Your search

This paper presents an algorithm that applies metrics derived from automatic QRS detection and segmentation in electrocardiogram signals for analyzing Heart Rate Variability to study the evolution of metrics in the frequency domain of a clinical procedure. The analysis was performed on three sets of elderly people, who are categorized according to frailty phenotype. The first set was comprised of frail elderly, the second pre-frail elderly, and the third robust elderly. Investigators from many disciplines have been encouraged to contribute to the understanding of molecular and physiological changes in multiple systems that may increase the vulnerability of frail elderly. In this work, the frailty phenotype can be characterized by unintentional weight loss, as self-reported, fatigue assessed by self-report, grip strength (measured directly), physical activity level assessed by self-report and gait speed (measured). The results obtained demonstrate the existence of significant differences between Heart Rate Variability metrics for the three groups, especially considering a higher preponderance for sympathetic nervous system for the group of robust patients in response to postural maneuver.

The adoption of computer-aided diagnosis and treatment systems based on different types of artificial neural networks (ANNs) is already a reality in several hospital and ambulatory premises. This chapter aims to present a discussion focused on the challenges and trends of adopting these computerized systems, highlighting solutions based on different types and approaches of ANN, more specifically, feed-forward, recurrent, and deep convolutional architectures. One section is focused on the application of AI/ANN solutions to support cardiology in different applications, such as the classification of the heart structure and functional behavior based on echocardiography images; the automatic analysis of the heart electric activity based on ECG signals; and the diagnosis support of angiogram images during surgical interventions. Finally, a case study is presented based on the application of a deep learning convolutional network together with a recent technique called transfer learning to detect brain tumors using an MRI images data set. According to the findings, the model has a high degree of specificity (precision of 0.93 and recall of 0.94 for images with no brain tumor) and can be used as a screening tool for images that do not contain a brain tumor. The f1-score for images with brain tumor was 0.93. The results achieved are very promising and the proposed solution may be considered to be used as a computer-aided diagnosis tool based on deep learning convolutional neural networks. Future works will consider other techniques and compare them with the one presented here. With the comprehensive approach and overview of multiple applications, it is valid to conclude that computer-aided diagnosis and treatment systems are important tools to be considered today and will be an essential part of the trend of personalized medicine over the coming years.

The adoption of IoT for smart health applications is a relevant tool for distributed and intelligent automatic diagnostic systems. This work proposes the development of an integrated solution to monitor maternal and fetal signals for high-risk pregnancies based on IoT sensors, feature extraction based on data analytics, and an intelligent diagnostic aid system based on a 1-D convolutional neural network (CNN) classifier. The fetal heart rate and a group of maternal clinical indicators, such as the uterine tonus activity, blood pressure, heart rate, temperature, and oxygen saturation are monitored. Multiple data sources generate a significant amount of data in different formats and rates. An emergency diagnostic subsystem is proposed based on a fog computing layer and the best accuracy was 92.59% for both maternal and fetal emergency. A smart health analytics system is proposed for multiple feature extraction and the calculation of linear and nonlinear measures. Finally, a classification technique is proposed as a prediction system for maternal, fetal, and simultaneous health status classification, considering six possible outputs. Different classifiers are evaluated and a proposed CNN presented the best results, with the F1-score ranging from 0.74 to 0.91. The results are validated based on the diagnosis provided by two specialists. The results show that the proposed system is a viable solution for maternal and fetal ambulatory monitoring based on IoT.

The area of clinical decision support systems (CDSS) is facing a boost in research and development with the increasing amount of data in clinical analysis together with new tools to support patient care. This creates a vibrant and challenging environment for the medical and technical staff. This chapter presents a discussion about the challenges and trends of CDSS considering big data and patient-centered constraints. Two case studies are presented in detail. The first presents the development of a big data and AI classification system for maternal and fetal ambulatory monitoring, composed by different solutions such as the implementation of an Internet of Things sensors and devices network, a fuzzy inference system for emergency alarms, a feature extraction model based on signal processing of the fetal and maternal data, and finally a deep learning classifier with six convolutional layers achieving an F1-score of 0.89 for the case of both maternal and fetal as harmful. The system was designed to support maternal–fetal ambulatory premises in developing countries, where the demand is extremely high and the number of medical specialists is very low. The second case study considered two artificial intelligence approaches to providing efficient prediction of infections for clinical decision support during the COVID-19 pandemic in Brazil. First, LSTM recurrent neural networks were considered with the model achieving R2=0.93 and MAE=40,604.4 in average, while the best, R2=0.9939, was achieved for the time series 3. Second, an open-source framework called H2O AutoML was considered with the “stacked ensemble” approach and presented the best performance followed by XGBoost. Brazil has been one of the most challenging environments during the pandemic and where efficient predictions may be the difference in saving lives. The presentation of such different approaches (ambulatory monitoring and epidemiology data) is important to illustrate the large spectrum of AI tools to support clinical decision-making.

