Medical Decision Support System Research Articles

Artificial intelligence in dentistry: A bibliometric analysis from 2000 to 2023

Background/purposeArtificial intelligence (AI) is reshaping clinical practice in dentistry. This study aims to provide a comprehensive overview of global trends and research hotspots on the application of AI to dentistry. Materials and methodsStudies on AI in dentistry published between 2000 and 2023 were retrieved from the Web of Science Core Collection. Bibliometric parameters were extracted and bibliometric analysis was conducted using VOSviewer, Pajek, and CiteSpace software. ResultsA total of 651 publications were identified, 88.7 % of which were published after 2019. Publications originating from the United States and China accounted for 34.5 % of the total. The Charité Medical University of Berlin was the institution with the highest number of publications, and Schwendicke and Krois were the most active authors in the field. The Journal of Dentistry had the highest citation count. The focus of AI in dentistry primarily centered on the analysis of imaging data and the dental diseases most frequently associated with AI were periodontitis, bone fractures, and dental caries. The dental AI applications most frequently discussed since 2019 included neural networks, medical devices, clinical decision support systems, head and neck cancer, support vector machine, geometric deep learning, and precision medicine. ConclusionResearch on AI in dentistry is experiencing explosive growth. The prevailing research emphasis and anticipated future development involve the establishment of medical devices and clinical decision support systems based on innovative AI algorithms to advance precision dentistry. This study provides dentists with valuable insights into this field.

Design of exact reduct rough set hardware accelerator for early-stage diabetes risk prediction

Diabetes is a prevalent, chronic metabolic disorder worldwide. Detecting and predicting risks early are vital for timely intervention. In this paper, the design and implementation of an Exact Reduct Rough Set Hardware Accelerator is presented for early-stage diabetes risk prediction. The proposed hardware accelerator leverages the principles of Rough Set theory to identify essential features or attributes (reducts) from a large dataset that effectively predict the risk of diabetes at an early stage. The architecture of the hardware accelerator is optimized to efficiently handle large datasets commonly encountered in medical applications. It includes modules for data preprocessing, discernibility, matrix computation, and reduct determination. The proposed design is implemented on SPARTAN -6 Field Programmable Gate Array; it works on 100 MHz and supports 3 stages pipelining. The extensive experimentation, employing a comprehensive dataset of diabetes patients, unequivocally demonstrates the hardware accelerator's superior performance compared to traditional methods and software-based implementations. The Exact Reduct Rough Set Hardware Accelerator provides a powerful tool for medical professionals to identify patients at risk early on, enabling timely interventions and personalized care to improve patient health outcomes. The proposed accelerator contributes to the growing field of medical decision support systems and holds promise for broader applications in healthcare and beyond. The findings from this study can be seamlessly incorporated into the system-on-chip platform, contributing to the creation of intelligent tools for monitoring and managing diabetes. By offloading rough set computations to hardware accelerators on the wearable device, the data does not need to be continuously transmitted to external servers for analysis, ensuring user privacy and reducing communication overhead.

A three-way decision method based on cumulative prospect theory for the hierarchical diagnosis and treatment system of chronic diseases

With the increase in the number of patients with chronic diseases, the contradiction between medical resources and the demand for medical services is increasingly stressed. The hierarchical medical system becomes an important measure to efficiently allocate medical resources. Given that the two-way referral of patients is a core issue of a hierarchical medical system, this paper takes the upward referral as an example and constructs a three-way decision model for the hierarchical diagnosis and treatment system of chronic diseases, which takes teleconsultation as a compromise. Firstly, considering the credibility of decision-making information, a new representation of the loss function is proposed by combining the subjective evaluations of doctors with the personal preferences of patients. Secondly, the credibility adjustment rules are designed, subject to the constraints of the loss function. Furthermore, taking into account the doctors’ psychological behaviors such as risk attitudes when facing uncertain decisions, a three-way decision model based on the cumulative prospect theory was constructed. The main highlight and contribution of this paper is to put forward a new form of the loss function and the adjustment method of the loss function. A medical decision support system is designed based on the proposed method. Finally, a real case of upward referral of patients with coronary heart disease in First Hospital of Qinhuangdao is given to illustrate the validity of the proposed method, and comparisons are conducted to show the superiority of the method. This study provides methodical support for the hierarchical diagnosis and treatment system in the medical field, and it is conducive to promoting the equalization of basic medical services, which has potential theoretical and practical significance.

