A phase 2 open-label study of cemiplimab in patients with advanced cutaneous squamous cell carcinoma (EMPOWER-CSCC-1): Final long-term analysis of Groups 1, 2, and 3, and primary analysis of fixed-dose treatment Group 6.

BACKGROUND: In the phase 2 EMPOWER-CSCC-1 study (NCT02760498), cemiplimab demonstrated antitumor activity against metastatic (mCSCC) and locally advanced cutaneous squamous cell carcinoma (laCSCC). OBJECTIVES: To report final analysis of weight-based cemiplimab in mCSCC and laCSCC (Groups 1 and 2), fixed-dose cemiplimab in mCSCC (Group 3), and primary analysis of fixed-dose cemiplimab in mCSCC/laCSCC (Group 6). METHODS: Patients received cemiplimab (3 mg/kg intravenously [IV] every 2 weeks [Groups 1 and 2]) or cemiplimab (350 mg IV [Groups 3 and 6]) every 3 weeks. The primary endpoint was objective response rate (ORR). Duration of response (DOR) and progression-free survival (PFS) are presented per protocol, according to post-hoc sensitivity analyses that only include the period of protocol-mandated imaging assessments. RESULTS: At 42.5 months, ORR for Groups 1-3 (n=193) was 47.2%, estimated 12-month DOR was 88.3%, and median PFS was 26.0 months. At 8.7 months, ORR for Group 6 (n=165 patients) was 44.8%; median DOR and median PFS were not reached. Serious treatment-emergent adverse event rates (grade ≥3) were Groups 1-3: 31.1% and Group 6: 34.5%. LIMITATIONS: Non-randomized study, non-survival primary endpoint. CONCLUSION: EMPOWER-CSCC-1 provides the largest prospective data on long-term efficacy and safety for anti-programmed cell death-1 therapy in advanced CSCC.

Prospective multicenter study using artificial intelligence to improve dermoscopic melanoma diagnosis in patient care.

BACKGROUND: Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. METHODS: Therefore, we assessed "All Data are Ext" (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e., providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. RESULTS: Overall, the AI shows higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p = 4.0e-145), obtaining a higher sensitivity (0.921, 95% CI 0.900-0.942 vs. 0.734, 95% CI 0.701-0.770; p = 3.3e-165) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p = 3.3e-165). CONCLUSION: As the algorithm exhibits a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists, particularly in diagnosing challenging cases.

Melanoma is a type of skin cancer that can spread to other parts of the body, often resulting in death. Early detection improves survival rates. Computational tools that use artificial intelligence (AI) can be used to detect melanoma. However, few studies have checked how well the AI works on real-world data obtained from patients. We tested a previously developed AI tool on data obtained from eight different hospitals that used different types of cameras, which also included images taken of rare melanoma types and from a range of different parts of the body. The AI tool was more likely to correctly identify melanoma than dermatologists. This AI tool could be used to help dermatologists diagnose melanoma, particularly those that are difficult for dermatologists to diagnose.

General practitioners' perspectives on statutory skin cancer screening-A questionnaire-based cross-sectional survey in Germany.

