Search

Machine learning, powered by cloud servers, has found application in medical diagnosis, enhancing the capabilities of smart healthcare services. Research literature demonstrates that the support vector machine (SVM) consistently demonstrates remarkable accuracy in medical diagnosis. Nonetheless, safeguarding patients' health data privacy and preserving the intellectual property of diagnosis models is of paramount importance. This concern arises from the common practice of outsourcing these models to third-party cloud servers that may not be entirely trustworthy. Few studies in the literature have delved into addressing these issues within SVM-based diagnosis systems. These studies, however, typically demand substantial communication and computational resources and may fail to conceal classification results and protect model intellectual property. This paper aims to tackle these limitations within a multi-class SVM medical diagnosis system. To achieve this, we have introduced modifications to an inner product encryption cryptosystem and incorporated it into our medical diagnosis framework. Notably, our cryptosystem proves to be more efficient than the Paillier and multi-party computation cryptography methods employed in previous research. Although we focus on a medical application in this paper, our approach can also be used for other applications that need the evaluation of machine learning models in a privacy-preserving way such as electricity theft detection in the smart grid, electric vehicle charging coordination, and vehicular social networks. To assess the performance and security of our approach, we conducted comprehensive analyses and experiments. Our findings demonstrate that our proposed method successfully fulfills our security and privacy objectives while maintaining high classification accuracy and minimizing communication and computational overhead. [ABSTRACT FROM AUTHOR]

Expert systems are computer programs that use knowledge and reasoning to solve problems typically solved by human experts. Expert systems have been used in medicine to diagnose diseases, recommend treatments, and plan surgeries. Interpretability of the results in medical applications is crucial since the decision that will be taken based on the system's output has a direct effect on people's health and lives which makes expert systems ideal choices when dealing with these applications in contrast to other machine learning approaches. An expert system has the ability to explain its own line of reasoning providing a robust way of diagnosis. This paper presents two types of expert systems for medical diagnosis. The first system is a case-based reasoning system using a database of previously diagnosed cases to diagnose a new case. The second system is a rule-based expert system that uses a set of if–then rules extracted from a decision tree classifier to make diagnoses. In this paper, machine learning-based similarity functions are proposed and compared with other traditional similarity functions. The results of this study suggest that expert systems can be a valuable tool for medical diagnosis. The two systems presented in this paper achieved competitive results, and they provide diagnoses similar to those made by human experts. [ABSTRACT FROM AUTHOR]

Biopolymers have attracted much of interest in various applications needed for sustainable and biodegradable solutions. Indeed, biopolymers lessen the requirement for petroleum‐based resources, municipal solid waste output, and carbon dioxide emissions. Polysaccharides are a unique category of biopolymers that are especially characteristic such as biocompatibility and editability. Polysaccharides functionalization plays a significant role in various applications and their suitability for additive applications. Sensor‐based polysaccharides are widely used with many drawbacks localized in durability, moldability, and sensitivity. Otherwise, biosensors are devices monitoring a specimen's biological phenomena or measurements, usually not disposable devices. For that, biosensors are needed urgently to address the high cost of disposable supplies in the medical diagnostic industry, which span many elements of medical diagnostic applications. Additionally, manipulating of polysaccharide‐based materials is considered accessible and usable and requires low equipment requirements. Herein, the main features of polysaccharides will be discussed, along with potential applications as biosensors for medical diagnosis and new lines of inquiry with such focus on the main required to formulate polysaccharides biosensors. [ABSTRACT FROM AUTHOR]

