No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Enhanced Approach to Predict Early Stage Chronic Kidney Disease
ResearchGate has not been able to resolve any citations for this publication.
Putting together mathematical models and deep learning has become a strong way to identify cardiovascular disease (CVD) in recent years. This paper looks at how dynamical systems, control theory, and machine learning methods can work together to make CVD forecast more accurate and reliable. To improve the ability of diagnostic tools to predict the future by using mathematical models like differential equations to describe how the heart works and deep learning architectures like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for feature extraction. This method considers both the time patterns of how the heart works and the non-linear complexity of risk factors like high blood pressure, high cholesterol, and family tendencies. The most important part of our method is creating a multi-stage prediction model. This model starts with differential equations that show how heart rate and blood pressure change over time. Next, it uses deep learning models that have been trained on large CVD datasets. Normalization and feature engineering methods are used to prepare the information. Key measures like age, BMI, and cholesterol levels are used as inputs. Metrics like precision, sensitivity, specificity, and F1-score are used to judge how well the model works. Early findings indicate that combining mathematical models with deep learning makes predictions a lot more accurate than using only standard machine learning models. In particular, adding time dynamics to the model lets it find hidden trends in physiological data that simple models often miss. Deep learning also lets the system learn on its own how different risk factors are related to each other, making it a strong tool for finding CVD early and predicting how bad it will be. The research shows that a mix of approaches could make personalized medicine better by giving doctors accurate and easy to understand prediction tools. In the future, researchers will focus on making these models work better so it can be used in real time in hospital settings. This could help lower the number of people who get cardiovascular disease around the world.
Introduction
Machine learning (ML) algorithms and statistical modeling offer a potential solution to offset the challenge of diagnosing early Alzheimer's disease (AD) by leveraging multiple data sources and combining information on neuropsychological, genetic, and biomarker indicators. Among others, statistical models are a promising tool to enhance the clinical detection of early AD. In the present study, early AD was diagnosed by taking into account characteristics related to whether or not a patient was taking specific drugs and a significant protein as a predictor of Amyloid-Beta (Aβ), tau, and ptau [AT(N)] levels among participants.
Methods
In this study, the optimization of predictive models for the diagnosis of AD pathologies was carried out using a set of baseline features. The model performance was improved by incorporating additional variables associated with patient drugs and protein biomarkers into the model. The diagnostic group consisted of five categories (cognitively normal, significant subjective memory concern, early mildly cognitively impaired, late mildly cognitively impaired, and AD), resulting in a multinomial classification challenge. In particular, we examined the relationship between AD diagnosis and the use of various drugs (calcium and vitamin D supplements, blood-thinning drugs, cholesterol-lowering drugs, and cognitive drugs). We propose a hybrid-clinical model that runs multiple ML models in parallel and then takes the majority's votes, enhancing the accuracy. We also assessed the significance of three cerebrospinal fluid biomarkers, Aβ, tau, and ptau in the diagnosis of AD. We proposed that a hybrid-clinical model be used to simulate the MRI-based data, with five diagnostic groups of individuals, with further refinement that includes preclinical characteristics of the disorder. The proposed design builds a Meta-Model for four different sets of criteria. The set criteria are as follows: to diagnose from baseline features, baseline and drug features, baseline and protein features, and baseline, drug and protein features.
Results
We were able to attain a maximum accuracy of 97.60% for baseline and protein data. We observed that the constructed model functioned effectively when all five drugs were included and when any single drug was used to diagnose the response variable. Interestingly, the constructed Meta-Model worked well when all three protein biomarkers were included, as well as when a single protein biomarker was utilized to diagnose the response variable.
Discussion
It is noteworthy that we aimed to construct a pipeline design that incorporates comprehensive methodologies to detect Alzheimer's over wide-ranging input values and variables in the current study. Thus, the model that we developed could be used by clinicians and medical experts to advance Alzheimer's diagnosis and as a starting point for future research into AD and other neurodegenerative syndromes.