BACKGROUND: In Germany, skin cancer screening (SCS) is available free of charge every two years to all those with statutory health insurance over the age of 35. General Practitioners (GP) can carry out the screening if they have completed an 8-hour training course. GPs play a crucial role in the implementation of SCS and act as gatekeepers between initial patient contact and referral to dermatologists. OBJECTIVE: To record how comprehensively GPs carry out SCS in terms of patient information and body examination, as well as to explore GPs opinions on the feasibility of SCS. METHODS: A cross-sectional survey was conducted. A questionnaire was sent to GPs with permission to perform SCS in two regions of Germany (Bavaria and Saxony) between August and September 2021. Data were analyzed using descriptive analysis. Subgroup analysis was performed according to regions (federal state, location of physician´s office), professional experience (experience in years, number of monthly screenings, age) and gender. Open questions were evaluated using qualitative content analysis. RESULTS: In the survey, 204 GPs responded. Genitalia (40.7%, 83/203), anal fold (62.3%, 127/204) and oral mucosa (66.7%, 136/204) were the least examined body regions during screening. Information on risks (false-positive findings: 18.6%, 38/203; false-negative findings: 13.2%, 27/203; overdiagnosis: 7.8%, 16/203) and benefits (48.0%, 98/202) were not always provided. GPs who performed screenings more frequently were more likely to provide information about the benefits of SCS (p<0.001; >10 vs. <5 screenings per month). Opinions were provided on uncertainties, knowledge requirements, structural and organizational requirements of SCS, SCS training and evaluation. The organization and remuneration of the SCS programme was seen as a barrier to implementation. GPs expressed uncertainties especially in unclear findings and in dermatoscopy. CONCLUSION: Uncertainties in the implementation of the SCS should be addressed by offering refresher courses. Good networking between GPs and dermatologists is essential to improve SCS quality.

Early versus late response to PD-1-based immunotherapy in metastatic melanoma.

BACKGROUND: Immune checkpoint inhibition (ICI) currently is the most effective treatment to induce durable responses in metastatic melanoma. The aims of this study are the characterization of patients with early, late and non-response to ICI and analysis of survival outcomes in a real-world patient cohort. METHODS: Patients who received PD-1-based immunotherapy for non-resectable stage-IV melanoma in any therapy line were selected from the prospective multicenter real-world DeCOG study ADOREG-TRIM (NCT05750511). Patients showing complete (CR) or partial (PR) response already during the first 3 months of treatment (Early Responders, EarlyR) were compared to patients showing CR/PR at a later time (Late Responders, LateR), a stable disease (SD) and to patients showing progressive disease (Non-Responders, NonR). RESULTS: Of 522 patients, 8.2 % were EarlyR (n = 43), 19.0 % were LateR (n = 99), 37.0 % had a SD (n = 193) and 35.8 % were NonR (n = 187). EarlyR, LateR and SD patients had comparable baseline characteristics. Multivariate logbinomial regression analyses adjusted for age and sex revealed positive tumor PD-L1 (RR=1.99, 95 %-CI=1.14-3.46, p = 0.015), and normal serum CRP (RR=1.59, 95 %-CI=0.93-2.70, p = 0.036) as independently associated with the achievement of an early response compared to NonR. The median progression-free and overall survival was 46.0 months (95 % CI 19.1; NR) and 47.8 months (95 %-CI 36.9; NR) for EarlyR, NR (95 %-CI NR; NR) for LateR, 8.1 months (7.0; 10.4) and 35.4 months (29.2; NR) for SD, and 2.0 months (95 %-CI 1.9; 2.1) and 6.1 months (95 %-CI 4.6; 8.8) for NonR patients. CONCLUSION: Less than 10 % of metastatic melanoma patients achieved an early response during the first 3 months of PD-1-based immunotherapy. Early responders were not superior to late responders in terms of response durability and survival.

Influence of adjuvant therapies on organ-specific recurrence of cutaneous melanoma: A multicenter study on 1383 patients of the prospective DeCOG registry ADOReg.