Flexible sensors, emerging as a novel sensing technology, have progressively garnered substantial interest among researchers. In recent years, there has been a growing emphasis on the utilization of nanofiber assemblies in the advancement of flexible mechanical sensors. This approach bestows upon these sensors several merits including cost-effectiveness, streamlined processing, enhanced user experience, and superior sensing capabilities. The primary objective of this review is to comprehensively assess and summarize the utilization of nanofiber sensors within the realm of flexible mechanical sensing. This endeavor aims to furnish invaluable theoretical and practical insights for the progression of flexible sensor technologies. This paper is centered on the fabrication of nanoflexible fiber sensors, primarily by methods such as polymer direct spinning, blending, nanofiber carbonization, gas phase growth, and nano-modification. Capitalizing on advancements in nanotechnology and leveraging the inherent attributes of nanofibers, and achieving breakthroughs in the development of highly sensitive, wide-range, and rapidly responsive sensors through the ingenious design of multi-tiered sensing structures, the incorporation of high-performance conductive materials, and the construction of intricate three-dimensional conductive network have garnered increasing attention from both academia and industry. Nanofiber-based mechanosensors are electronic devices utilizing flexible nanofiber aggregates as substrates. They possess the capability to detect external mechanical stimuli and convert them into electrical signals. These sensors can be categorized primarily into resistive, capacitive, piezoelectric, and triboelectric types according to their sensing mechanisms. The enhancement of nanofiber resistive flexible sensors predominantly hinges on the optimization of the sensor matrix structure and the conductive network design. Consequently, the development of resistive sensors based on nanofibers primarily revolves around refining the micro/nanostructure on the fiber’s surface and the impact of the macro-aggregate structure on resistive sensing performance. In the area of highly sensitive nanofiber capacitive mechanical sensing, the alteration of dielectric layer morphology and the reduction of compression modulus are pivotal for achieving heightened sensitivity in capacitive flexible sensors. Consequently, research in the field predominantly focuses on dielectric layer preparation. This encompasses aspects such as surface microstructures of nanofibers, composite matrices with nanofiber porosity, and textile/nanofiber composite structures. These endeavors aim to produce capacitive sensors that exhibit both high sensitivity and a broad detection range. Furthermore, to address the existing sensitivity limitations of capacitive sensors operating on the fundamental capacitance principle, there has been a recent emphasis on the concept of introducing ionic conductors into nanofibers. This approach aims to generate bilayer capacitance at the electrolyte-electrode interface, and it has garnered significant attention. In the realm of piezoelectric sensors, researchers have predominantly explored strategies to enhance the piezoelectric performance of polymer-based nanofibers. This includes avenues such as in situ polarization, nano-doping, thermal stretching, and the application of high electric fields. Within the domain of nanofiber-based triboelectric sensors, the primary focus of research centers on the inherent friction characteristics of the materials. Complementary to this, physical and chemical techniques are employed to manipulate the nanometer-scale surface morphology and facilitate surface functionalization of the materials. This, in turn, effectively enhances parameters like contact area, contact characteristics, friction effects, and ultimately augments the performance of triboelectric effect. Flexible mechanical sensors find utility across a broad spectrum of applications, spanning but not confined to domains such as health monitoring, medical diagnostics, human motion detection, and intelligent robotics. This paper undertakes a methodical endeavor to comprehensively encapsulate the multifaceted applications of nanofiber-based flexible sensors across various domains. In the domain of sports, they can be used to monitor athletes’ posture and range, analyze athletes’ movement skills and improve their performance. In the medical field, they can be used to monitor patients’ physiological parameters, such as heart rate, body temperature, blood oxygen and water equality, to realize real-time monitoring of patients’ health status, or to make intelligent medical equipment, such as intelligent artificial limbs and intelligent rehabilitation equipment, to help patients recover their functions and improve their quality of life. In the domain of intelligent robotics, flexible mechanical sensors enable interaction and perception with the environment, elevating the intelligence level of robots and empowering them to perceive user movements and sounds. Overall, the widespread application of flexible sensors significantly enhances the quality of life for individuals in diverse fields. As a vital research direction in flexible mechanical sensing, nanofiber sensors present numerous opportunities and challenges for future development. The distinctive structure and surface properties of nanofibers underpin their exceptional sensor performance, yet their mechanism of action requires further elucidation. By thoroughly exploring the interplay between nanofibers and sensor performance, sensor design and efficacy can be better optimized. Despite their commendable performance in flexible mechanical sensing, current nanofiber sensors encounter certain practical challenges, including limited sensitivity and stability. Consequently, it is imperative to conduct further research and advancements in nanofiber preparation technology to enhance the sensor’s sensitivity and stability. In conclusion, nanofiber sensors represent a promising research trajectory in the field of flexible mechanical sensing, offering vast potential for application. By refining the preparation process, delving deeper into their mechanisms, expanding their application domains, and fostering interdisciplinary collaboration, the performance and applicability of nanofiber sensors can be further enhanced. As science and technology continue to progress, nanofiber sensors are poised to yield more breakthroughs and innovations, contributing significantly to the intelligent and health-oriented development of human society. [ABSTRACT FROM AUTHOR]

Influenza has been a stationary disease in Mexico since 2009, and this causes a high cost for the national public health system, including its detection using RT-qPCR tests, treatments, and absenteeism in the workplace. Despite influenza's relevance, the main clinical features to detect the disease defined by international institutions like the World Health Organization (WHO) and the United States Centers for Disease Control and Prevention (CDC) do not follow the same pattern in all populations. The aim of this work is to find a machine learning method to facilitate decision making in the clinical differentiation between positive and negative influenza patients, based on their symptoms and demographic features. The research sample consisted of 15480 records, including clinical and demographic data of patients with a positive/negative RT-qPCR influenza tests, from 2010 to 2020 in the public healthcare institutions of Mexico City. The performance of the methods for classifying influenza cases were evaluated with indices like accuracy, specificity, sensitivity, precision, the f1-measure and the area under the curve (AUC). Results indicate that random forest and bagging classifiers were the best supervised methods; they showed promise in supporting clinical diagnosis, especially in places where performing molecular tests might be challenging or not feasible. [ABSTRACT FROM AUTHOR]

In modern days, for the perseverance of monitoring the vigor of a specific individual, the Wireless Body Sensor Networks have been emerging as an auspicious platform. The foremost challenge such as energy, path loss, and transmission distance that is prevalent from early days has been addressed in this article. The focal notion specified in this exploration is to discover the sensor locations on a human body that is much suitable for interconnecting the information about the intact body thus satisfying all the objectives. The focal difference between the proposed technique and the existing methods is that the projected methodology enacts multiple objectives as an alternative of distinct impartial. Further, the problem of finding the locations of sensors has been executed on an online monitoring system using MATLAB platform where the consequences are found to be improved practically for about 65% when compared with existing literature. [ABSTRACT FROM AUTHOR]

Traditional fuzzy set theory has recently demonstrated its inefficiency in handling linguistic terms directly, including the degree of neutrality in medical diagnoses. Most decision support systems in medical diagnoses are restricted since both explicit and tacit knowledge of doctors involving linguistic semantics while making decisions have not been considered in the system. Thus this paper has presented a novel approach utilizing hedge algebra and picture fuzzy sets applying for a medical decision support system. In the proposed model, picture fuzzy rule-based approach and hedge algebra using linguistic semantics are used to express rules and preferences which aims to support doctors in diagnosing patients. Experimental results in simulations for the proposed method demonstrate a high level of precision and confidence, indicating its potential utilization in medical diagnostic domain. [ABSTRACT FROM AUTHOR]

Nodule segmentation in lung computed tomography (CT) images is a significant part of the detection and diagnosis of lung cancer. Automatic analysis of lung CT images is necessary to calculate lung nodule characteristics for recognizing malignancy. In recent years, deep learning and neural networks have been used in medical applications. Deep learning utilizes neural networks to train huge amounts of information which effectively learns the nodule features in lower to higher grades for segmenting and predicting the medical images. In this paper, the proposed cat swarm optimization (CSO) based recurrent neural network (RNN) is utilized for lung nodule segmentation. The proposed model is estimated on the freely accessible lung image database consortium and image database resource initiative (LIDC-IDRI) dataset. The proposed model is segmented by using the markov random field (MRF) based firefly algorithm (FA) and cuckoo search algorithm (CSA). The result shows that the proposed CSO based RNN model delivers performance metrics like dice coefficient (DC) loss and accuracy values of about 96.28% and 90.28% respectively, which ensures accurate nodule segmentation in lung CT images. [ABSTRACT FROM AUTHOR]