Objective: This study highlights the potential of an Electrocardiogram (ECG) as a powerful tool for early diagnosis of COVID-19 in critically ill patients with limited access to CT–Scan rooms. Methods: In this investigation, 3 categories of patient status were considered: Low, Moderate, and Severe. For each patient, 2 different body positions have been used to collect 2 ECG signals. Then, from each collected signal, 10 non-linear features (Energy, Approximate Entropy, Logarithmic Entropy, Shannon Entropy, Hurst Exponent, Lyapunov Exponent, Higuchi Fractal Dimension, Katz Fractal Dimension, Correlation Dimension and Detrended Fluctuation Analysis) were extracted every 1s ECG time-series length to serve as entries for 19 Machine learning classifiers within a leave-one-out cross-validation procedure. Four different classification scenarios were tested: Low vs. Moderate, Low vs. Severe, Moderate vs. Severe and one Multi-class comparison (All vs. All). Results: The classification report results were: (1) Low vs. Moderate - 100% of Accuracy and 100% of F1–Score; (2) Low vs. Severe - Accuracy of 91.67% and an F1–Score of 94.92%; (3) Moderate vs. Severe - Accuracy of 94.12% and an F1–Score of 96.43%; and (4) All vs All - 78.57% of Accuracy and 84.75% of F1–Score. Conclusion: The results indicate that the applied methodology could be considered a good tool for distinguishing COVID-19’s different severity stages using ECG signals. Significance: The findings highlight the potential of ECG as a fast and effective tool for COVID-19 examination. In comparison to previous studies using the same database, this study shows a 7.57% improvement in diagnostic accuracy for the All vs All comparison.

Fast and efficient malaria diagnostics are essential in efforts to detect and treat the disease in a proper time. The standard approach to diagnose malaria is a microscope exam, which is submitted to a subjective interpretation. Thus, the automating of the diagnosis process with the use of an intelligent system capable of recognizing malaria parasites could aid in the early treatment of the disease. Usually, laboratories capture a minimum set of images in low quality using a system of microscopes based on mobile devices. Due to the poor quality of such data, conventional algorithms do not process those images properly. This paper presents the application of deep learning techniques to improve the accuracy of malaria plasmodium detection in the presented context. In order to increase the number of training sets, deep convolutional generative adversarial networks (DCGAN) were used to generate reliable training data that were introduced in our deep learning model to improve accuracy. A total of 6 experiments were performed and a synthesized dataset of 2.200 images was generated by the DCGAN for the training phase. For a real image database with 600 blood smears with malaria plasmodium, the proposed Deep Learning architecture obtained the accuracy of 100% for the plasmodium detection. The results are promising and the solution could be employed to support a mass medical diagnosis system.

The COVID-19 pandemic has posed a significant public health challenge on a global scale. It is imperative that we continue to undertake research in order to identify early markers of disease progression, enhance patient care through prompt diagnosis, identification of high-risk patients, early prevention, and efficient allocation of medical resources. In this particular study, we obtained 100 5-min electrocardiograms (ECGs) from 50 COVID-19 volunteers in two different positions, namely upright and supine, who were categorized as either moderately or critically ill. We used classification algorithms to analyze heart rate variability (HRV) metrics derived from the ECGs of the volunteers with the goal of predicting the severity of illness. Our study choose a configuration pro SVC that achieved 76% of accuracy, and 0.84 on F1 Score in predicting the severity of Covid-19 based on HRV metrics.

Following the World Health Organization proclaims a pandemic due to a disease that originated in China and advances rapidly across the globe, studies to predict the behavior of epidemics have become increasingly popular, mainly related to COVID-19. The critical point of these studies is to discuss the disease's behavior and the progression of the virus's natural course. However, the prediction of the actual number of infected people has proved to be a difficult task, due to a wide range of factors, such as mass testing, social isolation, underreporting of cases, among others. Therefore, the objective of this work is to understand the behavior of COVID-19 in the state of Ceará to forecast the total number of infected people and to aid in government decisions to control the outbreak of the virus and minimize social impacts and economics caused by the pandemic. So, to understand the behavior of COVID-19, this work discusses some forecast techniques using machine learning, logistic regression, filters, and epidemiologic models. Also, this work brings a new approach to the problem, bringing together data from Ceará with those from China, generating a hybrid dataset, and providing promising results. Finally, this work still compares the different approaches and techniques presented, opening opportunities for future discussions on the topic. The study obtains predictions with R2 score of 0.99 to short-term predictions and 0.93 to long-term predictions.