A Diabetic Retinopathy Classification and Analysis Towards the Development of a Computer-Aided Medical Decision Support System

A Diabetic Retinopathy Classification and Analysis Towards the Development of a Computer-Aided Medical Decision Support System

Признаки прогрессирования заболевания сетчатки глаза, используемые для повышения валидности системы поддержки принятия врачебных решений на основе искусственного интеллекта

Purpose is to determine the most significant diagnostic signs of retinal disease progression, which are used to increase the validity of the medical decision support system (mdSS) for describing oct images using the method of an expert survey. Material and methods. An expert analysis of the binary signs used in mdSS when describing the oct image of the macular area was carried out: each sign was assessed in terms of the development of the pathological process, the need for telemedicine consultation and (or) referral of patients to a medical organization. The expert method included a survey of 15 ophthalmologists with the necessary qualifications. the experts were asked to rank on a ten-point scale 123 binary signs used by mdSS to form a conclusion about the need for referral to an ophthalmological department for specialized medical care. Results and discussion. The conducted expert survey showed a similar understanding of the signs obtained in the description of retina oct image, which can be used as predictors of the deterioration of the clinical course of the disease in patients with a previously diagnosed diagnosis. If there are signs identified as predictors of the pathological process, mdSS offers to go to the portal «telemedical system of remote consultations of the federal and regional levels» (https://fcmk.minzdrav.gov.ru/), upload the received documents to receive advice on patient routing. Conclusion. The established list of diagnostic features allowed to increase the validity of mdSS in terms of substantiating the conclusion about the need to refer the patient for a consultation with an ophthalmologist to resolve the issue of providing timely specialized medical care. this mdSS can be used as an information service in the work of specialists with higher medical education, a certificate of a medical specialist in the field of «ophthalmology», helps to structure data when uploading to an existing portal of telemedicine consultations. Keywords: retinal diseases, OCT, medical decision support system, signs of disease progression

A comparative study of classification techniques in data mining algorithms used for medical diagnosis based on DSS

A significant amount of data is gathered by the healthcare sector, but it is not appropriately mined and utilized. Finding these hidden links and patterns is frequently underutilized. Our study focuses on this element of medical diagnostics by identifying patterns in the information gathered about kidney illness, liver disease, and chronic pancreatitis (CP) and designing adaptive medical decision support systems (MDSS) to assist doctors. This research compares a variety of data mining (DM) techniques, knowledge extraction tools, and software platforms for usage in a DSS for analysis using the Waikato environment for knowledge analysis (WEKA) mining tool (decision tree (DT)). The objective is to determine the most significant risk factors based on the extraction of the categorization criteria. The datasets used for this work are illustrates how successfully DM and DSS are integrated. In this research, we suggest using the C4.5 DT algorithm, Naïve Bayes (NB) algorithm, and the logistic regression (LR) algorithm to categorize these diseases and evaluate their performance and accuracy rates. It inferred that the C4.5 algorithm accuracy is 0.873% which is better than the other two algorithms in terms of rule generation and accuracy.

Classification of Chest X-ray Images using CNN for Medical Decision Support System

X-rays are a crucial tool used by healthcare professionals to diagnose a range of medical conditions. However, it is important to keep in mind that a timely and accurate diagnosis is crucial for effective patient management and treatment. While chest X-rays can provide highly precise anatomical data, manual interpretation of the images can be time-consuming and prone to errors, which can lead to delays or incorrect diagnoses. To address these issues, healthcare systems have taken steps to improve diagnostic imaging services following the impact of the COVID-19 pandemic. While deep learning-based automated systems for classifying chest X-rays have shown promise, there are still several challenges that need to be addressed before they can be widely used in clinical settings, including the lack of comprehensive and high-quality datasets. To overcome these limitations, a real-time DICOM dataset, has been converted to JPEG format to increase processing speed and improve data control. Three pre-trained models and a convolutional neural network (CNN) model with low complexity and three convolutional layers for feature extraction, along with max pooling layers and ReLU and Softmax activation functions have been implemented. With an validation accuracy of 95.05% on their CNN model using the SGD optimizer, the result has been validated using a separate, real-time unlabeled DICOM dataset of 1000 X-ray images.