In recent times, there has been considerable focus on harnessing artificial intelligence (AI) for medical image analysis and healthcare purposes. In this study, we introduce CADFU (Computer-Aided Diagnosis System for Foot Ulcers), a pioneering diabetic foot ulcer diagnosis system. The primary objective of CADFU is to detect and segment ulcers and similar chronic wounds in medical images. To achieve this, we employ two distinct algorithms. Firstly, DHuNeT, an innovative Dual-Phase Hyperactive UNet, is utilized for the segmentation task. Second, we used YOLOv8 for the task of detecting wounds. The DHuNeT autoencoder, employed for the wound segmentation task, is the paper's primary and most significant contribution. DHuNeT is the combination of sequentially stacking two UNet autoencoders. The hyperactive information transmission from the first UNet to the second UNet is the key idea of DHuNeT. The first UNet feeds the second UNet the features it has learned, and the two UNets combine their learned features to create new, more accurate, and effective features. We achieve good performance measures, especially in terms of the Dice co-efficient and precision, with segmentation scores of 85% and 92.6%, respectively. We obtain a mean average precision (mAP) of 86% in the detection task. Future hospitals could quickly monitor patients' health using the proposed CADFU system, which would be beneficial for both patients and doctors. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a neurodegenerative disease that can cause dementia and result in a severe reduction in brain function, inhibiting simple tasks, especially if no preventative care is taken. Over 1 in 9 Americans suffer from AD-induced dementia, and unpaid care for people with AD-related dementia is valued at USD 271.6 billion. Hence, various approaches have been developed for early AD diagnosis to prevent its further progression. In this paper, we first review other approaches that could be used for the early detection of AD. We then give an overview of our dataset and propose a deep convolutional neural network (CNN) architecture consisting of 7,866,819 parameters. This model comprises three different convolutional branches, each having a different length. Each branch is comprised of different kernel sizes. This model can predict whether a patient is non-demented, mild-demented, or moderately demented with a 99.05% three-class accuracy. In summary, the deep CNN model demonstrated exceptional accuracy in the early diagnosis of AD, offering a significant advancement in the field and the potential to improve patient care. [ABSTRACT FROM AUTHOR]

Correlation coefficients characterize relationships of various fuzzy sets and thus facilitate relevant applications. Regarding correlation coefficients of hesitant fuzzy sets (HFSs), a modified strategy of adjustment factor from hesitation degree is recently proposed, and the corresponding information enrichment can be probabilistically promoted to pursue correlation coefficients of probabilistic hesitant fuzzy sets (PHFSs). In this paper embracing PHFSs, a probabilistic adjustment factor is similarly constructed to modify an existing correlation coefficient, so an improved correlation coefficient is established; this new measure induces practical applications, mainly the decision making, medical diagnosis, and cluster analysis. According to PHFSs, the hesitation degree and adjustment factor are defined to achieve theoretical extensions, and the latter information factor is utilized to modify the existing correlation coefficient; thus, the new correlation coefficient emerges to offer improvements, and it acquires measure properties and example illustrations. Furthermore, the new and old correlation coefficients on PHFSs are comprehensively compared on the basis of a representative correlation coefficient on HFSs; accordingly, related correlation coefficients are applied in decision making, medical diagnosis, and cluster analysis, and our new correlation coefficient is verified to have the effectiveness and applicability. Article highlights: A modified correlation coefficient in PHFSs is proposed by fusing an adjustment factor based on hesitation degrees. The new correlation coefficient (CC) both extends an existing CC in HFSs and improves a current CC in PHFSs. The new CC is applied to decision making, medical diagnosis, cluster analysis to gain effective contrastive performance. [ABSTRACT FROM AUTHOR]

The intricate neuroinflammatory diseases multiple sclerosis (MS) and neuromyelitis optica (NMO) often present similar clinical symptoms, creating challenges in their precise detection via magnetic resonance imaging (MRI). This challenge is further compounded when detecting the active and inactive states of MS. To address this diagnostic problem, we introduce an innovative framework that incorporates state-of-the-art machine learning algorithms applied to features culled from MRI scans by pre-trained deep learning models, VGG-NET and InceptionV3. To develop and test this methodology, we utilized a robust dataset obtained from the King Abdullah University Hospital in Jordan, encompassing cases diagnosed with both MS and NMO. We benchmarked thirteen distinct machine learning algorithms and discovered that support vector machine (SVM) and K-nearest neighbor (KNN) algorithms performed superiorly in our context. Our results demonstrated KNN's exceptional performance in differentiating between MS and NMO, with precision, recall, F1-score, and accuracy values of 0.98, 0.99, 0.99, and 0.99, respectively, using leveraging features extracted from VGG16. In contrast, SVM excelled in classifying active versus inactive states of MS, achieving precision, recall, F1-score, and accuracy values of 0.99, 0.97, 0.98, and 0.98, respectively, using leveraging features extracted from VGG16 and VGG19. Our advanced methodology outshines previous studies, providing clinicians with a highly accurate, efficient tool for diagnosing these diseases. The immediate implication of our research is the potential to streamline treatment processes, thereby delivering timely, appropriate care to patients suffering from these complex diseases. [ABSTRACT FROM AUTHOR]

