Deficits in social interaction and communication characterize Autism Spectrum Disorder (ASD). Although widely recognized by its symptoms, diagnosing ASD remains challenging due to its wide range of clinical presentations. Methods: In this study, we propose a method to assist in the early diagnosis of autism, which is currently primarily based on clinical assessments. Our approach aims to develop an early differential diagnosis based on electroencephalogram (EEG) signals, seeking to identify patterns associated with ASD. In this study, we used EEG data from 56 participants obtained from the Sheffield dataset, including 28 individuals diagnosed with Autism Spectrum Conditions (ASC) and 28 neurotypical controls, applying numerical techniques to handle missing data. Subsequently, after a detailed analysis of the signals, we applied three different starting approaches: one with the original database and the other two with selection of the most significant attributes using the PSO and evolutionary search methods. In each of these approaches, we applied a series of machine learning models, where relatively high performances for classification were observed. Results: We achieved accuracies of 99.13% ± 0.44 for the dataset with original signals, 99.23% ± 0.38 for the dataset after applying PSO, and 93.91% ± 1.10 for the dataset after the evolutionary search methodology. These results were obtained using classical classifiers, with SVM being the most effective among the first two approaches, while Random Forest with 500 trees proved more efficient in the third approach. Conclusions: Even with all the limitations of the base, the results of the experiments demonstrated promising findings in identifying patterns associated with Autism Spectrum Disorder through the analysis of EEG signals. Finally, we emphasize that this work is the starting point for a larger project with the objective of supporting and democratizing the diagnosis of ASD both in children early and later in adults.

Proposal The aging population has led to an increase in chronic degenerative diseases, such as Alzheimer’s disease (AD) and frontotemporal dementia (FTD). Future projections indicate that this increase will be more pronounced, with cases tripling by 2050. Therefore, it is necessary to identify patterns of brain activity related to dementia to assist in earlier diagnosis. Objective In this study, we propose to compare the performance of Machine Learning (ML) models across different databases in patients with dementia and elderly individuals using EEG data. Methods We investigated various machine learning models using two distinct EEG databases: OpenNeuro (AD, FTD, and healthy controls) and GeronGnosis (mild cognitive impairment - MCI, AD, FTD, and healthy controls), the latter developed by the researchers and presented here for the first time. After extracting different signal attributes, we applied the Bayes Network, Random Tree, Random Forest, and SVM models and compared their best performances. Results The Random Forest model with 500 trees demonstrated the best classification performance, achieving an accuracy of 98% on the GeronGnosis database, while the OpenNeuro database reached an accuracy of 95%. Conclusion The GeronGnosis database was able to correctly classify patients with dementia and healthy controls with excellent performance across the studied metrics. Additionally, as an unprecedented national database, it allows for better representation of the local population, helping to improve the clinical applicability of classification models.

Deficits in social interaction and communication characterize Autism Spectrum Disorder (ASD). Although widely recognized by its symptoms, diagnosing ASD remains challenging due to its wide range of clinical presentations. Methods: In this study, we propose a method to assist in the early diagnosis of autism, currently primarily based on clinical assessments. Our approach aims to develop an early differential diagnosis based on electroencephalogram (EEG) signals, seeking to identify patterns associated with ASD. We used EEG data from 56 individuals from the Sheffield dataset, applying techniques to handle missing data. Subsequently, after a detailed analysis of the signals, we applied 3 different starting approaches: one with the original database and the other two with selection of the most significant attributes using the PSO and evolutionary search methods. In each of these approaches, we applied a series of machine learning models, where relatively high performances for classification were observed. Results: We achieved an accuracy of 99.13% ± 0.44 for the dataset with original signals, 99.23% ± 0.38 for the dataset after applying PSO, and an accuracy of 93.91% ± 1.10 for the dataset after the evolutionary search methodology. These results were obtained using classical classifiers, with SVM being the most effective among the first two approaches, while Random Forest with 500 trees proved more efficient in the third approach. Conclusion: Even with all the limitations of the base, the results of the experiments demonstrated promising findings in identifying patterns associated with Autism Spectrum Disorder through the analysis of EEG signals. Finally, we emphasize that this work is the starting point for a larger project, with the objective of supporting and democratizing the diagnosis of ASD, both in children early and later in adults.

Proposal:The aging population has led to an increase in chronic degenerative diseases, such as Alzheimer's disease (AD) and frontotemporal dementia (FTD). Future projections indicate that this increase will be more pronounced, with cases tripling by 2025. Therefore, it is necessary to identify patterns of brain activity related to dementia to assist in earlier diagnosis. Objective: In this study, we propose to compare the performance of machine learning (ML) models across different databases in patients with dementia and elderly individuals using EEG data. Methods: We investigated various machine learning models using two distinct EEG databases: OpenNeuro (AD, FTD, and healthy controls) and GeronGnosis (mild cognitive impairment - MCI, AD, FTD, and healthy controls), the latter developed by the researchers and presented here for the first time. After extracting different signal attributes, we applied the Bayes Network, Random Tree, Random Forest, and SVM models and compared their best performances. Results: The Random Forest model with 500 trees demonstrated the best classification performance, achieving an accuracy of 98% on the GeronGnosis database, while the OpenNeuro database reached an accuracy of 95%. Conclusion: The GeronGnosis database was able to correctly classify patients with dementia and healthy controls with excellent performance across the studied metrics. Additionally, as a national and unprecedented database, it allows for better representation of the local population, helping to improve the clinical applicability of classification models.

Purpose: Molecular docking prediction plays a pivotal role in intelligent drug design, offering significant advantages in the development of antivirus medications and vaccines. By accurately evaluating the interactions between drug molecules and target proteins, researchers can effectively expedite the discovery and development of vital pharmaceutical solutions, aiding in the mitigation of epidemics, pandemics, and the urgent need for improved vaccines. Methods: We propose an intelligent hybrid architecture for estimating molecular docking between two proteins using deep networks based on pseudo-convolutions and Random Forests. As input, we Evaluation of molecular docking by deep learning and Random Forests used the sequences of characters representing the bases of each protein. Through two layers of pseudo-convolutions, these sequences are reorganized and, finally, represented as co-occurrence matrices, concatenated into a feature vector. To validate our proposal, we used a combination of the public datasets Affinity Benchmark 3 and Negatome 2. Results: The experimental results revealed that the hybrid architecture , comprising two layers of pseudo-convolution followed by a decision layer with an ensemble of 25 Random Forests, yielded average accuracy of 94%, AUC of 93%, sensitivity of 94%, and specificity of 78%. This demonstrates the feasibility of achieving robust estimates of molecular docking without relying on 3D molecule modeling. Conclusion: These findings the potential of rapidly estimating protein affinity, providing valuable insights into drug interactions, molecular dynamics, and facilitating the intelligent design of pharmaceuticals, encompassing vaccines and antiviral drugs. These advancements play a critical role in cost reduction related to laboratory analysis and expediting the timely delivery of solutions to both the market and society at large, particularly in the context of epidemic outbreaks, pandemics, and the urgent demand for supplementary vaccines.