Automatic Brain Tumor Detection and Volume Estimation in Multimodal MRI Scans via a Symmetry Analysis

In this study, an automated medical decision support system is presented to assist physicians with accurate and immediate brain tumor detection, segmentation, and volume estimation from MRI which is very important in the success of surgical operations and treatment of brain tumor patients. In the proposed approach, first, tumor regions on MR images are labeled by an expert radiologist. Then, an automated medical decision support system is developed to extract brain tumor boundaries and to calculate their volumes by using multimodal MR images. One advantage of this study is that it provides an automated brain tumor detection and volume estimation algorithm that does not require user interactions by determining threshold values adaptively. Another advantage is that, because of the unsupervised approach, the proposed study realized tumor detection, segmentation, and volume estimation without using very large labeled training data. A brain tumor detection and segmentation algorithm is introduced that is based on the fact that the brain consists of two symmetrical hemispheres. Two main analyses, i.e., histogram and symmetry, were performed to automatically estimate tumor volume. The threshold values used for skull stripping were computed adaptively by examining the histogram distances between T1- and T1C-weighted brain MR images. Then, a symmetry analysis between the left and right brain lobes on FLAIR images was performed for whole tumor detection. The experiments were conducted on two brain MRI datasets, i.e., TCIA and BRATS. The experimental results were compared with the labeled expert results, which is known as the gold standard, to demonstrate the efficacy of the presented method. The performance evaluation results achieved accuracy values of 89.7% and 99.0%, and a Dice similarity coefficient value of 93.0% for whole tumor detection, active core detection, and volume estimation, respectively.

Сontemporary Medical Decision Support Systems Based on Artificial Intelligence for the Analysis of Digital Mammographic Images

The relevance of implementing artificial intelligence (AI) technologies in the diagnosis of breast cancer (BC) is associated with a continuing high increase in BC incidence among women and its leading position in the structure of cancer incidence. Theoretically, using AI technologies is possible both at the stage of screening and in clarifying BC diagnosis. The article provides a brief overview of AI systems used in clinical practice and discusses their prospects in BC diagnosis. Advances in machine learning can be effective to improve the accuracy of mammography screening by reducing missed cancer cases and false positives.

StoneNet: An Efficient Lightweight Model Based on Depthwise Separable Convolutions for Kidney Stone Detection from CT Images.

Kidney stone disease is one of the most common and serious health problems in much of the world, leading to many hospitalizations with severe pain. Detecting small stones is difficult and time-consuming, so an early diagnosis of kidney disease is needed to prevent the loss of kidney failure. Recent advances in artificial intelligence (AI) found to be very successful in the diagnosis of various diseases in the biomedical field. However, existing models using deep networks have several problems, such as high computational cost, long training time, and huge parameters. Providing a low-cost solution for diagnosing kidney stones in a medical decision support system is of paramount importance. Therefore, in this study, we propose "StoneNet", a lightweight and high-performance model for the detection of kidney stones based on MobileNet using depthwise separable convolution. The proposed model includes a combination of global average pooling (GAP), batch normalization, dropout layer, and dense layers. Our study shows that using GAP instead of flattening layers greatly improves the robustness of the model by significantly reducing the parameters. The developed model is benchmarked against four pre-trained models as well as the state-of-the-art heavy model. The results show that the proposed model can achieve the highest accuracy of 97.98%, and only requires training and testing time of 996.88s and 14.62s. Several parameters, such as different batch sizes and optimizers, were considered to validate the proposed model. The proposed model is computationally faster and provides optimal performance than other considered models. Experiments on a large kidney dataset of 1799 CT images show that StoneNet has superior performance in terms of higher accuracy and lower complexity. The proposed model can assist the radiologist in faster diagnosis of kidney stones and has great potential for deployment in real-time applications.