This study investigated whether adjuvant treatments in stage III cutaneous melanoma (CM) influenced patterns of recurrence. Patients with primary (n = 1033) or relapsed CM (n = 350) who received adjuvant therapies with Nivolumab (N), Pembrolizumab (P), or Dabrafenib and Trametinib (D + T) were extracted from the prospective multicenter real-world skin cancer registry ADOReg. Endpoints were progression-free survival (PFS), distant metastasis-free survival (DMFS), organ-specific DMFS, and overall survival (OS). For primary cases, D + T indicated an improved PFS (1- and 2-year PFS: 90.9%; 82.7%) as compared to P (81.0%, 73.9%; p = .0208), or N (83.8%, 75.2%; p = .0539). BRAF-mutated(mut) CM demonstrated significantly lower PFS (p = .0022) and decreased DMFS (p = .0580) when treated with immune checkpoint inhibitor (ICI) instead of D + T. Besides, NRAS-mut CM tended to perform worse than wt CM upon ICI (PFS: p = .1349; DMFS: p = .0540). OS was similar between the groups. Relapsed cases showed decreased PFS, DMFS, and OS in comparison to primary (all: p < .001), without significant differences between the subgroups. Organ-specific DMFS was significantly altered for primary cases with bone (p = .0367) or brain metastases (p = .0202). In relapsed CM, the frequency of liver (D + T: 1.5%; P: 12%; N: 9%) and LN metastases (D + T: 1.5%; P: 12%; N: 10.2%) was significantly lower with adjuvant D + T than ICI. NRAS-mut CM showed increased recurrence in primary and relapsed cases. These data show that adjuvant D + T is superior to ICI in primary BRAF-mut CM.

Shortened progression free and overall survival to immune-checkpoint inhibitors in BRAF-, RAS- and NF1- ("Triple") wild type melanomas.

BACKGROUND: Melanomas lacking mutations in BRAF, NRAS and NF1 are frequently referred to as "triple wild-type" (tWT) melanomas. They constitute 5-10 % of all melanomas and remain poorly characterized regarding clinical characteristics and response to therapy. This study investigates the largest multicenter collection of tWT-melanomas to date. METHODS: Targeted next-generation sequencing of the TERT promoter and 29 melanoma-associated genes were performed on 3109 melanoma tissue samples of the prospective multicenter study ADOREG/TRIM of the DeCOG revealing 292 patients suffering from tWT-melanomas. Clinical characteristics and mutational patterns were analyzed. As subgroup analysis, we analyzed 141 tWT-melanoma patients receiving either anti-CTLA4 plus anti-PD1 or anti PD1 monotherapy as first line therapy in AJCC stage IV. RESULTS: 184 patients with cutaneous melanomas, 56 patients with mucosal melanomas, 34 patients with acral melanomas and 18 patients with melanomas of unknown origin (MUP) were included. A TERT promoter mutation could be identified in 33.2 % of all melanomas and 70.5 % of all tWT-melanomas harbored less than three mutations per sample. For the 141 patients with stage IV disease, mPFS independent of melanoma type was 6.2 months (95 % CI: 4-9) and mOS was 24.8 months (95 % CI: 14.2-53.4) after first line anti-CTLA4 plus anti-PD1 therapy. After first-line anti-PD1 monotherapy, mPFS was 4 months (95 %CI: 2.9-8.5) and mOS was 29.18 months (95 % CI: 17.5-46.2). CONCLUSIONS: While known prognostic factors such as TERT promoter mutations and TMB were equally distributed among patients who received either anti-CTLA4 plus anti-PD1 combination therapy or anti-PD1 monotherapy as first line therapy, we did not find a prolonged mPFS or mOS in either of those. For both therapy concepts, mPFS and mOS were considerably shorter than reported for melanomas with known oncogene mutations.

Optimizing immune checkpoint blockade in metastatic uveal melanoma: exploring the association of overall survival and the occurrence of adverse events.

