Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images.

BACKGROUND: Skin cancer is the most common cancer in the United States. Current estimates are that one in five Americans will develop skin cancer in their lifetime. A skin cancer diagnosis is challenging for dermatologists requiring a biopsy from the lesion and histopathological examinations. In this article, we used the HAM10000 dataset to develop a web application that classifies skin cancer lesions. METHOD: This article presents a methodological approach that utilizes dermoscopy images from the HAM10000 dataset, a collection of 10015 dermatoscopic images collected over 20 years from two different sites, to improve the diagnosis of pigmented skin lesions. The study design involves image pre-processing, which includes labelling, resizing, and data augmentation techniques to increase the instances of the dataset. Transfer learning, a machine learning technique, was used to create a model architecture that includes EfficientNET-B1, a variant of the baseline model EfficientNET-B0, with a global average pooling 2D layer and a softmax layer with 7 nodes added on top. The results of the study offer a promising method for dermatologists to improve their diagnosis of pigmented skin lesions. RESULTS: The model performs best in detecting melanocytic nevi lesions with an F1 score of 0.93. The F1 score for Actinic Keratosis, Basal Cell Carcinoma, Benign Keratosis, Dermatofibroma, Melanoma, and Vascular lesions was consecutively 0.63, 0.72, 0.70, 0.54, 0.58, and 0.80. CONCLUSIONS: We classified seven distinct skin lesions in the HAM10000 dataset with an EfficientNet model reaching an accuracy of 84.3%, which provides a promising outlook for further development of more accurate models.

Changes of symptoms of eating disorders (ED) and their related psychological health issues during the COVID-19 pandemic: a systematic review and meta-analysis.

BACKGROUND: The COVID-19 pandemic and its related social restrictions have profoundly affected people's mental health. It can be assumed that symptomatic behaviors and mental health of individuals with eating disorders (ED) deteriorated during this time. To get a thorough overview, we conducted a systematic review and meta-analysis with the following aims: First, to provide a comprehensive overview of symptoms of ED during the COVID-19-related confinement; second, to identify psychological mechanisms which impacted the emergence and maintenance of ED symptoms; third, to describe changes of daily routine and changes of access to healthcare in individuals with ED during confinement. METHODS: We searched Embase, PubMed, and Scopus databases for observational studies published between January 1st, 2020, to July 1st, 2021, which investigated the symptomatology of ED during the COVID-19 pandemic. RESULTS: After the screening, 13 studies with 7848 participants were included in the present systematic review and meta-analysis. The overall pooled prevalence of exacerbation of binge eating, food restriction, purging behaviors, and concerns about food intake in the pooled sample of 7848 was 59.65% (95% CI: 49.30%; 69.60%), and the overall prevalence of improved symptoms of ED in the pooled sample of 741 individuals was 9.37% (95% CI: 3.92%; 16.57%). Furthermore, COVID-19-related social restrictions negatively impacted the psychological health, daily routines, and physical activity of individuals with ED. More specifically, symptoms of anxiety and depression related to ED were increased significantly over time. However, there were also positive aspects to the COVID-19 pandemic. The main positive consequences included more emotional support from the family, less pressure to engage in social activities, and more flexible meal planning. Individuals with ED reported having difficulties getting access to healthcare centers and using telemedicine. They also found a hard time communicating via online sessions. CONCLUSIONS: According to our interpretation, based on the data included in the systematic review and meta-analysis, the COVID-19 pandemic and its related social restrictions detrimentally impacted the mental health of majority of individuals with ED. Limited and impaired access to healthcare interventions appeared to have further exacerbated mental health issues of individuals with ED. Given this background, it seems that individuals with ED demand more attention during the COVID-19 crisis, and it is necessary to ensure that their course of treatment remains uninterrupted.

The COVID-19 pandemic and the consequent lockdowns have significantly impacted people's mental health and mental status worldwide. Remarkably, people with pre-existing illnesses (e.g., eating disorders) were affected by the COVID-19-related restrictions. Thus, gathering information and data would significantly help researchers and physicians provide better future therapy and support for people with ED. Moreover, the use of online surveys to evaluate the mental status of people with ED has grown hugely in the era of the COVID-19 pandemic, which could be used as a promising way of communicating with these people in the future. Considering the growing number of studies that reported the status of individuals with ED in the COVID-19 era, we aimed to conduct a comprehensive review to summarize the current literature. Our findings show that, of all individuals participating in the surveys, 59.65% of them experienced exacerbations in their ED symptoms and 9.37% experienced improved ED symptoms. Altogether, this emphasizes the challenges to maintaining well-being in individuals with ED during the pandemic.