Uncovering the Black Box of Coronary Artery Disease Diagnosis: The Significance of Explainability in Predictive Models

In recent times, coronary artery disease (CAD) prediction and diagnosis have been the subject of many Medical decision support systems (MDSS) that make use of machine learning (ML) and deep learning (DL) algorithms. The common ground of most of these applications is that they function as black boxes. They reach a conclusion/diagnosis using multiple features as input; however, the user is oftentimes oblivious to the prediction process and the feature weights leading to the eventual prediction. The primary objective of this study is to enhance the transparency and comprehensibility of a black-box prediction model designed for CAD. The dataset employed in this research comprises biometric and clinical information obtained from 571 patients, encompassing 21 different features. Among the instances, 43% of cases of CAD were confirmed through invasive coronary angiography (ICA). Furthermore, a prediction model utilizing the aforementioned dataset and the CatBoost algorithm is analyzed to highlight its prediction making process and the significance of each input datum. State-of-the-art explainability mechanics are employed to highlight the significance of each feature, and common patterns and differences with the medical bibliography are then discussed. Moreover, the findings are compared with common risk factors for CAD, to offer an evaluation of the prediction process from the medical expert’s point of view. By depicting how the algorithm weights the information contained in features, we shed light on the black-box mechanics of ML prediction models; by analyzing the findings, we explore their validity in accordance with the medical literature on the matter.

Identification of TLE Focus from EEG Signals by Using Deep Learning Approach.

Temporal lobe epilepsy, a neurological disease that causes seizures as a result of excessive neural activities in the brain, is the most common type of focal seizure, accounting for 30-35% of all epilepsies. Detection of epilepsy and localization of epileptic focus are essential for treatment planning and epilepsy surgery. Currently, epileptic focus is decided by expert physician by examining the EEG records and determining EEG channel where epileptic patterns begins and continues intensely during seizure. Examination of long EEG recordings is very time-consuming process, requires attention and decision can vary depending on physician. In this study, to assist physicians in detecting epileptic focus side from EEG recordings, a novel deep learning-based computer-aided diagnosis system is presented. In the proposed framework, ictal epochs are detected using long short-term memory network fed with EEG subband features obtained by discrete wavelet transform, and then, epileptic focus identification is realized by using asymmetry score. This algorithm was tested on EEG database obtained from the Ankara University hospital. Experimental results showed ictal and interictal epochs were classified with accuracy of 86.84%, sensitivity of 86.96% and specificity of 89.68% on Ankara University hospital dataset, and 96.67% success rate was obtained on Bonn EEG dataset. In addition, epileptic focus was identified with accuracy of 96.10%, sensitivity of 100% and specificity of 93.80% by using the proposed deep learning-based algorithm and university hospital dataset. These results showed that proposed method can be used properly in clinical applications, epilepsy treatment and surgical planning as a medical decision support system.

Ways to improve the efficiency of implementing artificial intelligence systems in medical practice

BACKGROUND: The medical market offers interesting solutions that use artificial intelligence (AI) technologies; however, such solutions often remain at the startup level or are used locally. The question is how to achieve the maximum when introducing AI systems into medical practice. AIM: To answer the question of why the large number of existing developments in AI and medical decision support systems are not used as widely as medical information systems, telemedical consultations, and other health IT solutions. Possible ways to improve the efficiency of implementing AI technologies and medical decision support systems in the work of physicians were presented. METHODS: Theoretical and general scientific (analysis of literature and Internet sources on the problem of research, synthesis, generalization, comparison, and systematization) and empirical (observation, interview, and testing) methods were used. RESUTLS: The main barriers to the effective implementation of AI systems in medical practice and possible options to solve the following problems were highlighted. Problem 1: incorrect data collection. Solution: care must be taken with the accumulation of materials used for the analysis and training by AI systems in medicine. Problem 2: incompetent developers. Solutions: involvement of effective third-party specialists or training ones own. Problem 3: medical workers and/or patients aversion to AI technologies. Solutions: education in the successful application of AI technologies and medical decision support systems in healthcare and involvement of practicing physicians as experts during the AI conceptualization. CONCLUSIONS: If the above criteria for the development and use of AI technologies and medical decision support systems are met, the effect of their introduction into medical practice will tend to be maximized.

