ECG Forecasting System Based on Long Short-Term Memory.

Worldwide, cardiovascular diseases are some of the primary causes of death; yet the early detection and diagnosis of such diseases have the potential to save many lives. Technological means of detection are becoming increasingly essential and numerous techniques have been created for this purpose, such as forecasting. Of these techniques, the time series forecasting technique seeks to predict future events. The long-term time series forecasting of physiological data could assist medical professionals in predicting and treating patients based on very early diagnosis. This article presents a model that utilizes a deep learning technique to predict long-term ECG signals. The forecasting model can learn signals' nonlinearity, nonstationarity, and complexity based on a long short-term memory architecture. However, this is not a trivial task as the correct forecasting of a signal that closely resembles the original complex signal's structure and behavior while minimizing any differences in amplitude continues to pose challenges. To achieve this goal, we used a dataset available on the Physio net database, called MIT-BIH, with 48 ECG recordings of 30 min each. The developed model starts with pre-processing to reduce interference in the original signals, then applies a deep learning algorithm, based on a long short-term memory (LTSM) neural network with two hidden layers. Next, we applied the root mean square error (RMSE) and mean absolute error (MAE) metrics to evaluate the performance of the model and obtained an average RMSE of 0.0070±0.0028 and an average MAE of 0.0522±0.0098 across all simulations. The results indicate that the proposed LSTM model is a promising technique for ECG forecasting, considering the trends of the changes in the original data series, most notably in R-peak amplitude. Given the model's accuracy and the features of the physiological signals, the system could be used to improve existing predictive healthcare systems for cardiovascular monitoring.

Enhancing Health and Public Health through Machine Learning: Decision Support for Smarter Choices.

In recent years, the integration of Machine Learning (ML) techniques in the field of healthcare and public health has emerged as a powerful tool for improving decision-making processes [...].

A review on multimodal machine learning in medical diagnostics.

Nowadays, the increasing number of medical diagnostic data and clinical data provide more complementary references for doctors to make diagnosis to patients. For example, with medical data, such as electrocardiography (ECG), machine learning algorithms can be used to identify and diagnose heart disease to reduce the workload of doctors. However, ECG data is always exposed to various kinds of noise and interference in reality, and medical diagnostics only based on one-dimensional ECG data is not trustable enough. By extracting new features from other types of medical data, we can implement enhanced recognition methods, called multimodal learning. Multimodal learning helps models to process data from a range of different sources, eliminate the requirement for training each single learning modality, and improve the robustness of models with the diversity of data. Growing number of articles in recent years have been devoted to investigating how to extract data from different sources and build accurate multimodal machine learning models, or deep learning models for medical diagnostics. This paper reviews and summarizes several recent papers that dealing with multimodal machine learning in disease detection, and identify topics for future research.

COVID-19 Detection by Means of ECG, Voice, and X-ray Computerized Systems: A Review.

Since the beginning of 2020, Coronavirus Disease 19 (COVID-19) has attracted the attention of the World Health Organization (WHO). This paper looks into the infection mechanism, patient symptoms, and laboratory diagnosis, followed by an extensive assessment of different technologies and computerized models (based on Electrocardiographic signals (ECG), Voice, and X-ray techniques) proposed as a diagnostic tool for the accurate detection of COVID-19. The found papers showed high accuracy rate results, ranging between 85.70% and 100%, and F1-Scores from 89.52% to 100%. With this state-of-the-art, we concluded that the models proposed for the detection of COVID-19 already have significant results, but the area still has room for improvement, given the vast symptomatology and the better comprehension of individuals' evolution of the disease.

Análise comparativa de desempenho das transformadas Wavelet e Hilbert na detecção do QRS em ECG / Performance comparison analysis of Wavelet and Hilbert transforms for QRS detection in ECG

O processo de detecção do complexo QRS é o primeiro passo de um processo de extração de parâmetros do sinal eletrocardiograma (ECG) em sistemas de auxílio ao diagnóstico médico. O presente trabalho apresenta resultados detalhados de comparação da aplicação de duas transformadas matemáticas, Wavelet e Hilbert, em um algoritmo de detecção de QRS em termos de taxas de detecções corretas (sensibilidade e preditividade positiva) e de uma medida de frequência de recorrência a processos de filtragem (pré-processamento). Uma abordagem inovadora é implementada, na qual as rotinas de filtragem são inseridas dentro do estágio de decisão, ou seja, é realizada a supressão da etapa de pré-processamento. As transformadas são aplicadas no algoritmo, que é baseado em um limiar adaptativo, com o objetivo de realçar, apenas quando necessário, os picos (pontos fiduciais)do QRS. Em uma primeira abordagem, apenas a transformada Wavelet é utilizada neste realce e, numa segunda abordagem, a transformada de Hilbert é inserida em série à aplicação da Wavelet em dois possíveis arranjos. São realizados experimentos dos algoritmos sobre os exames da base de dados Arrhythmia Database, pertencente ao conjunto de bases de dados do MIT-BIH. É composta por 48 gravações de ECG com duração de trinta minutos, amostrados a uma frequência de 360 Hz com resolução de 4,88 μV sobre uma faixa de variação de 10 mV. Ao todo, contabilizam-se 109.662 complexos QRS. Taxas de 98,85% de sensibilidade e 95,10% de preditividade positiva são obtidas com a aplicação exclusiva da transformada Wavelet, enquanto que 98,89% de sensibilidade e 98,52% de preditividade positiva são obtidas com aaplicação em série das transformadas Wavelet e de Hilbert.