The Internet of Medical Things (IoMT) has become a pivotal aspect of IoT applications, playing a crucial role in cutting down healthcare expenses, enhancing access to clinical services, and refining operational efficiency within the healthcare domain. An early detection of neurological brain disorders continues to present a formidable challenge. In response, our research endeavors are directed towards the IoMT-based system used for the real-time diagnosis of neurological disorders. In this paper, IoMT-based real-time diagnosis model is developed for neurological brain disorders using systematic deep learning and electroencephalogram (EEG) signal (RT-NeuroDDSM). We first introduce the time domain, channel and spatial attention network (TCSNet) for feature extraction which extracts the high-level time series, channel and spatial features, respectively. TCSNet aims to learn more valuable features from the input data to achieve good classification results. Furthermore, in order to maximize features, we create the modified normative fish swarm (MNFS) feature selection algorithm. Next, the detection of various neurological brain problems, including neuro-typical, epilepsy, and autism spectrum disorder (ASD), is accomplished by applying the hinging hyperplane neural network (HHNN). To verify the performance, we used the publicly accessible EEG datasets from University of Bonn-Germany, CHB-MIT EEG repository, and King Abdul-Aziz University. The RT-NeuroDDSM has an overall classification accuracy of 99.956%, making it 5.471% more in efficiency compared to the existing state-of-the-art model.
Brain tumors occur due to the expansion of abnormal cell tissues and can be malignant (cancerous) or benign (not cancerous). Numerous factors such as the position, size, and progression rate are considered while detecting and diagnosing brain tumors. Detecting brain tumors in their initial phases is vital for diagnosis where MRI (magnetic resonance imaging) scans play an important role. Over the years, deep learning models have been extensively used for medical image processing. The current study primarily investigates the novel Fine-Tuned Vision Transformer models (FTVTs)—FTVT-b16, FTVT-b32, FTVT-l16, FTVT-l32—for brain tumor classification, while also comparing them with other established deep learning models such as ResNet50, MobileNet-V2, and EfficientNet - B0. A dataset with 7,023 images (MRI scans) categorized into four different classes, namely, glioma, meningioma, pituitary, and no tumor are used for classification. Further, the study presents a comparative analysis of these models including their accuracies and other evaluation metrics including recall, precision, and F1-score across each class. The deep learning models ResNet-50, EfficientNet-B0, and MobileNet-V2 obtained an accuracy of 96.5%, 95.1%, and 94.9%, respectively. Among all the FTVT models, FTVT-l16 model achieved a remarkable accuracy of 98.70% whereas other FTVT models FTVT-b16, FTVT-b32, and FTVT-132 achieved an accuracy of 98.09%, 96.87%, 98.62%, respectively, hence proving the efficacy and robustness of FTVT’s in medical image processing.
Hyperspectral imagery, capturing information beyond the visible spectrum, is essential for many remote sensing applications. This paper introduces a novel approach utilizing a 3D Convolutional Neural Network (CNN) enhanced with self-attention mechanism to address the limitations of traditional architectures in hyperspectral image classification. The main problem tackled is the effective extraction of both spatial and spectral features from complex hyperspectral datasets. Our proposed model simultaneously analyzes spatial and spectral dimensions with improved accuracy and adaptability through self-attention. We systematically evaluate the performance of 1D CNN, 2D CNN, and 3D CNN models, alongside Multi-Column Neural Network (MCNN) and Hybrid Spectral Network (Hybrid SN) models, comparing them to our proposed approach. The evaluation, conducted on the Indian Pines and Salinas datasets, highlights significant improvements in classification accuracy and adaptability. Specifically, the proposed 3D CNN with self-attention achieves accuracy values of 98.45% and 91.32% on the Indian Pines and Salinas datasets, respectively. This paper provides critical insights for data scientists and remote sensing experts, contributing to informed decision-making in selecting CNN models tailored to specific application requirements and advancing the field of hyperspectral image classification (HSIC). Furthermore, our approach shows improved handling of the complex spectral variability and spatial heterogeneity inherent in hyperspectral data.