This paper proposes binary versions of artificial rabbits optimization (ARO) for feature selection (FS) with medical diagnosis data. ARO is a recent swarm-based optimization algorithm that mimics rabbits' natural survival tactics and eating habits. It was modeled in an optimization context to tackle optimization problems of continuous search spaces. In this paper, ARO is improved to deal with the binary domain of FS. The improvements include three additions: First, different alternatives of transfer functions were used to convert ARO from continuous to binary; second, the global-best concept was added to the binary ARO to improve the exploitation capability of the proposed algorithm; and finally, Lévy flight and opposition-based learning strategies were injected into the proposed algorithm to enhance its diversity and thus improve the balance between global exploration and local exploitation during all stages of the search process. Six binary variants of ARO were designed across an extensive set of experiments to study the impact of using the proposed amendments on the performance of the proposed ARO algorithm. These variants are: binary ARO with S-shaped transfer function (BAROS), binary ARO with V-shaped transfer function (BAROV), BAROS with the global-best concept (BGAROS), BGAROV with the global-best concept (BGAROV), BGAROS with Lévy flight and opposition-based learning strategies (BGAROSLO), and BGAROV with Lévy flight and opposition-based learning strategies (BGAROVLO). The proposed binary ARO versions were evaluated using 23 medical FS datasets. In addition, the proposed algorithm was applied to detect coronavirus disease using a real COVID-19 dataset. Five performance measures were used: classification accuracy, sensitivity, specificity, fitness value, and the number of selected features. In a nutshell, the proposed binary ARO versions were able to achieve success rates for these performance metrics as follows: 66.7%, 50%, 33.3%, 66.7%, and 83.3%, respectively. In conclusion, the success of the proposed ARO versions was realized due to the suitable design of the parameters of the proposed ARO version, such as transfer functions, global-best concept, Lévy flight, and opposition-based learning strategies. A comprehensive comparative evaluation was studied against ten well-established methods using the same datasets with a high preference for the proposed ARO versions, especially BGAROSLO which can achieve the best accuracy for the majority of the FS datasets. This is proven using Friedman's statistical test ad-hocked by Holm's test. [ABSTRACT FROM AUTHOR]

Hybrid quantum systems have shown promise in image classification by combining the strengths of both classical and quantum algorithms. These systems leverage the parallel processing power of quantum computers to perform complex computations while utilizing classical algorithms to handle the vast amounts of data involved in imaging. The hybrid approach is intended to improve accuracy and speed compared to traditional classical methods. Further research and development in this area can revolutionize the way medical images are classified and help improve patient diagnosis and treatment. The use of Conventional Neural Networks (CNN) for the classification and diagnosis of medical images using big datasets requires, in most cases, the use of special high-performance computing machines, which are very expensive and hard to access by most researchers. A new form of Machine Learning (ML), Quantum machine learning (QML), is being introduced as an emerging strategy to overcome this problem. A hybrid quantum–classical CNN uses both quantum and classical convolution layers designed to use a parameterized quantum circuit. This means that the computing model utilizes a quantum circuits approach to construct QML algorithms, which are then used to transform the quantum state to extract image hidden features. This computational acceleration is expected to achieve better algorithm performance than classical CNNs. This study intends to evaluate the performance of a Hybrid Quantum CNN (HQCNN) against a conventional CNN. This is followed by some optimizer modifications for both proposed and classical CNN methods to investigate the possible further improvement of their performance. The optimizer modification is based on forcing the optimizer to be directly adaptive to model accuracy. The optimizer adaptiveness is based on the development of an optimizer with a loss base adaptive momentum. Several algorithms are developed to achieve the above-mentioned goals, including CNN, QCNN, CNN with the adaptive optimizer, and QCNN with the Adaptive optimizer. The four algorithms are tested against a Kaggle brain dataset containing over 7000 samples. The test results show the hybrid quantum circuit algorithm outperformed the conventional CNN algorithm. The performance of both algorithms was further improved by using a fully adaptive SGD optimizer. [ABSTRACT FROM AUTHOR]

Glioma represents one of the most aggressive cancers, which can develop in the brain. The automatic tumor segmentation and its sub‐regions represent a challenging task owing to their considerable structural variation. It can appear in different ways and with several shapes, which makes tissue identification a crucial task. Reliable and accurate segmentation presents an important component in tumor treatment and diagnosis planning. To overcome these drawbacks, various Deep Learning (DL) schemes are proposed to aid doctors. In this paper, a novel Convolutional Neural Network (CNN) scheme for glioma segmentation was proposed. Our suggested technique consists of three phases. First, we use intensity normalization to ameliorate the image quality as a preprocessing step. Second, an automatic segmentation technique based on CNN has been proposed. The new model has several layers. Finally, and with the goal of refining the segmentation results, we employ a post‐processing approach. We use the public benchmark BraTS datasets from 2018 and 2020 with low‐grade and high‐grade glioma tumors to test the suggested framework. These datasets contain about 285 and 369 patients, respectively. The four modalities are exploited. Each patient has about 155 2D images from every modality. All the images have the same size (240 × 240 pixels). Our technique performs well compared to new methods, with Dice scores of 0.88 for the Whole Tumor, 0.84 for Tumor Core, and 0.71 for Enhancing Tumor based on the first dataset. According to the second dataset, the three regions had an average of 0.88, 0.9, and 0.75, respectively. The Jaccard indexes for the first data set are 0.8, 0.73, and 0.56 for the three regions, respectively. The second data set attains 0.8, 0.82, and 0.6 for the three regions. The results show that the suggested framework is an excellent way to segment data, especially compared to other methods. [ABSTRACT FROM AUTHOR]

The Molodtsov-initiated soft set theory plays an important role as a powerful mathematical tool for handling uncertainty. As an extension of the soft set, the fuzzy soft set can be seen to be more generic and flexible than utilizing the soft set only that fails to represent problem parameters fuzziness. Through this progress, the fuzzy soft set theory cannot deal with decision-making problems involving multi-attribute sets, bipolarity, or some effective considered parameters. Therefore, the goal of this article is to adapt effectiveness and bipolarity concepts with the multi-fuzzy soft set of order n. One can see that this approach generates a novel, extended, effective decision-making environment that is more applicable than any previously introduced one. In addition, types, concepts, and operations of effective bipolar-valued multi-fuzzy soft sets of dimension n are provided, each with an example. Furthermore, properties like absorption, associative, distributive, commutative, and De Morgan's laws of those new sets are investigated. Moreover, a decision-making methodology under effective bipolar-valued multi-fuzzy soft settings is established. This technique facilitates reaching the final decision that this student is qualified to take a certain education level, or this patient is suffering from a certain disease, etc. In addition, a case study represented in a medical diagnosis example is discussed in detail to make the proposed algorithm clearer. Applying matrix techniques in this example as well as using MATLAB®, not only makes it easier and faster in doing calculations, but also gives more accurate, optimal, and effective decisions. Finally, the sensitivity analysis, as well as a comparison with the existing methods, are conducted in detail and are summarized in a chart to show the difference between them and the current one. [ABSTRACT FROM AUTHOR]

