Non-invasive Diagnostic System Research Articles

Evaluation of tooth-specific optical properties for the development of a non-invasive pulp diagnostic system using Transmitted-light plethysmography: An in vitro study.

Transmitted-light plethysmography (TLP) is an objective and non-invasive pulp diagnosis method that has already been validated for applications for incisors. However, there is a demand for TLP use in the molars, it has not yet been established for this application. This study investigated the optimal light source wavelengths for TLP in premolars, to establish a pulp diagnosis system based on measuring pulpal blood flow. One extracted incisor and one extracted premolar, which were fully developed and healthy, were prepared. The optical properties of model teeth filled with 0-30 % hematocrit contents in the pulp chamber were analyzed at 525, 590, and 625 nm wavelengths. The incident and transmitted light intensity of model teeth were measured to determine the optical density (O.D.) using a prototype plethysmograph (J.Morita) and a spectrometer. The significant differences in O.D. at each wavelength were analyzed using the Kruskal-Wallis test followed by the Steel-Dwass test as a post-hoc test. Light propagation through the teeth was also observed under a microscope. A statistically significant differences in O.D. were observed among the three wavelengths at all hematocrit concentrations (p < 0.05). The observation of light absorption and scattering in the whole teeth supported the optical measurement results. The results indicated that the most appropriate wavelengths are 525 nm for incisors and 590 nm for premolars, as it balanced the light transmission through the tooth structure and the sensitivity for detecting changes in blood concentration. Further research is expected to expand the range of applications of TLP in premolars.

A comprehensive machine learning framework with particle swarm optimization for improved polycystic ovary syndrome (PCOS) diagnosis

Polycystic Ovary Syndrome (PCOS) is a hormonal disorder primarily affecting women of reproductive age, characterized by irregular menstrual cycles, elevated male hormones, and ovarian cysts. Early detection and treatment are crucial to prevent long-term complications. This research utilizes clinical data from Kaggle to develop a non-invasive PCOS diagnostic system. The authors conducted comprehensive data preprocessing, feature engineering, and exploratory data analysis (EDA). The refined dataset was incorporated into various default machine learning (ML) algorithms, including LR, LDA, GNB, SVM, XGB, DT, AB, RF, and KNN, for PCOS classification with varying train test ratios 70:30 to 80:20. To further enhance the model’s performance, the authors hybridized all the ML models with Particle Swarm Optimization (PSO). Remarkably, the proposed LR+PSO model achieved the highest accuracy at 96.30%, demonstrating exceptional proficiency with an 80:20 train-test ratio. It significantly improved sensitivity to 94.44%, indicating enhanced detection of positive cases, all while maintaining the highest specificity at 97.22% and precision at 94.44% compared to other models. These results highlight a substantial improvement in integrated models, emphasizing the potential of this novel approach to enhance PCOS diagnosis in terms of accuracy and efficiency, ultimately benefiting individuals with PCOS in their treatment journey.

Tear film assessment before and after phacoemulsification in patients with age-related cataracts

BackgroundThe study aims to assess the tear film before and after phacoemulsification in patients with age-related cataracts.MethodsA prospective observational study of 41 age-related cataract patients undergoing phacoemulsification procedure. Tear Film Break-Up Time (TBUT), Tear Film Meniscus Height (TMH), Meibomian glands (MG), and Lipid Layer Thickness (LLT) were assessed by a non-invasive Dry Eye Diagnostic System. All measurements were taken preoperatively, one week, one month, and three months postoperatively. The Marginal homogeneity and The Cochran Q tests were used in the statistical analysis.ResultsThe value of Non-Invasive Break-Up Time (NITBUT) was statistically significantly lower at one week (7.15 ± 3.31), one month (7.61 ± 3.41), and three months (7.66 ± 3.36) postoperatively than preoperatively (10.71 ± 2.71), p < 0.001. The Non- Invasive Tear Meniscus Height (NITMH) was significantly lower at one week (0.18 ± 0.0), one month (0.20 ± 0.09), and three months (0.20 ± 0.09) postoperatively than preoperatively (0.30 ± 0.113) p < 0.001. By the first month, both (NITBUT) and (NITMH) improved significantly compared to the first post-operative week. There was no statistically significant difference between one month and three months. The (NITMH) improved to a healthy level of ≥ 0.2 mm by the first month through the third month. Both (NITBUT) and (NITMH) did not reach the baseline by the third month. The meibomian glands and the lipid layer thickness had the same preoperative grade distribution without changes.ConclusionPhacoemulsification surgery can cause post-operative deterioration in the tear film, which starts within a week of the procedure, followed by gradual recovery over the next weeks and months. The phacoemulsification procedure mainly affects the tear break-up time and tear meniscus height. Both the lipid layer and meibomian glands are not affected.