Identification predictors of risk of dental implant rejection in the early postoperative period

BACKGROUND: The modern model of healthcare requires a paradigm shift in the thinking of healthcare managers, doctors, and patients. A personalized approach, identification of possible causes of diseases, and prevention of pathologies are the components of successful and quality healthcare delivery in our country. Dentistry is a field in which preventive, prophylactic, and personalized medicine is an integral part of patient care. One of the important tasks of modern digital dentistry is to find indicators that allow for predicting dental implant complications. The solution to this problem could be the creation of a medical decision support system that allows predicting outcomes before implant surgery. AIMS: To reliably identify predictors of early (up to 6 months) risk of dental implant rejection by applying hierarchical Bayesian survival analysis models. METHODS: Data collected retrospectively for patients who underwent dental implant placement between 2013 and 2022 were considered information bases. Data were generated from multicenter surveys conducted in dental implant centers in Stavropol, Moscow, and Penza. The total number of observed cases was 1472. A group of defined factors was considered candidate risk predictors, and the Bayesian hierarchical Cox model (Gsslasso Cox) was used to identify risk predictors. RESULTS: After retrospective analysis of the collected data and screening out incomplete and poor-quality information, the database included a total of 39 variables (factors) for 1472 observations (implants). The multivariate analysis yielded the following predictors of risk of early dental implant rejection: male sex (hazard ratio [HR] 2.388, 95% confidence interval [CI] 1.345; 4.240, p=0.003), age at implantation (years; HR1.034, 95% CI 1.0081.041, p=0.011), oral hygiene (SilnesLow index; HR 2.439, 95% CI 1.2054.701, p=0.051), osteoporosis (HR 5.512, 95% CI 3.6848.248, p 0.001), bone width (mm; HR 0.823, 95% CI 0.7160.944, p=0.006), anesthetic type (local; HR 0.469, 95% CI 0.2340.944, p=0.034), localized periodontitis (HR 2.024, 95% CI 1.4522.821, p=0.039), and low-festooned, thick gingiva (HR=0.485; 95% CI: 0.358-0.658; p=0.0104). CONCLUSIONS: This study shows that predictors of risk of dental implant rejection can be identified separately in the early postoperative period (up to 6 months) by using hierarchical Bayesian survival analysis models, and risk predictors different from those in the longer term are identified in this period.

A novel Swarm Optimized Clustering based genetic algorithm for medical decision support system

The clinical and diagnostic levels of medical decision-making may benefit from use of machine learning techniques. Algorithms for feature selection provide an basis about machine learning. The most discriminating health-related traits from the initial feature set may be quickly and effectively identified in a medical context by using feature selection. Choosing the most relevant attributes of data classes and improving classification performance are the two main goals of feature selection algorithms. The process of feature selection not only identifies the most useful characteristics but also aids in lowering the dataset's overall dimensions. Hence in this article, we propose a novel algorithm based on machine learning. Initially, the dataset is collected and preprocessed using normalisation method. The features are extracted using Linear Discriminant Analysis (LDA) and the relevant features are selected using the proposed Swarm Optimized Clustering based Genetic Algorithm (SOC-GA). On the healthcare datasets, we implemented the suggested method into action. Using Random Forest (RF) and Support Vector Machine (SVM) classifiers, performances of chosen feature subsets are assessed based on accuracy. The empirical findings from our studies in this research are competitive in terms of accuracy and outperformed the other well-known feature selection methods. This research offers remedies that might improve the accurate, efficient and trustworthy decision-making process in healthcare systems for targeted medical treatments.