Introduction: Despite recent advancements in the treatment of metastatic uveal melanoma (UM), the availability of further treatment options remains limited and the prognosis continues to be poor in many cases. In addition to tebentafusp, immune checkpoint blockade (ICB, PD-1 (+/-) CTLA-4 antibodies) is commonly used for metastatic UM, in particular in HLA-A 02:01-negative patients. However, ICB comes at the cost of potentially severe immune-related adverse events (irAE). Thus, the selection of patient groups that are more likely to benefit from ICB is desirable. Methods: In this analysis, 194 patients with metastatic UM undergoing ICB were included. Patients were recruited from German skin cancer sites and the ADOReg registry. To investigate the association of irAE occurrence with treatment response, progression-free survival (PFS), and overall survival (OS) two cohorts were compared: patients without irAE or grade 1/2 irAE (n=137) and patients with grade 3/4 irAE (n=57). Results: In the entire population, the median OS was 16.4 months, and the median PFS was 2.8 months. Patients with grade 3/4 irAE showed more favorable survival than patients without or grade 1/2 irAE (p=0.0071). IrAE occurred in 44.7% (87/194), and severe irAE in 29.4% (57/194) of patients. Interestingly, irColitis and irHepatitis were significantly associated with longer OS (p=0.0031 and p=0.011, respectively). Conclusions: This data may indicate an association between irAE and favorable survival outcomes in patients with metastatic UM undergoing ICB treatment and suggests that a reduced tolerance to tumor antigens could be linked to reduced tolerance to self-antigens.

Gene expression profiling in porocarcinoma indicates heterogeneous tumor development and substantiates poromas as precursor lesions.

BACKGROUND AND OBJECTIVES: Malignant sweat gland tumors are rare, with the most common being eccrine porocarcinoma (EP). Approximately 18% of benign eccrine poroma (EPO) transit to EP. Previous research has provided first insights into the mutational landscape of EP. However, only few studies have performed gene expression analyses. This leaves a gap in the understanding of EP biology and potential drivers of malignant transformation from EPO to EP. METHODS: Transcriptome profiling of 23 samples of primary EP and normal skin (NS). Findings from the EP samples were then tested in 17 samples of EPO. RESULTS: Transcriptome profiling revealed diversity in gene expression and indicated biologically heterogeneous sub-entities as well as widespread gene downregulation in EP. Downregulated genes included CD74, NDGR1, SRRM2, CDC42, ANXA2, KFL9 and NOP53. Expression levels of CD74, NDGR1, SRRM2, ANXA2, and NOP53 showed a stepwise-reduction in expression from NS via EPO to EP, thus supporting the hypothesis that EPO represents a transitional state in EP development. CONCLUSIONS: We demonstrated that EP is molecularly complex and that evolutionary trajectories correspond to tumor initiation and progression. Our results provide further evidence implicating the p53 axis and the EGFR pathway. Larger samples are warranted to confirm our findings.

Comparison of Extended Skin Cancer Screening Using a Three-Step Advanced Imaging Programme vs. Standard-of-Care Examination in a High-Risk Melanoma Patient Cohort.

Modern diagnostic procedures, such as three-dimensional total body photography (3D-TBP), digital dermoscopy (DD), and reflectance confocal microscopy (RCM), can improve melanoma diagnosis, particularly in high-risk patients. This study assessed the benefits of combining these advanced imaging techniques in a three-step programme in managing high-risk patients. This study included 410 high-risk melanoma patients who underwent a specialised imaging consultation in addition to their regular skin examinations in outpatient care. At each visit, the patients underwent a 3D-TBP, a DD for suspicious findings, and an RCM for unclear DD findings. The histological findings of excisions initiated based on imaging consultation and outpatient care were compared. Imaging consultation detected sixteen confirmed melanomas (eight invasive and eight in situ) in 39 excised pigmented lesions. Outpatient care examination detected seven confirmed melanomas (one invasive and six in situ) in 163 excised melanocytic lesions. The number needed to excise (NNE) in the imaging consultation was significantly lower than that in the outpatient care (2.4 vs. 23.3). The NNE was 2.6 for DD and 2.3 for RCM. DD, 3D-TBP, or RCM detected melanomas that were not detected by the other imaging methods. The three-step imaging programme improves melanoma detection and reduces the number of unnecessary excisions in high-risk patients.

Susceptibility of Melanoma Cells to Targeted Therapy Correlates with Protection by Blood Neutrophils.