The process of QRS detection is the first stage of a greater process: the feature extraction in the electrocardiogram (ECG). This work presents detailed results on the performance of two mathematical transforms, Hilbert and Wavelet, which are applied in QRS detection. The evaluation parameters are the detection rates and a measure of frequency of recurrence to filtering processes. An innovative approach is implemented: the filtering routines are inserted in the decision stage, i.e. the preprocessing stage is removed. The algorithm is based on adaptive threshold technique and the two transforms are applied in order to emphasize, only when necessary, the QRS fiducial points. In a first approach, only the Wavelet transform is applied, and in a second approach, the Hilbert transform is inserted before the Wavelet transform or after it. We evaluate these approaches on the well-known MIT-BIH Arrhythmia Database. It contains 48 half-hour recordings of annotated ECG with a sampling rate of 360 Hz and 4.88 μV resolution over a 10 mV range, totalizing 109,662 QRS complexes. Sensitivity rates of 98.85% and 98.89% are respectively attained when the Wavelet transform is applied in the filtering processes and both Hilbert and Wavelet transforms are applied. Predictability rates of 95.10% and 98.52% are also attained respectively using Wavelet transform and the simultaneous application of Hilbert and Wavelet transforms in the filtering processes.

Sistema inteligente para auxílio ao diagnóstico no monitoramento fetal eletrônico por análise de cardiotocografias / A computer aided diagnostic intelligent system for electronic fetal monitoring based on cardiotocographies

A análise acurada da frequência cardíaca fetal (FCF) correlacionada com as contrações uterinas permite diagnosticar, e consequentemente antecipar, diversos problemas relativos ao bem estar fetal e à preservação de sua vida. O presente trabalho apresenta os resultados de um sistema híbrido, baseado em regras determinísticas e em um módulo de inferência nebuloso do tipo Mamdani, para análise de sinais coletados através de exames denominados cardiotocografias (CTG). As variáveis analisadas são: o valor basal da FCF, suas variabilidades de curto e de longo prazo, acelerações transitórias e desacelerações, sendo estas classificadas por seu tipo e número de ocorrências. São utilizados dois modelos de classificação. A saída do sistema, em qualquer dos modelos, é um diagnóstico de primeiro nível baseado nestas variáveis de entrada. O sistema inteligente para auxílio ao diagnóstico no monitoramento fetal eletrônico por análise de cardiotocografias (SISCTG) foi desenvolvido na linguagem de scripts do programa MATLAB® v.7. O projeto conta também com uma parceria multi-institucional entre o Brasil e a Alemanha, envolvendo o Departamento de Engenharia de Teleinformática (DETI) da Universidade Federal do Ceará (UFC), a Maternidade-Escola Assis Chateaubriand (MEAC), a Technische Universitãt München e a empresa alemã Trium GmbH, que fornece a base de dados utilizada neste trabalho. Os resultados apresentados pelo SISCTG mostram-se promissores, com um índice de acertos (comparando-se os dois modelos utilizados) variando de 83% a 100%, de acordo com o tipo de diagnóstico. Isto permite projetar o aprimoramento deste sistema com novas variáveis de entrada (como a entropia aproximada da FCF e da sua variabilidade). A validação do sistema contou com especialistas brasileiros e alemães na área obstétrica.

The accurate analysis of the fetal heart rate (FHR) and its correlation with uterine contractions (UC) allow the diagnostic and the anticipation of many problems related to fetal distress and the preservation of its life. This paper presents the results of a hybrid system based on a set of deterministic rules and fuzzy inference system developed to analyze FHR and UC signals collected by cardiotocography (CTG) exams. The studied variables are basal FHR, short and long-term FHR variability, transitory accelerations and decelerations, these lasts classified by their type and number of occurrences. Two classification models are used. For both models, the system output is a first level diagnostic based on those input variables. The system is developed using the MATLAB® v.7 script language. The project is also supported by a multi-institutional agreement between Brazil and Germany, among the DETI (Departamento de Engenharia de Teleinformática of the Universidade Federal do Ceará), the MEAC (Maternidade-Escola Assis Chateaubriand), the TUM (Technische Universitãt München), and the Trium GmbH, a German company who supplied the database used in this project. The results are very promising with a diagnostic accuracy (considering the two models used) varying from 83% to 100%, according to the type of diagnostic. These results allow the projection of refinements of the proposed system, inserting new input variables (such as the approximate entropy of the FHR and its variability). The system validation methodology was based on the knowledge of Brazilian and German obstetricians.