Skin disorders encompass a wide range of conditions that affect the skin, a vital organ of the human body. Early detection of skin diseases is difficult due to a lack of awareness, subtle symptoms, similarities, inter-individual heterogeneity in symptoms, limited access to dermatologists, and difficulties in imaging techniques. In this article, we propose a clinical decision support model for detection and classification of skin diseases (DermCDSM) through productive improvement of division capabilities and a cross-breed profound learning procedure. The division cycle is expected to be further developed using an improved chameleon swarm optimization (ICSO) method that takes into account a more accurate and proficient identification of the main cause of the disease. By employing the ICSO algorithm, we aim to enhance the overall accuracy and reliability of disease detection methods. Multi-strategy seeking optimization (MSSO), which is used to optimize feature selection by identifying the most significant features for the task at hand, has been introduced to handle the tests connected to data dimensionality. Convolutional deep spiking neural networks (CD-SNN), a deep learning method, have been implemented to improve the precision of skin cancer diagnosis and multi-class classification. The benchmark ISIC 2017 dataset is utilized to validate the efficacy of our proposed framework, DermCDSM, and its superiority over existing approaches in terms of accuracy, dependability, and efficiency is demonstrated.
Rapid diagnosis to test diseases, such as COVID-19, is a significant issue. It is a routine virus test in a reverse transcriptase-polymerase chain reaction. However, a test like this takes longer to complete because it follows the serial testing method, and there is a high chance of a false-negative ratio (FNR). Moreover, there arises a deficiency of R.T.–PCR test kits. Therefore, alternative procedures for a quick and accurate diagnosis of patients are urgently needed to deal with these pandemics. The infrared image is self-sufficient for detecting these diseases by measuring the temperature at the initial stage. C.T. scans and other pathological tests are valuable aspects of evaluating a patient with a suspected pandemic infection. However, a patient's radiological findings may not be identified initially. Therefore, we have included an Artificial Intelligence (A.I.) algorithm-based Machine Intelligence (MI) system in this proposal to combine C.T. scan findings with all other tests, symptoms, and history to quickly diagnose a patient with a positive symptom of current and future pandemic diseases. Initially, the system will collect information by an infrared camera of the patient's facial regions to measure temperature, keep it as a record, and complete further actions. We divided the face into eight classes and twelve regions for temperature measurement. A database named patient-info-mask is maintained. While collecting sample data, we incorporate a wireless network using a cloudlets server to make processing more accessible with minimal infrastructure. The system will use deep learning approaches. We propose convolution neural networks (CNN) to cross-verify the collected data. For better results, we incorporated tenfold cross-verification into the synthesis method. As a result, our new way of estimating became more accurate and efficient. We achieved 3.29% greater accuracy by incorporating the "decision tree level synthesis method" and "ten-folded-validation method". It proves the robustness of our proposed method.
Image synthesis based on natural language description has become a research hotspot in edge computing in artificial intelligence. With the help of generative adversarial edge computing networks, the field has made great strides in high-resolution image synthesis. However, there are still some defects in the authenticity of synthetic single-target images. For example, there will be abnormal situations such as “multiple heads” and “multiple mouths” when synthesizing bird graphics. Aiming at such problems, a text generation single-target model SA-AttnGAN based on a self-attention mechanism is proposed. SA-AttnGAN (Attentional Generative Adversarial Network) refines text features into word features and sentence features to improve the semantic alignment of text and images; in the initialization stage of AttnGAN, the self-attention mechanism is used to improve the stability of the text-generated image model; the multistage GAN network is used to superimpose, finally synthesizing high-resolution images. Experimental data show that SA-AttnGAN outperforms other comparable models in terms of Inception Score and Frechet Inception Distance; synthetic image analysis shows that this model can learn background and colour information and correctly capture bird heads and mouths. The structural information of other components is improved, and the AttnGAN model generates incorrect images such as “multiple heads” and “multiple mouths.” Furthermore, SA-AttnGAN is successfully applied to description-based clothing image synthesis with good generalization ability.