In medical applications, effective medical diagnosis is developed by combining medical images from various morphologies using medical image fusion techniques. An accurate diagnosis cannot be made from a single modality image, and the existing approaches need better efficiency due to poor image quality and inconsistent performance. To solve this problem, this research proposes an effective artificial intelligence model based on multi-modal medical image fusion. This research develops a new method based on medical images using deep residual neural networks (ResNet-50) and a DarkNet-19. The optimised discrete wavelet transform (ODWT) is used for image decomposing. The original image's high- and low-frequency coefficients are decomposed by using ODWT. The low-frequency coefficient is then fused using the Modified ResNet-50 model. After that, DarkNet-19 fuses the high-frequency coefficients, and the input stimulus for DarkNet-19 is a high-frequency coefficient's modified average gradient. The inverse ODWT is employed to reconstruct the fused image finally. The proposed fusion model's effectiveness is assessed using the various CT-MRI, CT-PET, and MRI-SPECT imaging datasets. The proposed medical image fusion approach attains a maximum performance for PSNR of 40.03 dB, Fusion Factor of 6.1025, Fusion Symmetry of 0.0869, and Visual Information Fidelity of 0.121. [ABSTRACT FROM AUTHOR]

Abstract Background The concept of Pythagorean fuzzy sets (PFSs) is an utmost valuable mathematical framework, which handles the ambiguity generally arising in decision-making problems. Three parameters, namely membership degree, non-membership degree, and indeterminate (hesitancy) degree, characterize a PFS, where the sum of the square of each of the parameters equals one. PFSs have the unique ability to handle indeterminate or inconsistent information at ease, and which demonstrates its wider scope of applicability over intuitionistic fuzzy sets. Results In the present article, we opt to define two nonlinear distances, namely generalized chordal distance and non-Archimedean chordal distance for PFSs. Most of the established measures possess linearity, and we cannot incorporate them to approximate the nonlinear nature of information as it might lead to counter-intuitive results. Moreover, the concept of non-Archimedean normed space theory plays a significant role in numerous research domains. The proficiency of our proposed measures to overcome the impediments of the existing measures is demonstrated utilizing twelve different sets of fuzzy numbers, supported by a diligent comparative analysis. Numerical examples of pattern recognition and medical diagnosis have been considered where we depict the validity and applicability of our newly constructed distances. In addition, we also demonstrate a problem of suitable medicine selection for COVID-19 so that the transmission rate of the prevailing viral pandemic could be minimized and more lives could be saved. Conclusions Although the issues concerning the COVID-19 pandemic are very much challenging, yet it is the current need of the hour to save the human race. Furthermore, the justifiable structure of our proposed distances and also their feasible nature suggest that their applications are not only limited to some specific research domains, but decision-makers from other spheres as well shall hugely benefit from them and possibly come up with some further extensions of the ideas.

Nanostructured metal oxides (NMOs) provide electrical properties such as high surface-to-volume ratio, reaction activity, and good adsorption strength. Furthermore, they serve as a conductive substrate for the immobilization of biomolecules, exhibiting notable biological activity. Capitalizing on these characteristics, they find utility in the development of various electrochemical biosensing devices, elevating the sensitivity and selectivity of such diagnostic platforms. In this review, different types of NMOs, including zinc oxide (ZnO), titanium dioxide (TiO2), iron (II, III) oxide (Fe3O4), nickel oxide (NiO), and copper oxide (CuO); their synthesis methods; and how they can be integrated into biosensors used for medical diagnosis are examined. It also includes a detailed table for the last 10 years covering the morphologies, analysis techniques, analytes, and analytical performances of electrochemical biosensors developed for medical diagnosis.

Gene Selection (GS) is a strategy method targeted at reducing redundancy, limited expressiveness, and low informativeness in gene expression datasets obtained by DNA Microarray technology. These datasets contain a plethora of diverse and high-dimensional samples and genes, with a significant discrepancy in the number of samples and genes present. The complexities of GS are especially noticeable in the context of microarray expression data analysis, owing to the inherent data imbalance. The main goal of this study is to offer a simplified and computationally effective approach to dealing with the conundrum of attribute selection in microarray gene expression data. We use the Black Widow Optimization algorithm (BWO) in the context of GS to achieve this, using two unique methodologies: the unaltered BWO variation and the hybridized BWO variant combined with the Iterated Greedy algorithm (BWO-IG). By improving the local search capabilities of BWO, this hybridization attempts to promote more efficient gene selection. A series of tests was carried out using nine benchmark datasets that were obtained from the gene expression data repository in the pursuit of empirical validation. The results of these tests conclusively show that the BWO-IG technique performs better than the traditional BWO algorithm. Notably, the hybridized BWO-IG technique excels in the efficiency of local searches, making it easier to identify relevant genes and producing findings with higher levels of reliability in terms of accuracy and the degree of gene pruning. Additionally, a comparison analysis is done against five modern wrapper Feature Selection (FS) methodologies, namely BIMFOHHO, BMFO, BHHO, BCS, and BBA, in order to put the suggested BWO-IG method's effectiveness into context. The comparison that follows highlights BWO-IG's obvious superiority in reducing the number of selected genes while also obtaining remarkably high classification accuracy. The key findings were an average classification accuracy of 94.426, average fitness values of 0.061, and an average number of selected genes of 2933.767.