'Feeling Hot': Exploring the feasibility of nocturnal erection detection through penile temperature measurements.

The observational 'Feeling Hot' study aims to evaluate the feasibility of employing overnight penile temperature measurements for the detection of nocturnal erections, thereby contributing to the advancement and modernization of a non-invasive diagnostic system for erectile dysfunction. In this proof-of-concept study, 10 healthy men aged 20-25 were recruited, following the methodology outlined in the 'Staying Hot' study by Torenvlied et al. Participants underwent ambulatory overnight penile temperature measurements concurrent with RigiScan recordings. Key outcome measures included baseline and peak penile temperatures during RigiScan-annotated nocturnal erections. Reference measurements of the thigh temperature were also taken to assess nocturnal temperature variations. Statistically significant penile temperature increases (p = 0.008, n = 9) were observed during nocturnal erections, with an average elevation of 1.47°C noted during the initial erections. This underscores the practical utility of penile temperature measurements in detecting erection onset. Challenges arose in accurately determining erection duration and subsequent erection onsets due to the persistence of elevated temperatures following initial erections, termed the 'Staying Hot effect'. Reference thigh temperature measurements aided in addressing this challenge. Examining overnight penile temperature alongside simultaneous RigiScan recordings has yielded valuable insights into the viability of using the temperature methodology for detecting nocturnal erections. The 'Feeling Hot' study findings demonstrate significant penile temperature elevation during nocturnal erections in healthy young men, highlighting the potential of integrating this measurement methodology into the design of a modernized tool for ambulatory erectile dysfunction diagnostics. Further development of an advanced sensor system to comprehensively assess erection duration and quality is essential for enhancing clinical applicability.

Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis.

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

Computational modeling of superparamagnetic nanoparticle-based (affinity) diagnostics.

Magnetic nanoparticles (MNPs), particularly iron oxide nanoparticles (IONPs), are renowned for their superparamagnetic behavior, allowing precise control under external magnetic fields. This characteristic makes them ideal for biomedical applications, including diagnostics and drug delivery. Superparamagnetic IONPs, which exhibit magnetization only in the presence of an external field, can be functionalized with ligands for targeted affinity diagnostics. This study presents a computational model to explore the induced voltage in a search coil when MNPs pass through a simulated blood vessel, aiming to improve non-invasive diagnostic methods for disease detection and monitoring. A finite element model was constructed using COMSOL Multiphysics to simulate the behavior of IONPs within a dynamic blood vessel environment. Governing equations such as Ampère's law and Faraday's law of induction were incorporated to simulate the induced voltage in a copper coil as MNPs of various sizes flowed through the vessel. Rheological parameters, including blood viscosity and flow rates, were factored into the model using a non-Newtonian fluid approach. The amount of MNPs required for detection varies significantly based on the sensitivity of the detection equipment and the size of the nanoparticles themselves. For highly sensitive devices like a SQUID voltmeter, with a coil sensitivity approximately 10-12V, very low MNP concentrations-approximately 10-4μg/mL-are sufficient for detection, staying well within the safe range. As coil sensitivity decreases, such as with standard voltmeters at 10-8V or 10-6V, the MNP concentration required for detection rises, approaching or even exceeding potentially toxic levels. Additionally, the physical size of MNPs plays a role; larger nanoparticles (e.g., 50nm radius) require fewer total particles for detection at the same sensitivity than smaller particles like those with a 2.5nm radius. For instance, at a coil sensitivity of 10-10V, a 2.5nm particle requires approximately 1012 particles, whereas a 50-nm particle only needs 108. This highlights the importance of optimizing both detection sensitivity and particle size to balance effective detection with safety. This computational model demonstrates the feasibility of using superparamagnetic nanoparticles in real-time, non-invasive diagnostic systems.