Adoption and utilization of medical decision support systems in the diagnosis of febrile Diseases: A systematic literature review

Medical decision support systems (MDSS) utilized for medical diagnosis aim to improve patient care; they do so by simulating the human cognitive process in order to arrive at a valid clinical conclusion. Medical decision support systems play a significant role in promoting an efficient and effective health care system. However, the adoption and usage of these systems in daily medical practice have been slow due to a lack of physician confidence in the systems and concerns about the erosion of professional autonomy, obscure physicians’ role, and diminished physician-patient relationships. Despite successes in the development of decision support systems, there is still a low adoption and utilization of MDSSs. This study reviews the development, adoption, and utilization of MDSSs in diagnosing Febrile Diseases between 2008 - 2020. We carried out a systematic literature review on the adoption and utilization of MDSS in diagnosing Febrile Diseases using guidelines provided in literature for systematic reviews and a PRISMA flow to guide paper selection, inclusion, and exclusion criteria. Three reviewers independently carried out literature searches on selected databases for MDSS to diagnose febrile diseases. After the initial searches, the reviewers cross-checked the results, and disagreements were resolved through mutual agreements. The reviewers extracted the data based on an agreed template, and a separate set of reviewers cross-checked this. The extracted data was then synthesized, analyzed, and split into various themes to answer the research questions. We identified 113 papers on MDSS development and utilization and 15 papers on studies relating to the adoption of MDSS. The analysis revealed that Fuzzy Logic was the most prevalent model of MDSS in use, while most models discussed in the papers were unimplemented. The results show that the main reason for proposing these models was to improve accuracy and precision. The main factors influencing the adoption of these models by medical facilities were usefulness, relative advantage, and ease of use. However, the reasons for adopting MDSS by the medical facilities were not expressed in 50% of the studies. In contrast, most of those who adopted MDSS disclosed that it was used to improve effectiveness and adherence to guidelines. Finally, compared to WHO statistics, it was determined that the number of papers did not correspond to the disease burden in the research continents. Although considerable research has been carried out on the adoption and utilization of MDSS, there is a paucity of research on implemented models of MDSS. Despite the advances in MDSSs and their accuracy in diagnosing diseases, many developed models have remained unimplemented in clinical practice. Future studies should focus on encouraging the actual usage of existing models that have not been implemented and conducting research on diseases with a high burden in their context. Governments and medical facility managers need to implement new policies, guidelines, and a support structure that will encourage the adoption and actual usage of MDSS in daily medical practice.

Algorithms for Monitoring the Effectiveness of Therapeutic and Rehabilitation Procedures Based on Clinical Blood Analysis Indicators in the Medical Decision Support System

The purpose of research is development of algorithms for a computer system for monitoring the effectiveness of therapeutic procedures in terms of clinical blood analysis.Methods. A set of algorithms has been developed for a computer system for monitoring the effectiveness of medicinal prescriptions based on the results of a clinical blood test, including an algorithm for analyzing the dynamics of intercellular ratios in a clinical blood test, an algorithm for filling in a database, an algorithm for forming a base of decisive rules, an algorithm for analyzing the sensitivity of a decisive rule.Results. To determine the effectiveness of the treatment plan, it is proposed to evaluate intercluster distances between clustered pathological conditions using the PNN-FNN-FNN* neural network, built on a hybrid basis using probabilistic neural networks and fuzzy decision-making logic. The proposed structure of the PNN-FNN-FNN* hybrid neural network contains three macrolayers. The number of modules in macrolayers is equal to the number of selected clusters of the monitored disease. The first macrolayer consists of blocks of probabilistic neural networks, the number of which in each module is determined by the number of segments allocated in the space of informative features. The second and third macrolayers consist of two-layer fuzzy neural networks. The fuzzy neural network module with the FNN* structure is a block-type macrolayer, each of the blocks of which consists of two layers.Conclusion. Approbation of monitoring algorithms was carried out on an experimental group of patients with benign prostatic hyperplasia and patients with prostate cancer. Experimental studies of the classification quality indicators of a hybrid neural network with the PNN-FNN-FNN* structure in monitoring the effectiveness of treatment of urological patients have shown diagnostic indicators that allow us to recommend it for use in medical decision support systems when monitoring the effectiveness of treatment of urological patients.