Healthcare prediction has been a significant factor in saving lives in recent years. In the domain of health care, there is a rapid development of intelligent systems for analyzing complicated data relationships and transforming them into real information for use in the prediction process. Consequently, artificial intelligence is rapidly transforming the healthcare industry, and thus comes the role of systems depending on machine learning and deep learning in the creation of steps that diagnose and predict diseases, whether from clinical data or based on images, that provide tremendous clinical support by simulating human perception and can even diagnose diseases that are difficult to detect by human intelligence. Predictive analytics for healthcare a critical imperative in the healthcare industry. It can significantly affect the accuracy of disease prediction, which may lead to saving patients' lives in the case of accurate and timely prediction; on the contrary, in the case of an incorrect prediction, it may endanger patients' lives. Therefore, diseases must be accurately predicted and estimated. Hence, reliable and efficient methods for healthcare predictive analysis are essential. Therefore, this paper aims to present a comprehensive survey of existing machine learning and deep learning approaches utilized in healthcare prediction and identify the inherent obstacles to applying these approaches in the healthcare domain. [ABSTRACT FROM AUTHOR]

Bipolar complex fuzzy soft sets, one of the substantial notions, generalize the notions of bipolar complex fuzzy sets and soft sets. The notion of bipolar complex fuzzy soft sets is a significant tool to cope with the awkward and complicated information involving the second dimension, i.e., unreal part, both positive and negative opinions, and the parameters. Further, similarity measures play an important role in various fields such as data mining, machine learning, information retrieval, and natural language processing. They are used to measure the degree of similarity or dissimilarity between two or more objects, documents, images, or any other type of data. Consequently, in this script, we diagnose trigonometric similarity measures like generalized cosine similarity measure, generalized tangent similarity measure and generalized cotangent similarity measure, and generalized hybrid trigonometric similarity measure in the environment of bipolar complex fuzzy soft sets. Furthermore, we also discuss the weighted generalized cosine similarity measure, weighted generalized tangent similarity measure, weighted generalized cotangent similarity measure, and weighted generalized hybrid trigonometric similarity measure for bipolar complex fuzzy soft sets. After that, through the diagnosed similarity measures, we analyze real-life dilemmas like pattern recognition and medical diagnosis to portray the applicability and benefits of the diagnosed similarity measures in the real world. At the end of this study, we show the superiority and supremacy of the analyzed trigonometric similarity measures by doing their analysis with certain prevailing similarity measures. [ABSTRACT FROM AUTHOR]

As an extension of the concepts of fuzzy set and intuitionistic fuzzy set, the concept of Pythagorean fuzzy set better models some real life problems. Distance, entropy, and similarity measures between Pythagorean fuzzy sets play important roles in decision making. In this paper, we give a new entropy measure for Pythagorean fuzzy sets via the Sugeno integral that uses fuzzy measures to model the interaction between criteria. Moreover, we provide a theoretical approach to construct a similarity measure based on entropies. Combining this theoretical approach with the proposed entropy, we define a distance measure that considers the interaction between criteria. Finally, using the proposed distance measure, we provide an extended Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for multi-criteria decision making and apply the proposed technique to a real life problem from the literature. Finally, a comparative analysis is conducted to compare the results of this paper with those of previous studies in the literature. [ABSTRACT FROM AUTHOR]

This study examines the developmental processes, diagnosis processes, and needs of children with specific learning disabilities based on their parents' experiences. The research was conducted with a qualitative research methodology. The study group in the research was formed by the typical sampling method. The study group comprises the parents of 12 students with specific learning disabilities educated in mainstream classrooms. The researchers developed a semi-structured interview form in the context of literature. Content analysis of the transcribed voice recordings was made. As a result, four main themes emerged "Developmental Process, Social Relations, Diagnosis Process, and Strengths and Weaknesses." The parents have difficulties in their children's self-care skills, motor development, social development, cognitive development, and language development compared to their peers in preschool. The parents noticed their children's development needs during the homework process and pointed out the low level of knowledge of the teachers in both preschool and school periods. It was stated that the children had developmental needs in all developmental areas, especially language development in the preschool period. Also, parents expressed that their children have difficulties with often drawing attention to the difficulties experienced by their children in social relations. [ABSTRACT FROM AUTHOR]

With the development of complex evidence theory in the application of multisource information fusion, classical Dempster–Shafer evidence theory has been extended to complex plane, called complex evidence theory. However, counterintuitive result may occur in the case when fusing conflicting complex evidences. To address this problem, a new multisource information fusion method is proposed by means of complex evidential distance function. This proposed method can reduce the impact of abnormal complex evidence on the fusion results to better support decision. A numerical example and an application of medical diagnosis verify the feasibility and effectiveness of the proposed fusion method. [ABSTRACT FROM AUTHOR]

Many researchers have realized the intelligent medical diagnosis of diabetic retinopathy (DR) from fundus images by using deep learning methods, including supervised contrastive learning (SupCon). However, although SupCon brings label information into the calculation of contrastive learning, it does not distinguish between augmented positives and same-label positives. As a result, we propose the concept of Angular Margin and incorporate it into SupCon to address this issue. To demonstrate the effectiveness of our strategy, we tested it on two datasets for the detection and grading of DR. To align with previous work, Accuracy, Precision, Recall, F1, and AUC were selected as evaluation metrics. Moreover, we also chose alignment and uniformity to verify the effect of representation learning and UMAP (Uniform Manifold Approximation and Projection) to visualize fundus image embeddings. In summary, DR detection achieved state-of-the-art results across all metrics, with Accuracy = 98.91, Precision = 98.93, Recall = 98.90, F1 = 98.91, and AUC = 99.80. The grading also attained state-of-the-art results in terms of Accuracy and AUC, which were 85.61 and 93.97, respectively. The experimental results demonstrate that Angular Margin is an excellent intelligent medical diagnostic algorithm, performing well in both DR detection and grading tasks. [ABSTRACT FROM AUTHOR]

Ultraviolet (UV) radiation offers many exciting biomedical applications such as biosensing and cancer therapy. Photon upconversion through lanthanide (Ln)‐doped nanoparticles is an attractive approach for UV generation by excitation of near‐infrared (NIR) light, which is readily accessible and highly penetrating in tissue environments. By rationally engineering the emission property of upconversion nanoparticles (UCNPs) coupled with surface functionalization with photoactivatable molecules, various nanosystems can be constructed for biomedicine with the feature of minimal living tissue damage and remote light delivery at high spatiotemporal precisions. Such technology facilitates sensitive diagnosis and effective treatment of various diseases. This review focuses on the recent development of NIR‐to‐UV UCNPs, simultaneously highlighting emergent biomedical applications enabled by these materials. [ABSTRACT FROM AUTHOR]