Elevated levels of peripheral blood and tumor tissue neutrophils are associated with poorer clinical response and therapy resistance in melanoma. The underlying mechanism and the role of neutrophils in targeted therapy is still not fully understood. Serum samples of patients with advanced melanoma were collected and neutrophil-associated serum markers were measured and correlated with response to targeted therapy. Blood neutrophils from healthy donors and patients with advanced melanoma were isolated, and their phenotypes, as well as their in vitro functions, were compared. In vitro functional tests were conducted through nonadherent cocultures with melanoma cells. Protection of melanoma cell lines by neutrophils was assessed under MAPK inhibition. Blood neutrophils from advanced melanoma patients exhibited lower CD16 expression compared to healthy donors. In vitro, both healthy-donor- and patient-derived neutrophils prevented melanoma cell apoptosis upon dual MAPK inhibition. The effect depended on cell-cell contact and melanoma cell susceptibility to treatment. Interference with protease activity of neutrophils prevented melanoma cell protection during treatment in cocultures. The negative correlation between neutrophils and melanoma outcomes seems to be linked to a protumoral function of neutrophils. In vitro, neutrophils exert a direct protective effect on melanoma cells during dual MAPK inhibition. This study further hints at a crucial role of neutrophil-related protease activity in protection.

Personalized identification and characterization of genome-wide gene expression differences between patient-matched intracranial and extracranial melanoma metastasis pairs.

Melanoma is the most serious type of skin cancer that frequently spreads to other organs of the human body. Especially melanoma metastases to the brain (intracranial metastases) are hard to treat and a major cause of death of melanoma patients. Little is known about molecular alterations and altered mechanisms that distinguish intra- from extracranial melanoma metastases. So far, almost all existing studies compared intracranial metastases from one set of patients to extracranial metastases of an another set of melanoma patients. This neglects the important facts that each melanoma is highly individual and that intra- and extracranial melanoma metastases from the same patient are more similar to each other than to melanoma metastases from other patients in the same organ. To overcome this, we compared the gene expression profiles of 16 intracranial metastases to their corresponding 21 patient-matched extracranial metastases in a personalized way using a three-state Hidden Markov Model (HMM) to identify altered genes for each individual metastasis pair. This enabled three major findings by considering the predicted gene expression alterations across all patients: (i) most frequently altered pathways include cytokine-receptor interaction, calcium signaling, ECM-receptor interaction, cAMP signaling, Jak-STAT and PI3K/Akt signaling, (ii) immune-relevant signaling pathway genes were downregulated in intracranial metastases, and (iii) intracranial metastases were associated with a brain-like phenotype gene expression program. Further, the integration of all differentially expressed genes across the patient-matched melanoma metastasis pairs led to a set of 103 genes that were consistently down- or up-regulated in at least 11 of the 16 of the patients. This set of genes contained many genes involved in the regulation of immune responses, cell growth, cellular signaling and transport processes. An analysis of these genes in the TCGA melanoma cohort showed that the expression behavior of 11 genes was significantly associated with survival. Moreover, a comparison of the 103 genes to three closely related melanoma metastasis studies revealed a core set of eight genes that were consistently down- or upregulated in intra- compared to extracranial metastases in at least two of the three related studies (down: CILP, DPT, FGF7, LAMP3, MEOX2, TMEM119; up: GLDN, PMP2) including FGF7 that was also significantly associated with survival. Our findings contribute to a better characterization of genes and pathways that distinguish intra- from extracranial melanoma metastasis and provide important hints for future experimental studies to identify potential targets for new therapeutic approaches.

An Online Decision Aid for Patients With Metastatic Melanoma.

