These results indicate that the HRV signal contains valuable information and can be a predictor for epilepsy seizure. Although our results in comparison with EEG ares a little bit weaker, the recording of ECG is much easier and faster than EEG. Also, our finding showed the results of this study are considerably better than recent research based on ECG (Tab. 1, Fig. 10, Ref. 17).

Intensive care unit (ICU) patients are at risk of in-ICU morbidities and mortality, making specific systems for identifying at-risk patients a necessity for improving clinical care. This study presents a new method for predicting in-hospital mortality using heart rate variability (HRV) collected from the times of a patient's ICU stay. In this paper, a HRV time series processing based method is proposed for mortality prediction of ICU cardiovascular patients. HRV signals were obtained measuring R-R time intervals. A novel method, named return map, is then developed that reveals useful information from the HRV time series. This study also proposed several features that can be extracted from the return map, including the angle between two vectors, the area of triangles formed by successive points, shortest distance to 45° line and their various combinations. Finally, a thresholding technique is proposed to extract the risk period and to predict mortality. The data used to evaluate the proposed algorithm obtained from 80 cardiovascular ICU patients, from the first 48 h of the first ICU stay of 40 males and 40 females. This study showed that the angle feature has on average a sensitivity of 87.5% (with 12 false alarms), the area feature has on average a sensitivity of 89.58% (with 10 false alarms), the shortest distance feature has on average a sensitivity of 85.42% (with 14 false alarms) and, finally, the combined feature has on average a sensitivity of 92.71% (with seven false alarms). The results showed that the last half an hour before the patient's death is very informative for diagnosing the patient's condition and to save his/her life. These results confirm that it is possible to predict mortality based on the features introduced in this paper, relying on the variations of the HRV dynamic characteristics.

No abstract

No abstract

AIM: Autonomic nervous system (ANS) activities during different types of stress could affect the electrocardiogram (ECG) signal. This study aimed to recognize the types of stress by using different ECG signals in order to prevent its actual physiological effects on the heart signal. METHOD: The ECG signal recorded by portable wrist bracelets from 20 students in during seven phases which incorporated three different types of stress and four relaxation phases. After different forms of windowing the signal, we used linear and non-linear features such as detrended fl uctuation analysis (DFA), Poincaré plot, approximate and sample entropy, correlation dimension, and recurrence plot to extract various features of the heart rate variability (HRV). Then, different classifi ers were used to identify the types of stress. RESULTS: The results showed a decrease in NN50, RMSSD, pNN50, and recurrence plot features, and an increase in the DFA method during stress stages, which show the effect of stress on heart rate. Also, by using the convolutional neural network (CNN), an average classifi cation rate of 98 % was obtained in association with cognitive stress and that of 94.5 % in association with emotional stress. CONCLUSION: This paper showed that features extracted from HRV can detect the stress and non-stress stages with high signifi cance. Also, the accuracy of this paper proved that the proposed method is successful in preventing the dangerous effects of different types of stress on the heart (Tab.

No abstract

Abstract— Using intelligent methods to identify and classify a variety of diseases, in particular cancer, has gained tremendous attention today. Tumor classification plays an important role in medical diagnosis. This study's goal was to classify breast cancer (BC) tumors using software-based numerical techniques. To determine whether breast cancer masses are benign or malignant, we used MATLAB version 2020b to build a neural network. In the first step, the features of the training images and their output classes were used to train the network. Optimal weights were obtained after several repetitions, and the network was trained to produce the best result in the test phase after several repetitions. Because of using effective and accurate features, the method suggested here, which was based on an artificial neural network, delivered the diagnostic accuracy, specificity, and sensitivity of 100%, 100%, and 100%, respectively, to discern benign from malignant BC tumors, showing a better performance compared to previously proposed methods. One of the challenges for imaging-based diagnostic techniques in medicine is the difficulty of processing dense tissues. Breast cancer is one of the most common progressive diseases among females. Early diagnosis makes treatment easier and more effective. Using AI-based methods for automated diagnosis purposes can be valuable and have a reduced error rate because accurate diagnosis by manual means is time-consuming and error-prone.

No abstract