A Contact-Less Electrically Small Antenna Sensor for Retinal Cancer Cell Detection

A new noninvasive and portable diagnostic system for detecting ocular tumors has been proposed. The system uses a contact-less electrically small antenna sensor to detect retinal cancer cells. The antenna sensor is operated in the ISM (Industrial, Scientific, and Medical) 2.413 GHz band and has electrical dimensions of 8 × 16.2 × 0.35 mm3. The antenna sensor is fabricated on a biodegradable Teslin substrate and tested in an eye-mimicking phantom to compare numerical computations with measurements. The specific absorption rate (SAR) obtained at near and far-field distances under 1 g of tissue is 1.18 W/kg and 0.353 W/kg, and that under 10 g of tissue is 0.112 W/kg and 0.313 W/kg, respectively. Furthermore, to detect the ocular tumor using the proposed antenna sensor, the resonance frequency shift, and the unsupervised machine learning technique, principle component analysis (PCA) is employed on simulated and measured results. The resonance frequency shift for a 3.5 mm radius tumor is 70 MHz for a single tumor and 120 MHz for double tumors. The PCA generates clusters with and without tumors on the positive and negative sides of the two-dimensional plot. The proposed techniques are more impactful in distinguishing between healthy and malignant tissues. The proposed systematic approach could be a portable platform for early detection of cancerous cells inside the eye.

Disagreement of ESC guidelines from 2016 and 2021 and HFA-PEFF and H2 FPEF scores in diagnosis of heart failure with preserved ejection fraction in atrial fibrillation patients

Abstract Funding Acknowledgements Type of funding sources: None. Background Heart failure with preserved ejection fraction (HFpEF) frequently coexists with atrial fibrillation (AF). The gold-standard test for HFpEF diagnosis remains invasive assessment of left ventricular end-diastolic pressures but noninvasive diagnostic scoring systems have been developed to aid accurate diagnosis. However, the diagnosis of HFpEF in patients with AF is more difficult because some diagnostic criteria for HFpEF may be associated with AF instead of HFpEF per se. Purpose To compare the guidelines and scoring systems for HFpEF diagnosis in patients with AF, and to indicate the most relevant clinical and echocardiographic parameters supporting the diagnosis of HFpEF in an AF cohort. Methods Consecutive patients with paroxysmal or persistent AF scheduled for catheter ablation were included. Clinical characteristics and transthoracic echocardiography examination was collected at baseline visit. The European Society of Cardiology (ESC) guidelines from 2016 and 2021 as well as scoring systems (HFA-PEFF and H2FPEF scores) were used to diagnose HFpEF. In the H2FPEF score, patients with AF alone, score of 3, were assessed as group with the low risk for HFpEF (instead of intermediate risk according to the H2FPEF score), as all enrolled patients had AF. Multiple logistic regression was performed to find optimal parameters predicting HFpEF, that was defined as diagnosis of HFpEF according to all following scores: ESC guidelines from 2016 and 2021 and high risk in HF2FPEF and HF-PEFF scores. Results We analysed 325 patients (median age 65 [59-72], 36% women). Considerable differences were observed in HFpEF diagnoses when stratifying patients according to ESC 2016 and ESC 2021 guideline definitions; the percentage of HFpEF patients reduced from 55% (n=180) to 28% (n=90). The agreement of HF2PEF score relative to HFA-PEFF score was 46% (n=25/55), 54% (n=115/213) and 35% (n=20/57) of patients regarding low, intermediate and high risk for HFpEF, respectively. Overall, 5.8% of patients (n=19) had HFpEF (Figure 1). These 19 patients were older (median age 70 vs 65, p&amp;lt;0.001), had more often persistent AF (63% vs 30%; p&amp;lt;0.001) and vascular disease (37% vs 14%, p=0.017) as compared to those without HFpEF. Based on multiple logistic regression, higher values of N-terminal-pro hormone BNP (NT-proBNP; OR 1.02, 95CI 1.01-1.03) and LA volume index (LAVI; OR 1.13, 95%CI 1.04-1.23) were independent predictors of having HFpEF in AF population. The NT-proBNP of 45 pmol/L and LAVI of 45ml/kg2 were ideal cutoffs and constructed a model to predict HFpEF which fitted with a concordance index of 0.91 (95% CI 0.87–0.94) (Figure 2). Conclusions The differences in HFpEF definition in the guidelines and various scoring systems lead to considerable difference in stratification of HFpEF in AF patients. In our population, just 5.8% of AF patients were diagnosed with HFpEF regarding ESC guidelines and high risk for HFpEF in scoring systems.

