Automatic surgical skill assessment has the capacity to bring a transformative shift in the assessment, development, and enhancement of surgical proficiency. It offers several advantages, including objectivity, precision, and real-time feedback. These benefits will greatly enhance the development of surgical skills for novice surgeons, enabling them to improve their abilities in a more effective and efficient manner. In this study, we aimed to investigate the utilization of hand skeleton dynamics for evaluating surgical proficiency, specifically by employing sequences of hand skeletons to distinguish between experienced surgeons and surgical residents. To the best of our knowledge, this study represents a pioneering approach in using hand skeleton sequences for assessing surgical skills.

To effectively capture the spatial-temporal correlations within sequences of hand skeletons for surgical skill assessment, we present STGFormer, a novel approach that combines the capabilities of Graph Convolutional Networks and Transformers. STGFormer is designed to learn advanced spatial-temporal representations and efficiently capture long-range dependencies. We evaluated our proposed approach on a dataset comprising experienced surgeons and surgical residents practicing surgical procedures in a simulated training environment. Our experimental results demonstrate that the proposed STGFormer outperforms all state-of-the-art models for the task of surgical skill assessment. Specifically, we achieve an accuracy of 85.17% and a weighted average F1-score of 83.29%. These results represent a significant improvement of 3.25% and 3.16% respectively when compared to the best state-of-the-art model.

Psoriasis is a dermatological lesion that manifests in several regions of the body. Its late diagnosis can generate the aggravation of the disease itself, as well as of the comorbidities associated with it. The proposed work presents a computational system for image classification in smartphones, through deep convolutional neural networks, to assist the process of diagnosis of psoriasis.

The dataset and the classification algorithms used revealed that the clas- sification of psoriasis lesions was most accurate with unsegmented and unprocessed images, indicating that deep learning networks are able to do a good feature selection. Smaller models have a lower accuracy, al- though they are more adequate for environments with power and memory restrictions, such as smartphones.

Inflammatory bowel disease is a chronic disease of unknown cause that can affect the entire gastrointestinal tract, from the mouth to the anus. It is important for patients with this pathology that a good diagnosis is made as early as possible, so that the inflammation present in the mucosa intestinal is controlled and the most severe symptoms are reduced, thus offering the quality of life to people. Therefore, through this comparative study, we seek to find a way of automating the diagnosis of these patients during the endoscopic examination, reducing the subjectivity that is subject to the observation of a gastroenterologist, using six CNNs: AlexNet, ResNet50, VGG16, ResNet50-MobileNetV2 and Hybrid model. Also, five ViTs were used in this study: ViT-B/32, ViT-S/32, ViT-B/16, ViT-S/16 and R26+S/32. This comparison also consists in applying knowledge distillation to build simpler models, with fewer parameters, based on the learning of the pre-trained architectures on large volumes of data. It is concluded that in the ViTs framework, it is possible to reduce 25x the number of parameters by maintaining good performance and reducing the inference time by 5.32 seconds. For CNNs the results show that it is possible to reduce 107x the number of parameters, reducing consequently the inference time in 3.84 seconds.

Depression is a frequently underestimated illness that significantly impacts a substantial number of individuals worldwide, making it a significant mental disorder. The world today lives fully connected, where more than half of the world's population uses social networks in their daily lives. If we interpret and understand the feelings associated with a social media post, we can detect potential depression cases before they reach a major state associated with consequences for the patient. This paper proposes the use of natural language processing (NLP) techniques to classify the sentiment associated with a post made on the Twitter social network. This sentiment can be non-depressive, neutral, or depressive. The authors collected and validated the data, and performed pre-processing and feature generation using TF-IDF and Word2Vec techniques. Various DL and ML models were evaluated on these features. The Extra Trees classifier combined with the TF-IDF technique emerged as the most successful combination for classifying potential depression sentiment in tweets, achieving an accuracy of 84.83%.

This paper proposes a biometric application for iris capture devices using a Siamese network based on an EfficientNetv2 and a triplet loss function to classify iris NIR images captured under alcohol/drugs/sleepiness conditions. The results show that our model can detect the "Fit/Unfit" alertness condition from iris samples captured after alcohol, drug consumption, and sleepiness conditions robustly with an accuracy of 87.3% and 97.0% for Fit/Unfit, respectively. The sleepiness condition is the most challenging, with an accuracy of 72.4%. The Siamese model uses a smaller number of parameters than the standard Deep learning Network algorithm. This work complements and improves the literature on biometric applications for developing an automatic system to classify "Fitness for Duty" using iris images and prevent accidents due to alcohol/drug consumption and sleepiness.