The quantity of scientific images associated with patient care has increased markedly in recent years due to the rapid development of hospitals and research facilities. Every hospital generates more medical photographs, resulting in more than 10 GB of data per day being produced by a single image appliance. Software is used extensively to scan and locate diagnostic photographs to identify patient's precise information, which can be valuable for medical science research and advancement. An image recovery system is used to meet this need. This paper suggests an optimized classifier framework focused on a hybrid adaptive neuro-fuzzy approach to accomplish this goal. In the user query, similarity measurement, and the image content, fuzzy sets represent the vagueness that occurs in such data sets. The optimized classifying method 'hybrid adaptive neuro-fuzzy is enhanced with the improved cuckoo search optimization. Score values are determined by utilizing the linear discriminant analysis (LDA) of such classified images. The preliminary findings indicate that the proposed approach can be more reliable and effective at estimation than can existing approaches.
Early detection of vessels from fundus images can effectively prevent the permanent retinal damages caused by retinopathies such as glaucoma, hyperextension, and diabetes. Concerning the red color of both retinal vessels and background and the vessel's morphological variations, the current vessel detection methodologies fail to segment thin vessels and discriminate them in the regions where permanent retinopathies mainly occur. This research aims to suggest a novel approach to take the benefit of both traditional template-matching methods with recent deep learning (DL) solutions. These two methods are combined in which the response of a Cauchy matched filter is used to replace the noisy red channel of the fundus images. Consequently, a U-shaped fully connected convolutional neural network (U-net) is employed to train end-to-end segmentation of pixels into vessel and background classes. Each preprocessed image is divided into several patches to provide enough training images and speed up the training per each instance. The DRIVE public database has been analyzed to test the proposed method, and metrics such as Accuracy, Precision, Sensitivity and Specificity have been measured for evaluation. The evaluation indicates that the average extraction accuracy of the proposed model is 0.9640 on the employed dataset.
Electroencephalography (EEG) signals are non-stationary and mixed with artefacts. A clinical finding through observation is relatively difficult and may lead to misinterpretations. In particular, epilepsy is the brain neural disorder which is hard to be diagnosed by visual observation of EEG signals. In an attempt to avoid such key issues, automated detection of epilepsy is proposed by analyzing EEG signals in a systematic way to support the clinical decision making process. Initially the EEG signal data is preprocessed by removing signal noise and artefacts by adopting selective threshold denoising method of Discrete Wavelet Transform (DWT). Distinct statistical features are mined from each signal sub bands through multiscale approximation. The dimensionality of the signal features are reduced by using kernel based robustified Principal Component Analysis (PCA). A two-class Support Vector Machine (SVM) nonlinear classifier is used for classifying the ictal and interictal EEG signals with its two variants namely Polynomial Kernel and Radial Basis Function kernel. The performance of the various classification experiments are determined by computing of sensitivity (SEN) and specificity (SPE) and accuracy (ACC). The 5-fold cross validation is exercised to assess the performance of the classifier. Classification accuracy of 99.6% is obtained with the proposed model and outperforms similar benchmarking classification works reported recently.
Nowadays, medical data classification plays an important role in healthcare informatics applications such as disease prediction, classification, etc. The recently developed machine learning and deep learning models are commonly employed for effective medical data classification, which can be applied for disease diagnosis. The existing techniques make few shortcomings in terms of computational complexity, higher-dimensional features, higher execution time, etc. To tackle these issues, this paper develops a new classification model with metaheuristic algorithm based optimal feature selection for Chronic Kidney Disease diagnosis. Initially, the data with missing values were evacuated in the pre-processing stage. Then, the best subset of features selected by a metaheuristic algorithm named Oppositional based FireFly Optimization algorithm, which helps in the prediction or classification of the disease more accurately. The incorporation of oppositional based learning concept helps to improve the convergence rate of FireFly algorithm. For classification, Deep Neural Network was proposed to diagnose the existence of CKD. The effectiveness of the proposed feature selection-based classifier was tested on the dataset as measures of sensitivity, specificity, and accuracy. The results concluded that the proposed algorithm achieved a high accuracy rate when compared to the algorithms of existing classifier models.