Using CCA-Fused Cepstral Features in a Deep Learning-Based Cry Diagnostic System for Detecting an Ensemble of Pathologies in Newborns

Crying is one of the means of communication for a newborn. Newborn cry signals convey precious information about the newborn's health condition and their emotions. In this study, cry signals of healthy and pathologic newborns were analyzed for the purpose of developing an automatic, non-invasive, and comprehensive Newborn Cry Diagnostic System (NCDS) that identifies pathologic newborns from healthy infants. For this purpose, Mel-frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) were extracted as features. These feature sets were also combined and fused through Canonical Correlation Analysis (CCA), which provides a novel manipulation of the features that have not yet been explored in the literature on NCDS designs, to the best of our knowledge. All the mentioned feature sets were fed to the Support Vector Machine (SVM) and Long Short-term Memory (LSTM). Furthermore, two Hyperparameter optimization methods, Bayesian and grid search, were examined to enhance the system's performance. The performance of our proposed NCDS was evaluated with two different datasets of inspiratory and expiratory cries. The CCA fusion feature set using the LSTM classifier accomplished the best F-score in the study, with 99.86% for the inspiratory cry dataset. The best F-score regarding the expiratory cry dataset, 99.44%, belonged to the GFCC feature set employing the LSTM classifier. These experiments suggest the high potential and value of using the newborn cry signals in the detection of pathologies. The framework proposed in this study can be implemented as an early diagnostic tool for clinical studies and help in the identification of pathologic newborns.

Abstract 13864: Can Catheter Ablation Be Effective in Patients With Persistent Atrial Fibrillation and Heart Failure With Preserved Ejection Fraction Diagnosed Using HFA-PEFF Score?

Background: The efficiency of atrial fibrillation (AF) ablation for heart failure with preserved ejection fraction (EF) (HFpEF) has not been well investigated due to the difficulty of diagnosing HFpEF. The HFA-PEFF score from the European Society of Cardiology has been introduced as a new non-invasive diagnostic system for HFpEF. Methods: We studied 101 persistent AF patients with EF≥50% who underwent first catheter ablation (age 70±10 years, 68 men). The HFA-PEFF score was calculated as a sum of points in echocardiographic functional and morphological, and biomarker (brain natriuretic peptide: BNP) domains. Based on the HFA-PEFF score, patients were divided into High-group (score of ≥5, n=34) and Low-group (score of &lt;5, n=67). Results: The High-group had older, higher BNP levels, left atrial volume index (LAVI), and E/e' than those in the Low-group. However, after 1.1±0.3 procedures, BNP levels (335±247 to 111±95 vs. 167±107 to 90±134pg/mL) and LAVI (62±19 to 44±12 vs. 52±22 to 42±17ml/m 2 ) were significantly decreased in each (all p&lt;0.05 by paired t-test) and reached levels that were not significantly different in both groups. In addition, during 13.9±15.6 months after the first procedure, although recurrences of AF/atrial tachycardia were observed in 28 patients, the Kaplan-Meier curve analysis revealed no significant difference in recurrence-free survival between the two groups (Log-rank p=0.944, Figure). Conclusion: These data suggest that AF catheter ablation is effective even in patients diagnosed with HFpEF by a high HFA-PEFF score in terms of maintaining sinus rhythm comparable to patients with lower scores and improvements in cardiac function.

