PURPOSE: The combination of talimogene laherparepvec (T-VEC) and pembrolizumab previously demonstrated an acceptable safety profile and an encouraging complete response rate (CRR) in patients with advanced melanoma in a phase Ib study. We report the efficacy and safety from a phase III, randomized, double-blind, multicenter, international study of T-VEC plus pembrolizumab (T-VEC-pembrolizumab) versus placebo plus pembrolizumab (placebo-pembrolizumab) in patients with advanced melanoma. METHODS: Patients with stage IIIB-IVM1c unresectable melanoma, naïve to antiprogrammed cell death protein-1, were randomly assigned 1:1 to T-VEC-pembrolizumab or placebo-pembrolizumab. T-VEC was administered at ≤ 4 × 10⁶ plaque-forming unit (PFU) followed by ≤ 4 × 10⁸ PFU 3 weeks later and once every 2 weeks until dose 5 and once every 3 weeks thereafter. Pembrolizumab was administered intravenously 200 mg once every 3 weeks. The dual primary end points were progression-free survival (PFS) per modified RECIST 1.1 by blinded independent central review and overall survival (OS). Secondary end points included objective response rate per mRECIST, CRR, and safety. Here, we report the primary analysis for PFS, the second preplanned interim analysis for OS, and the final analysis. RESULTS: Overall, 692 patients were randomly assigned (346 T-VEC-pembrolizumab and 346 placebo-pembrolizumab). T-VEC-pembrolizumab did not significantly improve PFS (hazard ratio, 0.86; 95% CI, 0.71 to 1.04; P = .13) or OS (hazard ratio, 0.96; 95% CI, 0.76 to 1.22; P = .74) compared with placebo-pembrolizumab. The objective response rate was 48.6% for T-VEC-pembrolizumab (CRR 17.9%) and 41.3% for placebo-pembrolizumab (CRR 11.6%); the durable response rate was 42.2% and 34.1% for the arms, respectively. Grade ≥ 3 treatment-related adverse events occurred in 20.7% of patients in the T-VEC-pembrolizumab arm and in 19.5% of patients in the placebo-pembrolizumab arm. CONCLUSION: T-VEC-pembrolizumab did not significantly improve PFS or OS compared with placebo-pembrolizumab. Safety results of the T-VEC-pembrolizumab combination were consistent with the safety profiles of each agent alone.

Background: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers. Objective: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance. Methods: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined. Results: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier. Conclusions: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients’ benefits.

Background: Early detection of melanoma can be lifesaving but this remains a challenge. Recent diagnostic studies have revealed the superiority of artificial intelligence (AI) in classifying dermoscopic images of melanoma and nevi, concluding that these algorithms should assist a dermatologist’s diagnoses. Objective: The aim of this study was to investigate whether AI support improves the accuracy and overall diagnostic performance of dermatologists in the dichotomous image–based discrimination between melanoma and nevus. Methods: Twelve board-certified dermatologists were presented disjoint sets of 100 unique dermoscopic images of melanomas and nevi (total of 1200 unique images), and they had to classify the images based on personal experience alone (part I) and with the support of a trained convolutional neural network (CNN, part II). Additionally, dermatologists were asked to rate their confidence in their final decision for each image. Results: While the mean specificity of the dermatologists based on personal experience alone remained almost unchanged (70.6% vs 72.4%; P=.54) with AI support, the mean sensitivity and mean accuracy increased significantly (59.4% vs 74.6%; P=.003 and 65.0% vs 73.6%; P=.002, respectively) with AI support. Out of the 10% (10/94; 95% CI 8.4%-11.8%) of cases where dermatologists were correct and AI was incorrect, dermatologists on average changed to the incorrect answer for 39% (4/10; 95% CI 23.2%-55.6%) of cases. When dermatologists were incorrect and AI was correct (25/94, 27%; 95% CI 24.0%-30.1%), dermatologists changed their answers to the correct answer for 46% (11/25; 95% CI 33.1%-58.4%) of cases. Additionally, the dermatologists’ average confidence in their decisions increased when the CNN confirmed their decision and decreased when the CNN disagreed, even when the dermatologists were correct. Reported values are based on the mean of all participants. Whenever absolute values are shown, the denominator and numerator are approximations as every dermatologist ended up rating a varying number of images due to a quality control step. Conclusions: The findings of our study show that AI support can improve the overall accuracy of the dermatologists in the dichotomous image–based discrimination between melanoma and nevus. This supports the argument for AI-based tools to aid clinicians in skin lesion classification and provides a rationale for studies of such classifiers in real-life settings, wherein clinicians can integrate additional information such as patient age and medical history into their decisions.

Background: An increasing number of studies within digital pathology show the potential of artificial intelligence (AI) to diagnose cancer using histological whole slide images, which requires large and diverse data sets. While diversification may result in more generalizable AI-based systems, it can also introduce hidden variables. If neural networks are able to distinguish/learn hidden variables, these variables can introduce batch effects that compromise the accuracy of classification systems. Objective: The objective of the study was to analyze the learnability of an exemplary selection of hidden variables (patient age, slide preparation date, slide origin, and scanner type) that are commonly found in whole slide image data sets in digital pathology and could create batch effects. Methods: We trained four separate convolutional neural networks (CNNs) to learn four variables using a data set of digitized whole slide melanoma images from five different institutes. For robustness, each CNN training and evaluation run was repeated multiple times, and a variable was only considered learnable if the lower bound of the 95% confidence interval of its mean balanced accuracy was above 50.0%. Results: A mean balanced accuracy above 50.0% was achieved for all four tasks, even when considering the lower bound of the 95% confidence interval. Performance between tasks showed wide variation, ranging from 56.1% (slide preparation date) to 100% (slide origin). Conclusions: Because all of the analyzed hidden variables are learnable, they have the potential to create batch effects in dermatopathology data sets, which negatively affect AI-based classification systems. Practitioners should be aware of these and similar pitfalls when developing and evaluating such systems and address these and potentially other batch effect variables in their data sets through sufficient data set stratification.

Objective. To investigate microRNA (miRNA) that is potentially implicated in primary Sjögren syndrome (pSS)–related salivary hypofunction in labial salivary glands and to study miRNA-mediated mechanisms underlying oral dryness and altered rheology, focusing on the mucin O-glycosylation pathway. Methods. We performed miRNA expression profiling in minor salivary gland samples of patients with pSS presenting a different impairment in their unstimulated salivary flow rate. A computational in silico analysis was performed to identify genes and pathways that might be modulated by the deregulated miRNA that we had identified. To confirm in silico analysis, expression levels of genes encoding for glycosyltransferases and glycan-processing enzymes were investigated using Human Glycosylation-RT² Profiler PCR Array. Results. Among 754 miRNA analyzed, we identified 126 miRNA that were significantly deregulated in pSS compared to controls, with a trend that was inversely proportional with the impairment of salivary flow rates. An in silico approach pinpointed that several upregulated miRNA in patients with pSS target important genes in the mucin O-glycosylation. We confirmed this prediction by quantitative real-time PCR, highlighting the downregulation of some glycosyltransferase and glycosidase genes in pSS samples compared to controls, such as GALNT1, responsible for mucin-7 glycosylation. Conclusion. Collectively, our data suggest that the expression of different predicted miRNA-target genes in the mucin type O-glycan biosynthesis pathway is altered in pSS patients with low salivary flow and that the miRNA expression profile could influence the glycosidase expression levels and consequently the rheology in pSS.