Acute febrile neutrophilic dermatosis (Sweet syndrome) in acute myeloid leukemia patients: a 28-year institutional experience.

INTRODUCTION: Sweet syndrome (SS) is well-known to be associated with underlying hematologic malignancies. The incidence and qualities of SS among novel targeted therapies for acute myeloid leukemia (AML) have not yet been described. METHODS: Through retrospective review of 19432 patients diagnosed with acute/chronic leukemia or myelodysplastic syndromes/ myeloproliferative neoplasms (MDS+/-MPN) over 28 years, we calculated the incidence of SS in the setting of select hematologic malignancies and described the clinicopathologic characteristics of SS in patients with onset of SS after initiation of novel AML-targeted therapies. RESULTS: Overall incidence of SS was 0.36% (95% CI: 0.27% - 0.45%), which was significantly higher among patients with AML (50/5248, 0.94%; 95% CI: 0.71% - 1.25%). Nine AML patients were on 4 classes of novel targeted treatments - IDH1/2 inhibitor alone, FLT3 inhibitor, IDH2 and DOT1L inhibitor, and anti-CD33 therapy. In therapies inducing myeloid blast differentiation, SS occurred at later onset following treatment. CONCLUSIONS: In AML patients with fever and unusual skin lesions, physicians may consider SS earlier which may shorten time to diagnosis. Future assessments of SS among patients treated with novel therapies for AML and molecular studies of biopsies may help further explain this dermatologic adverse event with earlier diagnosis and management of neutrophilic dermatoses in these patients.

Prospective validation of dermoscopy-based open-source artificial intelligence for melanoma diagnosis (PROVE-AI study).

The use of artificial intelligence (AI) has the potential to improve the assessment of lesions suspicious of melanoma, but few clinical studies have been conducted. We validated the accuracy of an open-source, non-commercial AI algorithm for melanoma diagnosis and assessed its potential impact on dermatologist decision-making. We conducted a prospective, observational clinical study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. The primary aim was to assess the reliability of ADAE's sensitivity at a predefined threshold of 95%. Patients who had consented for a skin biopsy to exclude melanoma were eligible. Dermatologists also estimated the probability of melanoma and indicated management choices before and after real-time exposure to ADAE scores. All lesions underwent biopsy. Four hundred thirty-five participants were enrolled and contributed 603 lesions (95 melanomas). Participants had a mean age of 59 years, 54% were female, and 96% were White individuals. At the predetermined 95% sensitivity threshold, ADAE had a sensitivity of 96.8% (95% CI: 91.1-98.9%) and specificity of 37.4% (95% CI: 33.3-41.7%). The dermatologists' ability to assess melanoma risk significantly improved after ADAE exposure (AUC 0.7798 vs. 0.8161, p = 0.042). Post-ADAE dermatologist decisions also had equivalent or higher net benefit compared to biopsying all lesions. We validated the accuracy of an open-source melanoma AI algorithm and showed its theoretical potential for improving dermatology experts' ability to evaluate lesions suspicious of melanoma. Larger randomized trials are needed to fully evaluate the potential of adopting this AI algorithm into clinical workflows.

Dermatologic adverse events associated with IDH inhibitors ivosidenib and enasidenib for the treatment of acute myeloid leukemia.

Two novel inhibitors of isocitrate dehydrogenase (IDHi), ivosidenib and enasidenib, significantly improve survival for AML patients with an IDH1 or IDH2 mutation, respectively; however, rash has been reported as a toxicity of IDHi. The objective of our study is to determine the incidence, grade, clinical, and histopathologic features of dermatologic adverse events (DAEs) secondary to IDHi. This study is a retrospective analysis of 169 patients who were treated with either ivosidenib or enasidenib as single agent or in combination with induction chemotherapy at Memorial Sloan Kettering Cancer Center from January 1, 2013 to April 1, 2021. DAEs thought to be possibly, probably, or definitely related to IDHi occurred in 55 of 169 patients [0.32, 95 % CI: 0.25 - 0.40]. Of a total 81 DAEs observed, the most common DAE types were inflammatory dermatoses (27 %); cutaneous vascular manifestations (8%); cutaneous infections (7%); and pruritus (2%). Notably, 50% of infections and 15.5% of rashes were high grade. Knowledge of these findings is critical to optimize the treatment and quality of life of patients with AML on IDHi.