Review of the algorithms used in exhaled breath analysis for the detection of diabetes

Currently, intensive work is underway on the development of truly noninvasive medical diagnostic systems, including respiratory analysers based on the detection of biomarkers of several diseases including diabetes. In terms of diabetes, acetone is considered as a one of the potential biomarker, although is not the single one. Therefore, the selective detection is crucial. Most often, the analysers of exhaled breath are based on the utilization of several commercially available gas sensors or on specially designed and manufactured gas sensors to obtain the highest selectivity and sensitivity to diabetes biomarkers present in the exhaled air. An important part of each system are the algorithms that are trained to detect diabetes based on data obtained from sensor matrices. The prepared review of the literature showed that there are many limitations in the development of the versatile breath analyser, such as high metabolic variability between patients, but the results obtained by researchers using the algorithms described in this paper are very promising and most of them achieve over 90% accuracy in the detection of diabetes in exhaled air. This paper summarizes the results using various measurement systems, feature extraction and feature selection methods as well as algorithms such as support vector machines, k-nearest neighbours and various variations of neural networks for the detection of diabetes in patient samples and simulated artificial breath samples.

High-Performance Image Acquisition and Processing for Stereoscopic Diagnostic Systems with the Application of Graphical Processing Units.

In recent years, cinematography and other digital content creators have been eagerly turning to Three-Dimensional (3D) imaging technology. The creators of movies, games, and augmented reality applications are aware of this technology’s advantages, possibilities, and new means of expression. The development of electronic and IT technologies enables the achievement of a better and better quality of the recorded 3D image and many possibilities for its correction and modification in post-production. However, preparing a correct 3D image that does not cause perception problems for the viewer is still a complex and demanding task. Therefore, planning and then ensuring the correct parameters and quality of the recorded 3D video is essential. Despite better post-production techniques, fixing errors in a captured image can be difficult, time consuming, and sometimes impossible. The detection of errors typical for stereo vision related to the depth of the image (e.g., depth budget violation, stereoscopic window violation) during the recording allows for their correction already on the film set, e.g., by different scene layouts and/or different camera configurations. The paper presents a prototype of an independent, non-invasive diagnostic system that supports the film crew in the process of calibrating stereoscopic cameras, as well as analysing the 3D depth while working on a film set. The system acquires full HD video streams from professional cameras using Serial Digital Interface (SDI), synchronises them, and estimates and analyses the disparity map. Objective depth analysis using computer tools while recording scenes allows stereographers to immediately spot errors in the 3D image, primarily related to the violation of the viewing comfort zone. The paper also describes an efficient method of analysing a 3D video using Graphics Processing Unit (GPU). The main steps of the proposed solution are uncalibrated rectification and disparity map estimation. The algorithms selected and implemented for the needs of this system do not require knowledge of intrinsic and extrinsic camera parameters. Thus, they can be used in non-cooperative environments, such as a film set, where the camera configuration often changes. Both of them are implemented with the use of a GPU to improve the data processing efficiency. The paper presents the evaluation results of the algorithms’ accuracy, as well as the comparison of the performance of two implementations—with and without the GPU acceleration. The application of the described GPU-based method makes the system efficient and easy to use. The system can process a video stream with full HD resolution at a speed of several frames per second.