Development of Bioimpedance Spectroscopy Technology in Medical Decision Support Systems

The purpose of research – development of bioimpedance spectroscopy methods to develop on their basis objective and realistically accessible criteria for assessing the severity and prognosis of diseases, as well as evaluating the effectiveness of treatment methods, developing criteria for the use of conservative therapy options and surgical interventions in severe patients.Methods. The proposed method involves the use of a recurrent modified Voigt model as a biomaterial segment impedance model. For each model of a biomaterial segment, a Cole plot is plotted in a given frequency range. At the stage of determining the parameters of each of the models, a recurrent procedure is performed, which is the solution of systems of nonlinear equations, starting from one link of the Voight model with a subsequent increase in their number at each iteration step, until the value of the approximation error by the Voight model of the Cole experimental plot reaches allowed value.Results. As a result of the study, fundamentally new results have been obtained that allow creating intelligent decision support systems for diagnosing socially significant diseases. A bioimpedance analysis model based on multifrequency bioimpedance measurement has been created, which makes it possible to decompose the biomaterial impedance into structural elements, on the basis of which to determine descriptors for neural network classifiers of medical risk. In the work, an analysis of classifier errors was carried out in classifying the risk of acute destructive pancreatitis, which showed that the maximum value of the quality indicators of various classifier models was 78%, the minimum was 62%, demonstrating close values to the quality indicators of the ultrasound diagnostic method.Conclusion. The use of multifrequency sensing and modified Voight models in neural network classifiers of medical risk makes it possible to build clinical decision support systems for diagnosing socially significant diseases, as well as the ability to improve classification quality indicators and expand the functionality of intelligent medical decision-making systems.

Compensatory mechanisms of reduced interhemispheric EEG connectivity during sleep in patients with apnea

We performed a mathematical analysis of functional connectivity in electroencephalography (EEG) of patients with obstructive sleep apnea (OSA) (N = 10; age: 52.8 ± 13 years; median age: 49 years; male/female ratio: 7/3), compared with a group of apparently healthy participants (N = 15; age: 51.5 ± 29.5 years; median age: 42 years; male/female ratio: 8/7), based on the calculation of wavelet bicoherence from nighttime polysomnograms. Having observed the previously known phenomenon of interhemispheric synchronization deterioration, we demonstrated a compensatory increase in intrahemispheric connectivity, as well as a slight increase in the connectivity of the central and occipital areas for high-frequency EEG activity. Significant changes in functional connectivity were extremely stable in groups of apparently healthy participants and OSA patients, maintaining the overall pattern when comparing different recording nights and various sleep stages. The maximum variability of the connectivity was observed at fast oscillatory processes during REM sleep. The possibility of observing some changes in functional connectivity of brain activity in OSA patients in a state of passive wakefulness opens up prospects for further research. Developing the methods of hypnogram evaluation that are independent of functional connectivity may be useful for implementing a medical decision support system.

Blockchain-Based Medical Decision Support System

An urgent task at this moment is the use of blockchain technology to ensure the security of medical decision support systems (MDSS). Our research is devoted to development of blockchain-based MDSS (regarding possibility or impossibility of organ and tissue donation/transplantation, regarding possibility or impossibility of using reproductive technologies in the treatment of infertility). The developed blockchain-based medical decision support system provides reliable protection and security of medical information through the use of blockchain technology, provides support of decision regarding possibility or impossibility of organ and tissue donation/transplantation, provides support of decision regarding possibility or impossibility of use of reproductive technologies in the infertility treatment. The proposed blockchain-based medical decision support system: automates medical decision-making processes, minimizes the human factor and its influence on the medical decision process, and takes into account the norms of current legislation when making medical decisions, thereby allowing not to pay for the services of a hired lawyer, and also works with verified and protected medical data entered in the blockchain, which allows you to get rid of leaks of medical information and to ensure reliable protection of medical data.