BACKGROUND: Treatment decisions in metastatic melanoma (MM) are highly dependent on patient preferences and require the patients' involvement. The complexity of treatment options with their individual advantages and disadvantages is often overwhelming. We therefore developed an online patient decision aid (PtDA) to facilitate shared decision making (SDM). METHODS: To evaluate the PtDA we conducted a two-armed, twocenter, prospective, open randomized controlled trial with MM patients who were facing a decision about first-line treatment. The patients were allotted randomly in a 1:1 ratio to an intervention group (IG) with access to the PtDA before discussion with a physician or to a control group (CG) without access to the PtDA. The primary endpoint was knowledge about the options for first-line treatment (multiple-choice test, 10 items, range 0-40 points). The secondary endpoints were the SDM (third-party ratings of audio recordings of the treatment discussions) and satisfaction with the decision at the follow-up visit. RESULTS: Of the 128 randomized patients, 120 completed the baseline questionnaire and were analyzed (59% male, median age 66 years). The primary endpoint, i.e., the mean difference in knowledge after discussion with a physician, differed significantly between the IG and the CG (-3.22, 95% CI [-6.32; -0.12], p = 0.042). No differences were found for the secondary endpoints, SDM and satisfaction with the decision. The patients in the IG rated the PtDA as very useful. CONCLUSION: The PtDA improved the knowledge of patients with MM about the options for treatment. Both groups were highly satisfied with their treatment decisions. However, additional physician training seems necessary to promote SDM.

Second-line therapies for steroid-refractory immune-related adverse events in patients treated with immune checkpoint inhibitors.

BACKGROUND: Immune checkpoint inhibitors (ICI) induce adverse events (irAEs) that do not respond to steroids, i.e. steroid-refractory (sr) irAEs, and irAEs in which steroids cannot be tapered, i.e. steroid-dependent (sd) irAEs, in about 10% of cases. An evidence-based analysis of the effectiveness of second-line immunosuppressive agents with regard to irAE and tumor control is lacking. METHODS: The international web-based Side Effect Registry Immuno-Oncology (SERIO; http://serio-registry.org) is a collaborative initiative with the Paul-Ehrlich-Institute to document rare, severe, complex or therapy-refractory immunotherapy-induced side effects. The registry was queried on August 1, 2023 for cases of irAEs which were treated with second-line therapies. RESULTS: From a total of 1330 cases, 217 patients (16.3%) received 249 second-line therapies. A total of 19 different second-line therapies were employed, including TNF-alpha antagonists (46.5%), intravenous immunoglobulins (IVIG; 19.1%), mycophenolate mofetil (15.9%), and methotrexate (3.6%). Therapy choices were determined by the type of irAE. The time to onset of sr-/sd-irAEs after ICI initiation did not consistently differ from steroid-responsive irAEs. While 74.3% of sr-/sd-irAEs resolved and 13.1% had improved, 4.3% persisted, 3.9% resulted in permanent sequelae, and 4.3% in death with ongoing symptoms. Infliximab exhibited potential for earlier symptom improvement compared to mycophenolate mofetil or IVIG. Tumor response in patients with second-line treated sd-/sr-irAE was similar to patients with irAEs treated with steroids only. CONCLUSION: Several second-line therapies are effective against sr-/sd-irAEs, the second-line therapies show no clear negative impact on tumor response, and infliximab shows potential for faster improvement of symptoms. However, prospective comparative data are needed.

Network-based analysis of heterogeneous patient-matched brain and extracranial melanoma metastasis pairs reveals three homogeneous subgroups.

Melanoma, the deadliest form of skin cancer, can metastasize to different organs. Molecular differences between brain and extracranial melanoma metastases are poorly understood. Here, promoter methylation and gene expression of 11 heterogeneous patient-matched pairs of brain and extracranial metastases were analyzed using melanoma-specific gene regulatory networks learned from public transcriptome and methylome data followed by network-based impact propagation of patient-specific alterations. This innovative data analysis strategy allowed to predict potential impacts of patient-specific driver candidate genes on other genes and pathways. The patient-matched metastasis pairs clustered into three robust subgroups with specific downstream targets with known roles in cancer, including melanoma (SG1: RBM38, BCL11B, SG2: GATA3, FES, SG3: SLAMF6, PYCARD). Patient subgroups and ranking of target gene candidates were confirmed in a validation cohort. Summarizing, computational network-based impact analyses of heterogeneous metastasis pairs predicted individual regulatory differences in melanoma brain metastases, cumulating into three consistent subgroups with specific downstream target genes.