Modified Visual Geometric Group Architecture for MRI Brain Image Classification

The advancement of automated medical diagnosis in biomedical engineering has become an important area of research. Image classification is one of the diagnostic approaches that do not require segmentation which can draw quicker inferences. The proposed non-invasive diagnostic support system in this study is considered as an image classification system where the given brain image is classified as normal or abnormal. The ability of deep learning allows a single model for feature extraction as well as classification whereas the rational models require separate models. One of the best models for image localization and classification is the Visual Geometric Group (VGG) model. In this study, an efficient modified VGG architecture for brain image classification is developed using transfer learning. The pooling layer is modified to enhance the classification capability of VGG architecture. Results show that the modified VGG architecture outperforms the conventional VGG architecture with a 5% improvement in classification accuracy using 16 layers on MRI images of the REpository of Molecular BRAin Neoplasia DaTa (REMBRANDT) database.

Basic Study on non-invasive diagnosis of diabetes using Polarization Sensitive Doppler Optical Coherence Tomography

In this study, a novel non-invasive diagnostic system of diabetes is proposed on the basis of Polarization Sensitive Doppler OCT (PS-D OCT). This can provide not only polarization information of tissue, i.e. retardation, but also capillary network, i.e. Doppler phase, as xy cross-section around upper dermis. In this experiment, PS-D OCT was applied to human forearm skin before and after meal, when blood glucose level was varying. As a result, this system can tomographically visualize insulin secretion function as capillary dilation. Consequently, it was concluded that there could be promising potential of non-invasive diagnosis of diabetes.

Automated newborn cry diagnostic system using machine learning approach

Researchers have found that crying is an acoustic symptom among unhealthy newborns. This study aims to develop a non-invasive newborn cry diagnostic system (NCDS) using information at different levels of the cry audio signal (CAS) of infants. The unhealthy newborn group in our experiment consists of 34 clinical cases. The proposed machine learning (ML) techniques include the extraction of feature sets of Mel frequency cepstral coefficients (MFCC), auditory-inspired amplitude modulation (AAM) features, and a prosody feature set of tilt, intensity, and rhythm features. The training models are probabilistic neural networks and support vector machine algorithms. The feature sets of AAM and MFCC extract low-level patterns, whereas the prosody feature set of tilt, intensity, and rhythm extracts high-level information in an infant CAS. The AAM feature set in the NCDS has never yet been examined. As an innovative aspect of this study, the AAM feature set is included in the NCDS, and this feature set is fused with the feature sets of MFCC and prosody. As another innovation, we reproduce real-world problems by including many pathologies in the unhealthy group. Among the evaluated frameworks proposed, the fusion of all feature sets improves the system performance. The best result is obtained with the fusion of AAM and MFCC with an F-measure of over 80%. The results of this experiment reveal the usefulness of information at different levels within the CASs of newborns, which vary among healthy and unhealthy groups. Moreover, to identify unhealthy newborns, this information can be captured noninvasively by applying ML methods to the NCDS.

Prevalence of Polypoidal Choroidal Vasculopathy Using Non-indocyanine green angiography–based Criteria

Polypoidal choroidal vasculopathy (PCV) is a form of neovascular AMD characterized by polypoidal lesions and branching vascular networks. Diagnosis has traditionally required the use of invasive indocyanine green angiography, though recently a validated non-invasive diagnostic system has been developed that identified PCV-specific features using optical coherence tomography (OCT) and color fundus photography. In this work we applied this new system to a large population-based cohort of ethnic Chinese and successfully identified PCV and related anatomical features. We estimated a population prevalence of 0.31% (95% CI, 0.06-0.91%) and additionally demonstrate that PCV-related retinal findings were relatively rare in the population.

Improvements in Medical System Safety Analytics for Authentic Measure of Vital Signs Using Fault-Tolerant Design Approach.

