extremity are often misdiagnosed as cellulitis (aka "pseudocellulitis") and treated with antibiotics and/or hospitalization. There is limited data on the cost and complications from misdiagnosed cellulitis. OBJECTIVE To characterize the national health care burden of misdiagnosed cellulitis in patients admitted for treatment of lower extremity cellulitis. DESIGN, SETTING, AND PARTICIPANTSCross-sectional study using patients admitted from the emergency department (ED) of a large urban hospital with a diagnosis of lower extremity cellulitis between June 2010 and December 2012. Patients who were discharged with a diagnosis of cellulitis were categorized as having cellulitis, while those who were given an alternative diagnosis during the hospital course, on discharge, or within 30 days of discharge were considered to have pseudocellulitis. A literature review was conducted for calculation of large-scale costs and complication rates. We obtained national cost figures from the Medical Expenditure Panel Survey (MEPS), provided by the Agency for Healthcare Research and Quality (AHRQ) for 2010 to calculate the hospitalization costs per year attributed to misdiagnosed lower extremity pseudocellulitis.EXPOSURES The exposed group was composed of patients who presented to and were admitted from the ED with a diagnosis of lower extremity cellulitis. MAIN OUTCOMES AND MEASURESPatient characteristics, hospital course, and complications during and after hospitalization were reviewed for each patient, and estimates of annual costs of misdiagnosed cellulitis in the United States. RESULTSOf 259 patients, 79 (30.5%) were misdiagnosed with cellulitis, and 52 of these misdiagnosed patients were admitted primarily for the treatment of cellulitis. Forty-four of the 52 (84.6%) did not require hospitalization based on ultimate diagnosis, and 48 (92.3%) received unnecessary antibiotics. We estimate cellulitis misdiagnosis leads to 50 000 to 130 000 unnecessary hospitalizations and $195 million to $515 million in avoidable health care spending. Unnecessary antibiotics and hospitalization for misdiagnosed cellulitis are projected to cause more than 9000 nosocomial infections, 1000 to 5000 Clostridium difficile infections, and 2 to 6 cases of anaphylaxis annually.CONCLUSIONS AND RELEVANCE Misdiagnosis of lower extremity cellulitis is common and may lead to unnecessary patient morbidity and considerable health care spending.

IMPORTANCE Pyoderma gangrenosum is an inflammatory neutrophilic dermatosis. Current knowledge of this rare disease is limited owing to a lack of validated diagnostic criteria and large population studies. OBJECTIVE To evaluate the association of age with the clinical presentation and comorbidities of pyoderma gangrenosum. DESIGN, SETTING, AND PARTICIPANTS This was a multicenter retrospective cohort study performed at tertiary academic referral centers in urban settings. Adults (Ն18 years) who were evaluated and diagnosed as having pyoderma gangrenosum at the Brigham and Women's and Massachusetts General Hospitals from 2000 to 2015 and the University of Pennsylvania Health System from 2006 to 2016 were included. MAIN OUTCOMES AND MEASURES Patient demographics, clinical features, medical comorbidities, and treatment. RESULTS Of the 356 validated cases of pyoderma gangrenosum included in the study, 267 (75%) were women and 284 (84.8%) were white. The mean (SD) age at presentation was 51.6 (17.7) years. Pathergy was recorded in 100 patients (28.1%). A total of 238 patients (66.9%) had associated medical comorbidities: inflammatory bowel disease in 146 patients (41.0%); inflammatory arthritis in 73 patients (20.5%); solid organ malignant neoplasms in 23 patients (6.5%); hematologic malignant neoplasms in 21 patients (5.9%); and hematologic disorders, specifically monoclonal gammopathy of undetermined significance, myelodysplastic syndrome, and polycythemia vera in 17 patients (4.8%). When stratified by age, pathergy was more common in patients 65 years or older (36.3% vs 24.3%; P = .02). Inflammatory bowel disease was the only medical comorbidity that was more common in patients younger than 65 years (47.7% vs 26.6%; P < .001), while a number of medical comorbidities were more common in those 65 years or older, including rheumatoid arthritis (13.3% vs 6.2%; P = .03), ankylosing spondylitis (1.8% vs 0%; P = .04), solid organ malignant neoplasms (13.3% vs 3.3%; P < .001), hematologic malignant neoplasms (9.7% vs 4.1%; P = .04), and the aforementioned hematologic disorders (10.6% vs 2.1%; P < .001). CONCLUSIONS AND RELEVANCE Although clinical presentation in this large cohort was similar between different age groups, disease associations varied by age. The findings of this study may allow for a more focused, age-specific evaluation of patients with pyoderma gangrenosum.