High response rate with extended dosing of cemiplimab in advanced cutaneous squamous cell carcinoma.

BACKGROUND: Cemiplimab (Libtayo®), a human monoclonal immunoglobulin G4 antibody to the programmed cell death-1 receptor, is approved for the treatment of patients with advanced cutaneous squamous cell carcinoma (CSCC), who are not candidates for curative surgery or curative radiation, using an every-3-weeks (Q3W) dosing interval. Pharmacokinetic modeling indicated that Ctrough of extended intravenous dosing of 600 mg every 4 weeks (Q4W) would be comparable to the approved intravenous dosage of 350 mg Q3W. We examined the efficacy, pharmacokinetics, and safety of cemiplimab dosed Q4W. METHODS: In this open-label, phase II trial (ClinicalTrials.gov identifier NCT02760498), the cohort of patients ≥18 years old with advanced CSCC received cemiplimab 600 mg intravenously Q4W for up to 48 weeks. Tumor measurements were recorded every 8 weeks. The primary endpoint was objective response rate by independent central review. RESULTS: Sixty-three patients with advanced CSCC were treated with cemiplimab. The median duration of follow-up was 22.4 months (range: 1.0-39.8). An objective response was observed in 39 patients (62%; 95% CI: 48.8% to 73.9%), with 22% of patients (n=14) achieving complete response and 40% (n=25) achieving partial response. The most common treatment-emergent adverse events were diarrhea, pruritus, and fatigue. CONCLUSIONS: Extended dosing of cemiplimab 600 mg intravenously Q4W exhibited substantial antitumor activity, rapid and durable responses, and an acceptable safety profile in patients with advanced CSCC. These results confirm that cemiplimab is a highly active therapy for advanced CSCC. Additional data would help ascertain the benefit-risk profile for the 600 mg intravenous dosing regimen compared with the approved regimen.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics.

Importance: The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. Objective: To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. Design, Setting, and Participants: This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. Exposures: All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. Results: The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). Conclusions and Relevance: The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Effects of an immunosuppressive therapy on the efficacy of immune checkpoint inhibition in metastatic melanoma - An analysis of the prospective skin cancer registry ADOREG.

BACKGROUND: The impact of immunosuppressive therapy (IST) on immune-checkpoint inhibition (ICI) is unclear. METHODS: Patients with unresectable advanced melanoma (MM) treated with ICI in the years 2011-2020 were identified from the prospective multicenter German skin cancer registry ADOREG. Patients with IST within 60 days before, or within 30 days after start of ICI were compared to patients without IST. End points were disease control rate (DCR), overall survival (OS) and progression-free survival (PFS) determined by Kaplan-Meier method. Prognostic factors were evaluated in a Cox regression model. RESULTS: Of 814 patients treated with ICI, 73 (9%) received concomitant IST, mainly steroids. Patients with brain metastases (BM) received IST more frequently (n = 34/130 patients; 26%), than patients without BM (39/684 patients; 6%). In patients without BM, IST initiated before, but not IST initiated after start of ICI was significantly associated with worse PFS (univariate hazard ratio (HR) 2.59, 95% confidence interval (95%-CI) 1.07-6.28, p = 0.035; multivariate HR 3.48, 95%-CI 1.26-9.6, p = 0.016). There was no association between IST and OS or DCR. In patients with BM, IST initiated before, but not after start of ICI was significantly associated with worse OS (univariate HR 2.06, 95%-CI 1.07-3.95, p = 0.031; multivariate HR 5.91, 95%-CI 1.74-20.14, p = 0.004). There was no association between IST and PFS or DCR. CONCLUSION: Patients receiving IST 60 days before start of ICI showed a tendency to an impaired therapy outcome. IST initiated within 30 days after start of ICI, mainly due to early side effects, did not affect the efficacy of ICI therapy.