Data mining for healthcare is an interdisciplinary field of study that originated in database statistics and is useful in examining the effectiveness of medical therapies. Machine learning and data visualization Diabetes-related heart disease is a kind of heart disease that affects diabetics. Diabetes is a chronic condition that occurs when the pancreas fails to produce enough insulin or when the body fails to properly use the insulin that is produced. Heart disease, often known as cardiovascular disease, refers to a set of conditions that affect the heart or blood vessels. Despite the fact that various data mining classification algorithms exist for predicting heart disease, there is inadequate data for predicting heart disease in a diabetic individual. Because the decision tree model consistently beat the naive Bayes and support vector machine models, we fine-tuned it for best performance in forecasting the likelihood of heart disease in diabetes individuals.
Chronic Kidney disease (CKD) is a progressive disease affecting more than twenty million individuals in the United States. Disease progression is often characterized by complications such as cardiovascular diseases, anemia, hyperlipidemia and metabolic bone diseases etc., Based on estimated GFR values, the disease is categorized in 5 stages which significantly influence patient outcome. Cardiovascular ultrasound (US) (echocardiography) imagery demonstrate significant hemodynamic alterations that are secondary to CKD in the form of volume/ pressure overload. As the CKD pathology directly impacts cardiovascular disease, the US imaging shows structural and hemodynamic adaptation. Hence, the development of a computer-aided diagnosis (CAD) model to predict CKD would be desirable, and can potentially improve treatment. Several prior studies have utilized kidney features for quantitative analysis. In this paper, acquisition of the four-chamber heart US image is employed to predict CKD stage. The method combines image and feature fusion techniques under a graph embedding framework to characterize heart chamber properties. Moreover, a support vector machine is incorporated to classify heart US images. The proposed method achieved 100 % accuracy for a two-class system, and 99.09 % accuracy for a multi-class categorization scenario. Hence, our proposed CAD tool is deployable in both clinic and hospital settings for computer-aided screening of CKD.
Objectives
In this paper, we propose a computationally efficient Correlational Neural Network (CorrNN) learning model and an automated diagnosis system for detecting Chronic Kidney Disease (CKD). A Support Vector Machine (SVM) classifier is integrated with the CorrNN model for improving the prediction accuracy.
Material and methods
The proposed hybrid model is trained and tested with a novel sensing module. We have monitored the concentration of urea in the saliva sample to detect the disease. Experiments are carried out to test the model with real-time samples and to compare its performance with conventional Convolutional Neural Network (CNN) and other traditional data classification methods.
Results
The proposed method outperforms the conventional methods in terms of computational speed and prediction accuracy. The CorrNN-SVM combined network achieved a prediction accuracy of 98.67%. The experimental evaluations show a reduction in overall computation time of about 9.85% compared to the conventional CNN algorithm.
Conclusion
The use of the SVM classifier has improved the capability of the network to make predictions more accurately. The proposed framework substantially advances the current methodology, and it provides more precise results compared to other data classification methods.
In recent times, Chronic Kidney Disease (CKD) has affected more than 10% of the population worldwide and millions of people die every year. So, early-stage detection of CKD could be beneficial for increasing the life expectancy of suffering patients and reducing the treatment cost. It is required to build such a multimedia driven model which can help to diagnose the disease efficiently with higher accuracy before leading to worse conditions. Various techniques related to conventional machine learning models have been used by researchers in the past time without involvement of multimodal data-driven learning. This research paper offers a novel deep learning framework for chronic kidney disease classification using stacked autoencoder model utilizing multimedia data with a softmax classifier. The stacked autoencoder helps to extract the useful features from the dataset and then a softmax classifier is used to predict the final class. It has experimented on UCI dataset which contains early stages of 400 CKD patients with 25 attributes, which is a binary classification problem. Precision, recall, specificity and F1-score were used as evaluation metrics for the assessment of the proposed network. It was observed that this multimodal model outperformed the other conventional classifiers used for chronic kidney disease with a classification accuracy of 100%.