Background: In the past vicennium, several artificial intelligence (AI) and machine learning (ML) models have been developed to assist in medical diagnosis, decision making, and design of treatment protocols. The number of active pathologists in Poland is low, prolonging tumor patients' diagnosis and treatment journey. Hence, applying AI and ML may aid in this process. Therefore, our study aims to investigate the knowledge of using AI and ML methods in the clinical field in pathologists in Poland. To our knowledge, no similar study has been conducted. Methods: We conducted a cross-sectional study targeting pathologists in Poland from June to July 2022. The questionnaire included self-reported information on AI or ML knowledge, experience, specialization, personal thoughts, and level of agreement with different aspects of AI and ML in medical diagnosis. Data were analyzed using IBM® SPSS® Statistics v.26, PQStat Software v.1.8.2.238, and RStudio Build 351. Results: Overall, 68 pathologists in Poland participated in our study. Their average age and years of experience were 38.92 ± 8.88 and 12.78 ± 9.48 years, respectively. Approximately 42% used AI or ML methods, which showed a significant difference in the knowledge gap between those who never used it (OR = 17.9, 95% CI = 3.57–89.79, p < 0.001). Additionally, users of AI had higher odds of reporting satisfaction with the speed of AI in the medical diagnosis process (OR = 4.66, 95% CI = 1.05–20.78, p = 0.043). Finally, significant differences (p = 0.003) were observed in determining the liability for legal issues used by AI and ML methods. Conclusion: Most pathologists in this study did not use AI or ML models, highlighting the importance of increasing awareness and educational programs regarding applying AI and ML in medical diagnosis. [ABSTRACT FROM AUTHOR]

Clérambault a posé le diagnostic de « paranoïa » concernant le roi Louis XI (1423–1483). L'objectif de cet article est de rendre compte des divers éléments qui permettent de questionner ce « diagnostic ». Après avoir fait une revue de la littérature psychiatrique au sujet du « cas » Louis XI, nous questionnerons les historiens, puis, considérant l'ensemble de ces recherches, nous mettrons en relief la « méfiance » pathologique du roi, que nous analyserons à la lumière de la psychopathologie et de l'orientation psychanalytique. Le roi Louis XI a été surnommé « l'homme le plus méfiant qui soit ». Au-delà de cette méfiance caractérisée, il semble bien également avoir manifesté des idées de persécution et des préoccupations hypocondriaques. Le diagnostic de « paranoïa » – mais, pour nous, une paranoïa non déclenchée, non délirante – semble pouvoir être retenu, eu égard notamment à la conception qu'en avait Clérambault. La discussion principale est relative à la notion de « méfiance » en psychopathologie, et à son rôle qu'elle peut jouer sur le mode d'une « défense réussie » dans la paranoïa. Compte tenu d'un certain consensus – parmi les références psychiatriques, mais aussi parmi les historiens – il est fort probable que Louis XI ait présenté une forme de paranoïa, avec idées de persécutions, tyrannie, cruauté, soif de pouvoir, préoccupations hypocondriaques, le tout en un sens « contenu » par une méfiance extrême qui semble l'avoir mis à l'abri d'un délire systématisé. Clérambault issued the diagnosis that King Louis XI (1423–1483) was paranoid. The objective of this article is to enumerate the various elements that make it possible to question this "diagnosis". After reviewing the psychiatric literature about the "case" of Louis XI, we consulted historians, and then, considering all of this research, we highlight the king's pathological sense of "distrust" which we then analyze in the light of psychopathology and psychoanalytical orientation. King Louis XI was nicknamed "the most suspicious man ever". Beyond this characterized distrust, he also seems to have manifested a persecution complex and hypochondriac concerns. As far as the diagnosis of "paranoia" is concerned, – a non-triggered, non-deviant paranoia seems to us to be appropriate, especially in view of Clérambault's conception of it. The main discussion is related to the notion of "mistrust" in psychopathology, and the role it can play as a "successful defense" in paranoia. Given that there is a certain consensus – among psychiatric references, but also among historians – it is very likely that Louis XI presented a form of paranoia, with ideas of persecution, tyranny, cruelty, thirst for power, and hypochondriac concerns, All in a sense "contained" by an extreme distrust which seems to have sheltered him from a systematized delirium. [ABSTRACT FROM AUTHOR]

A q-rung orthopair fuzzy (q-ROF) set (q-ROFS) is one of the advanced fuzzy sets capable of processing complex real-world information satisfactorily. q-ROF distance measures are used to indicate the degree of difference between the data conveyed by q-ROFSs. Though numerous distance measures have been proposed in earlier studies, they cannot meet the axioms of distance measure or exist counter-intuitive cases. This study aims to formulate a novel q-ROF distance measure based on matrix norm and a strictly increasing (or decreasing) function. Further, the originated distance measure is shown to fulfill the axiomatic requirements of the distance function. The proposed measure not only meets the axiomatic definition of distance measure but also remedies the counter-intuitive cases. Appropriate experimental configurations are developed to compare the suggested distance measure with existing measures by employing them in several examples. Following the proposed q-ROF distance measures, a new method for dealing with multi-criteria group decision-making (MCGDM) problems in the q-ROF environment is presented. To illustrate the application potentiality of the established method, a numerical example concerning renewable energy source selection is assessed with q-ROF input. Finally, sensitivity and comparative analyses are executed to verify the stability and efficacy of the provided approach. [ABSTRACT FROM AUTHOR]

In this study, we investigate a novel conception called complex interval-valued hesitant fuzzy set (CIvHFS) as the modification of some prevailing conceptions such as interval-valued complex fuzzy set (IvCFS) and interval-valued hesitant fuzzy set (IvHFS), to tickle the data or information which have intricate and haziness in the genuine life dilemmas. The CIvHFS carries the membership grade in the model of a finite subset of numerous interval values which contains in the unit disc of a complex plane. We also propound the operational laws of the investigated conception. Further, we establish certain vector similarity measures (VSMs) and weighted VSMs (WVSMs) in the setting of CIvHFS, including the Jaccard similarity measure (JSM), Dice similarity measure (DSM), and Cosine SM (CSM), etc. Along with this, we also investigate hybrid VSM and weighted hybrid VSM relying on the CIvHFS. Moreover, we present some generalized exponential and non-exponential based SMs for CIvHFS. To portray the usefulness and advantages of the developed SMs in genuine life, we employ these SMs to solve pattern recognition and medical diagnosis. Finally, to assess the dependability and rationality of the developed SMs, we compare the investigated SMs with certain prevailing SMs.