Drug resistance is an key factor in the failure of drug therapy, as the antiretroviral therapy against the human immunodeficiency virus (HIV). Due to the high costs of direct phenotypic assays, genotypic assays, based on sequencing of the viral genome or part of it, are commonly used to infer drug resistance via in silico predictions. In these approaches, the interpretation of the sequence information constitutes the biggest challenge. The large amount of data linking genotype and phenotype information provides a framework for predicting drug resistance from genotype, based on machine learning methods. Primarily, the sequence based information is used but largely fails to predict resistance in previously unobserved variants. The inclusion of structural and dynamic information is supposed to improve the predictions but has been limited by their computational cost of calculation. This study shows the feasibility of dynamic descriptors derived from normal mode analysis in elastic network models of HIV type 1 (HIV-1) protease in predicting drug resistance. We show that exploring the pre-configuration of dynamic information covering the intrinsic movement spectrum of proteinase in HIV-1 by multiple conformation approach descriptors improve the classification task.

Stroke can cause significant damage to neurons, resulting in various sequelae that negatively impact the patient’s ability to perform essential daily activities such as chewing, swallowing, and verbal communication. Therefore, it is important for patients with such difficulties to undergo a treatment process and be monitored during its execution to assess the improvement of their health condition. The use of computerized tools and algorithms that can quickly and affordably detect such sequelae proves helpful in aiding the patient’s recovery. Due to the death of internal brain cells, a stroke often leads to facial paralysis, resulting in certain asymmetry between the two sides of the face. This paper focuses on analyzing this asymmetry using a deep learning method without relying on handcrafted calculations, introducing the Facial Point Graphs (FPG) model, a novel approach that excels in learning geometric information and effectively handling variations beyond the scope of manual calculations. FPG allows the model to effectively detect orofacial impairment caused by a stroke using video data. The experimental findings on the Toronto Neuroface dataset revealed the proposed approach surpassed state-of-the-art results, promising substantial advancements in this domain.

Melanoma is the most severe type of skin cancer due to its ability to cause metastasis. It is more common in black people, often affecting acral regions: palms, soles, and nails. Deep neural networks have shown tremendous potential for improving clinical care and skin cancer diagnosis. Nevertheless, prevailing studies predominantly rely on datasets of white skin tones, neglecting to report diagnostic outcomes for diverse patient skin tones. In this work, we evaluate supervised and self-supervised models in skin lesion images extracted from acral regions commonly observed in black individuals. Also, we introduce a dataset containing skin lesions in acral regions and assess the datasets concerning the Fitzpatrick scale to verify performance on black skin. Our results highlight the limited generalizability of these models, revealing their favorable performance solely for lesions on white skin. Developing specific models due to negligence in creating diverse datasets is unacceptable. Deep neural networks have great potential to improve diagnosis, particularly for populations with limited access to dermatology. However, including skin lesions with less common characteristics is necessary to ensure these populations can access the benefits of inclusive technology.

This work focuses on the problem of mortality prediction in patients with pneumonia after admission into an intensive care unit, by addressing it via logistic regression. This approach can model the relationship between clinical correlates and the probability of the binary outcome, with obvious advantages such as simplicity and interpretability of the predictive models. This work further inspects the potential of localized models, an approach based on different (parallel) predictive models each one constructed in clusters automatically identified in the training set. The predicted outcome is then obtained via membership separation (M, which corresponds to the outcome of the closest localized model) or weights (W, outcome as the weight average of localized outcomes via inverse distance). The results point out a similar balanced accuracy of 0.73 for the global model M24-48PS (without oversampling) and the W M24-48PSC model (weighted average of localized models without oversampling), which is partially explained by the small separability between the identified clusters. Therefore, a proof of concept was performed to support the usefulness of localized models in more separable data. This study considered a small amount of data for training and testing (chosen as that closest to the centroids of the identified clusters) and the results suggest that the localized approach can outperform the global one in more separable data.

Appropriate pain treatment relies on an accurate assessment of pain. Limitations regarding subjective reporting of pain or observational bias, when pain is assessed by a healthcare professional, can lead to inadequate pain treatment. Therefore, pain assessment using physiological signals has been studied in past years due to the importance of objective measurement. The aim of this work is to use features extracted from electrocardiogram (ECG) signals to classify induced pain levels and to identify the best models for this classification task. Specifically, the goal is to determine the optimal hyperparameters of the classification algorithms and the optimal features for accurately distinguishing between higher and lower levels of pain. A model combining 15 ECG-features related to the P, R, S, and T waves and the Random Forest algorithm provided the best performance for predicting induced pain levels. This model achieved an accuracy of 95.3%, an F1-score of 94.0%, a precision of 97.9%, and a recall of 90.4%. These results show the feasibility of identifying pain through the physiological characteristics of the ECG.