Electronic Health Records (EHRs) have changed the way healthcare is provided by recording patient information, making it easier to handle data, and letting healthcare workers talk to each other without any problems. But EHRs haven't completely come to their full guarantee however when it comes to making strides quiet care and making proficient choices superior. This theoretical talks almost a other way to make strides EHR frameworks by utilizing progressed information integration and machine learning methods. The objective is to create clinical choice back way better and, within the conclusion, make understanding comes about way better. The recommended approach makes the foremost of the colossal sum of information in electronic wellbeing records (EHRs) by combining distinctive sorts of information, such as organized clinical information, unorganized composed notes, restorative images, genetic information, and real-time real signs. Diverse information sources are brought together utilizing progressed information integration strategies to form a full understanding profile that appears the patient's wellbeing state and therapeutic foundation as a entirety. This bound together data environment is the premise for building progressed machine learning models that can draw valuable conclusions, figure how patients will do, and recommend the most excellent care for each individual. Machine learning methods are exceptionally vital for getting valuable data from EHR information. These calculations can discover mystery associations and complex designs by utilizing strategies like profound learning, normal dialect preparing, and expectation modeling. They can also accurately predict clinical events. These models are always learning and getting better, so they can change to new patient data and clinical situations.
Healthcare information systems are going through a huge change that will make them more efficient, safe, and easy to use. As more persistent records are digitized and private therapeutic information is shared, it is more critical than ever to create beyond any doubt that security, security, and availability are well secured. Blockchain innovation can be a great way to bargain with these issues since it makes a decentralized, unchangeable record that can be utilized to securely store and send healthcare information whereas securing its security and security. This exposition looks at how blockchain innovation might offer assistance make wellbeing data frameworks more secure and more congruous with each other. Healthcare companies can set up a trusted and unchangeable way to oversee understanding information over different frameworks and parties by utilizing blockchain independent plan, cryptography, and voting instruments. One of the leading things approximately blockchain innovation is that it can make data more private. Cryptographic instruments, like encryption and computerized marks, make it conceivable to store and share private wellbeing information securely with individuals who are permitted to see it, without compromising persistent security. Moreover, since blockchain is unchangeable, once information is recorded, it can't be changed or eradicated. This makes the history of who gotten to and changed information clear and simple to check. In conjunction with ensuring protection, blockchain innovation moreover makes things more secure by bringing down the chances of information spills and unlawful get to. Blockchain-based wellbeing data frameworks make information keeping less centralized and use solid encryption strategies to lower the chances of single focuses of failure and unlawful changes. This makes information more secure and dependable. Keen contracts on blockchain stages can too mechanize and execute get to control rules, making beyond any doubt that as it were individuals who are permitted to can see certain restorative data or do certain activities that have as of now been set up. Interoperability is another important part of modern healthcare information systems that lets different healthcare companies and systems work together and share data easily.
The prevalence of chronic kidney diseases has raised the demand for kidney replacement therapy over recent years. Although kidney transplantation provides better life quality than other alternatives, the replacement might face rejection and endanger individuals’ lives. Therefore, predicting this rejection is of great importance, and due to the complexity of the human body's immune system, it is a complicated task. Machine learning has been widely used in disease diagnoses such as graft rejection. One of the common issues in disease diagnosis is the class imbalance problem. The predictive model is likely to misclassify all of the minority class samples in such cases. This paper proposes a method that can accurately predict kidney rejection in an imbalanced dataset. We have adopted kidney transplantation data from 378 patients collected from 1994 to 2011. Our main contribution is to develop a novel clustering method using Red Deer Algorithm (RDA), which is later utilized in proposing a three-stage clustering-based undersampling approach to handle the class imbalance problem so that the final predictive models can classify the given data more accurately. The undersampling method includes denoising, RDA clustering, and sample selection. Moreover, the proposed clustering method is also used to reduce the data dimensionality. Subsequently, five different classification algorithms such as Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Decision Tree (DT), and an ensemble method are used to predict kidney graft rejection. Then, these classifiers are compared in terms of five performance evaluation metrics: accuracy, sensitivity, specificity, F1 score, and area under the Receiver Operating Characteristic (ROC) curve (AUC). The obtained results indicate that the decision tree model outperformed other algorithms and achieved 0.96, 0.94, 0.97, 0.95, and 0.95 for accuracy, sensitivity, specificity, F1 score, and AUC, respectively. Hence, it is highly recommended to use the proposed method as a decision support system for clinical experts to predict kidney transplantation failure.