Automatic medical diagnosis has gained significant attention among researchers, particularly in disease diagnosis. Differentiating between dermatology diseases is pivotal in clinical decision-making as it provides prognostic and predictive information and treatment strategies. This paper proposes a dermatology detection system based on deep learning (DL) and object recognition. The proposed model consists of three phases: Data preprocessing, data augmentation, and classification with localization. In the data preprocessing phase, we apply various operations such as color transformation, resizing, normalization, and labeling to prepare the input image for enrollment in our DL models. The data augmentation phase is carried out on the input images using the convolutional generative adversarial network algorithm. In the third phase, YOLO-V5 is used to classify and localize objects. The dataset is carefully collected with the assistance of medical specialists to ensure its accuracy. The proposed models are evaluated and compared using various metrics. Our empirical results demonstrate that the proposed model outperforms state-of-the-art models in terms of accuracy. Our proposed methodology offers significant improvements in detecting vitiligo and melanoma compared to recent techniques.

Medical diagnosis research has recently focused on feature selection techniques due to the availability of multiple variables in medical datasets. Wrapper-based feature selection approaches have shown promise in providing faster and more cost-effective predictors. However, selecting the most relevant features from medical datasets to increase disease classification accuracy remains a challenging research issue. To address this challenge, we propose an effective wrapper-based feature selection approach called BTLBO-KNN. It combines an improved Binary Teaching-Learning Based Optimization (BTLBO) algorithm with the K-Nearest Neighbor (KNN) classifier to accelerate the convergence rate in finding the near-optimal features subset. BTLBO-KNN incorporates two new efficient binary teaching and learning processes, an abandoned learner’s replacement mechanism, and a teacher knowledge improvement method. We extensively compare BTLBO-KNN with recent state-of-the-art wrapper-based feature selection approaches on COVID-19 and 23 gene-expression and medical datasets with different dimensional complexities. Our results demonstrate the superiority of BTLBO-KNN over its alternatives in terms of minimizing the number of selected features and the classification error rate.

In recent days, due to the complexities of different diseases of similar types, it becomes very difficult to diagnose an accurate type of disease, and so medical diagnosis becomes a difficult task for the experts working in health departments. Many researchers try to develop new methods and techniques to over the difficulties that come across in the way of medical diagnosis. In this paper, we try to develop some novel techniques that will help experts to diagnose diseases accurately. Based on a more advanced structure of intuitionistic fuzzy rough sets, in this article, we establish confidence-level intuitionistic fuzzy average/geometric aggregation operators to incorporate the familiarity degree of experts with evaluated objects for an initial assessment while intuitionistic fuzzy rough average/geometric aggregation operators cannot do so. Moreover, we have given some basic properties of the initiated operators. To show the effective use of these operators we have proposed an algorithm with an illustrative example. Furthermore, based on the intuitionistic fuzzy rough model, we have also established a medical diagnosis model to incorporate the difficulty that occurs in the diagnosis of disease. Furthermore, a comparative analysis demonstrates the efficiency of our proposed methods.

Abstract Surface-enhanced Raman scattering (SERS) is a very promising tool for the direct detection of biomarkers for the diagnosis of i.e., cancer and pathogens. Yet, current SERS strategies are hampered by non-specific interactions with co-existing substances in the biological matrices and the difficulties of obtaining molecular fingerprint information from the complex vibrational spectrum. Raman signal enhancement is necessary, along with convenient surface modification and machine-based learning to address the former issues. This review aims to describe recent advances and prospects in SERS-based approaches for cancer and pathogens diagnosis. First, direct SERS strategies for key biomarker sensing, including the use of substrates such as plasmonic, semiconductor structures, and 3D order nanostructures for signal enhancement will be discussed. Secondly, we will illustrate recent advances for indirect diagnosis using active nanomaterials, Raman reporters, and specific capture elements as SERS tags. Thirdly, critical challenges for translating the potential of the SERS sensing techniques into clinical applications via machine learning and portable instrumentation will be described. The unique nature and integrated sensing capabilities of SERS provide great promise for early cancer diagnosis or fast pathogens detection, reducing sanitary costs but most importantly allowing disease prevention and decreasing mortality rates.

According to recent studies and statistics, Cervical Cancer (CC) is one of the most common causes of death worldwide, and mainly in the developing countries. CC has a mortality rate around 60%, in less developing countries and the percentages could go even higher, due to poor screening processes, lack of sensitization, and several other reasons. Therefore, this paper aims to utilize the high capabilities of machine learning techniques in the early prediction of CC. In specific, three well-known feature selection and ranking methods have been used to identify the most significant features that help in the diagnosis process. Also, eighteen different classifiers that belong to six learning strategies have been trained and extensively evaluated against a primary data which consists of five hundred images. Moreover, an investigation regarding the problem of imbalance class distribution which is common in medical dataset is conducted. The results revealed that LWNB and RandomForest classifiers showed the best performance in general, and considering four different evaluation metrics. Also, LWNB and Logistic classifiers were the best choices to handle the problem of imbalance class distribution which is common in medical diagnosis task. The final conclusion could be made is that using an ensemble model which consists of several classifiers such as LWNB, RandomForest, and Logistic is the best solution to handle this type of problems. [JJCIT 2022; 8(4.000): 357-369]

Cite this article: Bone Joint Res 2023;12(4):256–258.