The study presents a novel design method that improves system availability using fault-tolerant features in a non-invasive medical diagnostic system. This approach addresses the effective detection of functional faults, improves the uninterruptible system operating period with reduced false alarms, and provides an authentic measure of vital cardiac signs using diverse multimodal sensing elements like the photoplethysmogram (PPG) and the ECG. Most systems rely on a 1oo1 (one-out-of-one) design method, which inherently limits accuracy in existing practice. In this proposed approach, the quality of segregated authentic vital sign measured values could tremendously benefit the performance of resourceful nursing with negligible alarm fatigue and predict illness more accurately. The system builds upon the selected 2oo2 (two-out-of-two) safety-related design architecture and is evaluated with implemented functions like the fault detection and identification logic, the correlation coefficient-based safety function, and the fault-tolerant safe degradation switching mechanism for accurate measurements. The system was tested on 50 adults of various age groups. The analyzed captured data showed highly accurate vital sign data in this fault-tolerant approach with reduced false alarms. The proposed design method evaluated safety-related mechanisms along with a combination of the same and diverse sensors in a medical monitoring device, showing more reliable functioning of the system and authentic data for better nursing. This design approach showed a 45–55% increased improvement in system availability, thus allowing for accurate and uninterruptable tracking of vital signs for better nursing during critical times in the ICU.

Circulating miRNAs Related to Epithelial-Mesenchymal Transitions (EMT) as the New Molecular Markers in Endometriosis.

Endometriosis is a chronic gynecological disease defined by the presence of endometrial-like tissue found outside the uterus, most commonly in the peritoneal cavity. Endometriosis lesions are heterogenous but usually contain endometrial stromal cells and epithelial glands, immune cell infiltrates and are vascularized and innervated by nerves. The complex etiopathogenesis and heterogenity of the clinical symptoms, as well as the lack of a specific non-invasive diagnostic biomarkers, underline the need for more advanced diagnostic tools. Unfortunately, the contribution of environmental, hormonal and immunological factors in the disease etiology is insufficient, and the contribution of genetic/epigenetic factors is still fragmentary. Therefore, there is a need for more focused study on the molecular mechanisms of endometriosis and non-invasive diagnostic monitoring systems. MicroRNAs (miRNAs) demonstrate high stability and tissue specificity and play a significant role in modulating a range of molecular pathways, and hence may be suitable diagnostic biomarkers for the origin and development of endometriosis. Of these, the most frequently studied are those related to endometriosis, including those involved in epithelial–mesenchymal transition (EMT), whose expression is altered in plasma or endometriotic lesion biopsies; however, the results are ambiguous. Specific miRNAs expressed in endometriosis may serve as diagnostics markers with prognostic value, and they have been proposed as molecular targets for treatment. The aim of this review is to present selected miRNAs associated with EMT known to have experimentally confirmed significance, and discuss their utility as biomarkers in endometriosis.

Inception Architecture for Brain Image Classification

A non-invasive diagnostic support system for brain cancer diagnosis is presented in this study. Recently, very deeper convolution neural networks are designed for computerized tasks such as image classification, natural language processing. One of the standard architecture designs is the Visual Geometric Group (VGG) models. It uses a large number of small convolution filters (3x3) connected serially. Before applying max pooling, convolution filters are stacked up to four layers to extract features’ abstraction. The main drawback of going deeper is over fitting, and also updating gradient weights is very hard. These limitations are overcome using the inception module, which is wider rather than deeper. Also, it has parallel convolution layers with 3x3, 5x5, and 1x1 filters that reduce the computational complexity due to stacking, and the outputs are concatenated. This study’s experimental results show the usefulness of inception architecture for aiding brain image classification on Repository of Molecular Brain Neoplasia DaTa (REMBRANDT) Magnetic Resonance Imaging (MRI) images with an average accuracy of 95.1%, sensitivity of 96.2%, and specificity of 94%.

Применение полнопротеомного анализа клеток крови, плазмы и мочи для дифференциальной диагностики заболеваний

The paper considers a methodology for creating concepts for new non-invasive diff erential diagnostic systems based on proteomic profi ling of blood cells, plasma and urine. In this case, the relative quantitative information about all proteins found in the samples is used simultaneously. In the presented examples, using machine learning methods, it became possible to separate groups of patients with diabetic nephropathy and glomerulonephritis according to proteomic data of blood plasma, and to separate patients with hypertensive nephropathy from these groups using proteomic data of urine. With the help of regression analysis, it was possible to construct a linear model capable of assessing the moment of the need to initiate therapy in the future for patients at an early stage of chronic lymphocytic leukemia