The prevalence of chronic disease comorbidity and multimorbidity is a significant health issue worldwide. In many cases, for individuals, the occurrence of one chronic disease leads to the development of one or more other chronic conditions. This exerts a significant burden on healthcare systems globally. Disease comorbidity is defined as the simultaneous occurrence of more than one disease. And a person having more than two comorbidities is referred to as multimorbid. This study followed a machine learning and network analytics-based approach to predict major chronic disease comorbidity and multimorbidity. In doing so, this study first extracted patient networks from the research dataset. In such networks, nodes represent patients and edges between two nodes indicate that the underlying two patients had at least one common disease. This study also considered other relevant features from patients’ health trajectories. Out of the five machine learning models considered in this study (Logistic regression, k-nearest neighbours, Naïve Bayes, Random Forest and Extreme Gradient Boosting) and two deep learning models (Multilayer perceptrons and Convolutional neural networks), Extreme Gradient Boosting showed the highest accuracy (95.05%), followed by the Convolutional neural networks (91.67%). The attribute of the number of episodes from the patient trajectory had been found as the most important feature, followed by the patient network attribute of transitivity. Other relevant results (feature correlation, variable clustering, confusion matrix and kernel density estimation) were also reported and discussed. The findings and insights of this study can help healthcare stakeholders and policymakers mitigate the negative impact of disease comorbidity and multimorbidity.
Contrast-enhanced magnetic resonance imaging (CE-MRI) is one of the methods routinely used in clinics for the diagnosis of renal impairments. It allows assessment of kidney perfusion and also visualization of various lesions and tissue atrophy due to e.g. renal artery stenosis (RAS). An important indicator of the renal tissue state is the volume and shape of the kidney. Therefore it is highly desirable to equip radiological units in clinics with the software capable of automatic segmentation of the kidneys in CE-MRI images. This paper proposes a solution to this task using an original architecture of a deep neural network. The proposed design employs a three-branch convolutional neural network specialized in 1) detection of renal parenchyma within an MR image patch, 2) segmentation of the whole kidney and 3) annotation of the renal cortex. We tested our architecture for normal kidneys in healthy subjects and for poorly perfused organs in RAS patients. The accuracy of renal parenchyma segmentation was equal to 0.94 in terms of the intersection over union (IoU) ratio. Accuracy of the cortex segmentation depends on the level of tissue health condition and ranges from 0.76 up to 0.92 of IoU.
Chronic Kidney Disease (CKD) is a serious health issue that is growing at an alarming rate. A person having CKD can only be saved by providing kidney transplantation or dialysis but as it involves huge medical expenditure it remains unaffordable to low and middle-income countries. Therefore, early-stage diagnosis is critical to contain CKD at the initial stage, which can reduce the mortality rate and bring down the cost of treatment significantly. This study proposes a novel feature selection method namely Majority Vote-Grey Wolf Optimization (MV-GWO) with machine learning algorithms for the detection of CKD using benchmark CKD dataset. For validating the proposed method we have used different evaluation metrics. The proposed method achieved higher accuracy of 98.75%, sensitivity of 100%, F1-score of 99% and Mathew Correlation Coefficient of 0.9735 with only five optimal features. Furthermore, we have interpreted the machine learning model by analyzing the most critical features using SHapley Additive exPlanations (SHAP) feature importance plot, summary plot, dependence plot, and Partial dependence plots.
