Today, cardiovascular disease is the leading cause of death in developed countries. The most common arrhythmia is atrial fibrillation, which increases the risk of ischemic stroke. An electrocardiogram is one of the best methods for diagnosing cardiac arrhythmias. Often, the signals of the electrocardiogram are distorted by noises of varying nature. In this paper, we propose a neural network classification system for electrocardiogram signals based on the Long Short-Term Memory neural network architecture with a preprocessing stage. Signal preprocessing was carried out using a symlet wavelet filter with further application of the instantaneous frequency and spectral entropy functions. For the experimental part of the article, electrocardiogram signals were selected from the open database PhysioNet Computing in Cardiology Challenge 2017 (CinC Challenge). The simulation was carried out using the MatLab 2020b software package for solving technical calculations. The best simulation result was obtained using a symlet with five coefficients and made it possible to achieve an accuracy of 87.5% in recognizing electrocardiogram signals.

Today, skin cancer is one of the most common malignant neoplasms in the human body. Diagnosis of pigmented lesions is challenging even for experienced dermatologists due to the wide range of morphological manifestations. Artificial intelligence technologies are capable of equaling and even surpassing the capabilities of a dermatologist in terms of efficiency. The main problem of implementing intellectual analysis systems is low accuracy. One of the possible ways to increase this indicator is using stages of preliminary processing of visual data and the use of heterogeneous data. The article proposes a multimodal neural network system for identifying pigmented skin lesions with a preliminary identification, and removing hair from dermatoscopic images. The novelty of the proposed system lies in the joint use of the stage of preliminary cleaning of hair structures and a multimodal neural network system for the analysis of heterogeneous data. The accuracy of pigmented skin lesions recognition in 10 diagnostically significant categories in the proposed system was 83.6%. The use of the proposed system by dermatologists as an auxiliary diagnostic method will minimize the impact of the human factor, assist in making medical decisions, and expand the possibilities of early detection of skin cancer.

Currently, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in patients with cancer. Biopsy methods are an invasive research method and are not always available for primary diagnosis. Imaging methods have low accuracy and depend on the experience of the dermatologist. Artificial intelligence technologies can match and surpass visual analysis methods in accuracy, but they have the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. One possible way to improve accuracy and reduce the risk of false negatives is to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The paper proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The accuracy of recognition in 10 diagnostically significant categories for the proposed system was 85.19%. The novelty of the proposed system lies in the use of cross-entropy loss when training the modified function with the help of weight coefficients. The introduction of weighting factors has reduced the number of false negative forecasts, as well as improved accuracy by 1.02-4.03 percentage points compared to the original multimodal systems. The introduction of the proposed multimodal system as an auxiliary diagnostic tool can reduce the consumption of financial and labor resources involved in the medical industry, as well as increase the chance of early detection of skin cancer.

Implants are now the standard method of replacing missing or damaged teeth. Despite the improving technologies for the manufacture of implants and the introduction of new protocols for diagnosing, planning, and performing implant placement operations, the percentage of complications in the early postoperative period remains quite high. In this regard, there is a need to develop new methods for preliminary assessment of the patient’s condition to predict the success of single implant survival. The intensive development of artificial intelligence technologies and the increase in the amount of digital information that is available for analysis make it relevant to develop systems based on neural networks for auxiliary diagnostics and forecasting. Systems based on artificial intelligence in the field of dental implantology can become one of the methods for forming a second opinion based on mathematical decision making and forecasting. The actual clinical evaluation of a particular case and further treatment are carried out by the dentist, and AI-based systems can become an integral part of additional diagnostics. The article proposes an artificial intelligence system for analyzing various patient statistics to predict the success of single implant survival. As the topology of the neural network, the most optimal linear neural network architectures were developed. The one-hot encoding method was used as a preprocessing method for statistical data. The novelty of the proposed system lies in the developed optimal neural network architecture designed to recognize the collected and digitized database of various patient factors based on the description of the case histories. The accuracy of recognition of statistical factors of patients for predicting the success of single implants in the proposed system was 94.48%. The proposed neural network system makes it possible to achieve higher recognition accuracy than similar neural network prediction systems due to the analysis of a large number of statistical factors of patients. The use of the proposed system based on artificial intelligence will allow the implantologist to pay attention to the insignificant factors affecting the quality of the installation and the further survival of the implant, and reduce the percentage of complications at all stages of treatment. However, the developed system is not a medical device and cannot independently diagnose patients. At this point, the neural network system for analyzing the statistical factors of patients can predict a positive or negative outcome of a single dental implant operation and cannot be used as a full-fledged tool for supporting medical decision-making.

Fast and accurate processing of electroencephalogram (EEG) signals is necessary for correct realization of neurointerfaces. Neural network is one of the ways of its processing. In this article the method of EEG processing with the help of multilayer perceptron trained by the algorithm of error backpropagation is considered. The results of modeling during training of the neural network showed the minimum value of the Mean Squared error.