Background and Purpose
The precise kidney segmentation is very helpful for diagnosis and treatment planning in urology, by giving information about malformation in the shape and size of the kidney. Kidney segmentation in abdominal computed tomography (CT) images provides support for the efficient and effortless detection of kidney tumors or cancers. Manual kidney segmentation is time-consuming and not reproducible. To overcome this problem, computer-aided automatic approach is used for kidney segmentation. The purpose of presenting this review paper is to analyze different automatic kidney segmentation methods in abdominal CT scans.
Materials and Methods
PRISMA guidelines were used to conduct the systematic review. To acquire related articles, three online open source databases were used and a query was formed with relevant keywords. On the basis of inclusion and exclusion criteria, relevant papers were selected from the search results for finding answers to the four evolved research questions.
Results
The results reported in the different studies were analyzed based on the formulated research questions. The challenges of these studies were listed to overcome in the future. Many performance parameters representing the results like Hausdorff Distance (HD) and Dice Similarity Coefficient (DSC) were compared among the relevant studies.
Conclusion
The systematic review article consists of the essence of the several computer-aided kidney segmentation methods using abdominal CT images, which are dedicated to answering the evolved research questions like various methods, accuracy, datasets size, various challenges, and the effect of pathological kidney on the performance of segmentation method had been discussed.
The prevalence of chronic kidney disease of unknown etiology (CKDu) is receiving considerable attention due to the serious threat to human health throughout the world. However, the roles of geo-socio-environmental factors in the prevalence of the CKDu endemic areas are still unknown. Sri Lanka is one of the countries most seriously affected by CKDu, where 10 out of 25 districts have been identified as the areas with the high prevalence of CKDu (10–20%). This review summarizes the geographical distribution of CKDu and its probable geochemical, behavioral, sociological, and environmental risk factors based on research related to hydrogeochemical influences on CKDu in Sri Lanka. More than 98% of CKDu patients have consumed groundwater as their primary water source in daily life, indicating the interactions of geogenic contaminants (such as F−, total dissolved solids, Hofmeister ions) in groundwater is responsible for the disease. Apart from the hydrogeochemical factors, mycotoxins, cyanotoxins, use of some herbal medicines, dehydration, and exposure to agrochemicals were alleged as risk factors. Sociological factors, including poverty, living habits and anthropogenic activities, may also provoke the emergence of CKDu. Therefore, the interaction of geo-socio environmental risk factors should be sociologically and scientifically considered to prevent the prevalence of CKDu. Future in-depth studies are required to reveal the individual role of each of the postulated etiological factors, possibly using machine learning and advanced statistics.
In the field of medicine, decision-making has traditionally been carried out based on the best available scientific information and the experience of specialists using data found in analog formats such as radiographies, medical reports, and handwritten notes, among others. In this sense, the Big Data phenomenon is changing the world of medicine since the technologies that have been developed have made available to researchers and clinicians enormous amounts of data in digital formats that can be used to complement or help in complex tasks such as mentioned decision making. A key element in this process is data analysis techniques, since without them it is not possible to exploit the information. Currently the most used techniques are based on algorithms in the area of artificial intelligence and more specifically machine learning. This paper focuses on a specific domain of medicine, renal replacement therapies for end-stage renal disease, where machine learning is beginning to be used as a complementary tool to predict or make decisions. This paper provides a narrative review of the main machine learning methods that are being used to conduct end-stage renal disease treatment analyses.
It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys automatically. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images. These features are used as input to learn kidney boundary distance maps using a boundary distance regression network and the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixelwise classification network in an end-to-end learning fashion. We also adopted a data-augmentation method based on kidney shape registration to generate enriched training data from a small number of US images with manually segmented kidney labels. Experimental results have demonstrated that our method could automatically segment the kidney with promising performance, significantly better than deep learning-based pixel classification networks.
Deep Belief Networks (DBN) with IoT Based Alzheimer's Disease Detection and Classification
- N Alqahtani
- S Alam
- I Aqeel
- M Shuaib
- I Khormi
- S B Mohsen
- Khan