Medical Diagnosis Process Research Articles

Views of Parents of Children With Down Syndrome on Early Intervention Services in Turkey

Perceptions of parents of young children receiving early intervention are important to understand. Parents have valuable opinions on the delivery of early interventions services and can provide critical feedback that can help professionals revise their existing early intervention delivery modalities. In the current study, we examined the perceptions of parents of young children with Down syndrome on early intervention services in Turkey. Specifically, we aimed to understand the parents' views on medical and educational evaluation and diagnosis processes. The study was conducted using a cross-sectional research design, which is one of the survey design methods. Data were collected from a total of 893 parents via an online survey. The results demonstrated that children with Down syndrome were diagnosed within an average of 2.3 months from birth, but the average age for starting education was 10.5 months. The majority of the parents evaluated the process until their children were diagnosed and accessed education services as a rather slow process that proceeded with their own means and efforts. Furthermore, the parents reported that during the diagnosis processes the type of materials, equipment, toys, and settings used were not relevant and time provided was insufficient. Moreover, the majority of the parents reported that the education services presented to them and their children were not sufficient and early intervention services were not provided within a system. As a result, although the legal regulations in Turkey are parallel to those in developed countries and studies in the field have been increasingly gaining momentum, issues such as the absence of an early intervention system model, insufficient cooperation between experts and institutions, and the shortage of expert staff in the field are still present and awaiting a solution.

Fine-grained interactive attention learning for semi-supervised white blood cell classification

White blood cell (WBC) is an essential part of the human immune system. To diagnose blood diseases, hematologists have to think about the WBC information. For instance, the number of each type of WBCs often implies the health condition of the human body. Thus, the classification of white blood cell images plays a significant role in the medical diagnosis process. However, manual WBC inspection is time-consuming and labor-intensive for experts, which means automated classification methods are needed for WBC recognition. Another problem is that the traditional automatic recognition system needs a large amount of annotated medical images for training, which is highly costly. In this respect, the semi-supervised learning framework has recently been widely used for medical diagnosis due to its specificity, which can explore relevant information from massive unlabeled data. In this study, a novel semi-supervised white blood cell classification method is proposed, named by Fine-grained Interactive Attention Learning (FIAL). It consists of a Semi-Supervised Teacher-Student (SSTS) module and a Fine-Grained Interactive Attention (FGIA) mechanism. In detail, SSTS employs limited labeled WBC images and generates predicted probability vectors for a large amount of unlabeled WBC samples, like a human. After top-k selection in predicted probabilities, the efficient data can be exploited from unlabeled WBC images for training. With a very small amount of annotated WBC images, FIAL achieves an average accuracy of 93.2% on BCCD dataset when giving 75 labeled images for each category, which sufficiently elaborates our excellent capability on semi-supervised white blood cell image classification task.

CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING

The popularity of the use of computational tools such as artificial intelligence has been increasing in recent years, and its importance in medicine is a fact. This field has benefited greatly thanks to the incorporation of more effective and faster methodologies in the medical diagnosis and registration processes. In the present work, the classification of images related to three diseases: Tuberculosis, Glaucoma and Parkinson's is carried out. We used deep learning and the RESNET50 convolutional neural network to extract classification characteristics, and then perform the classification based on standard methods, such as support vector machines, Naïve Bayes, and Centroid-based classifier, which are incorporated into two scenarios (cross validation; training and test sets). The classifier's performance is evaluated quantitatively using three evaluation metrics. The results obtained support the feasibility of the proposed methodology and its potential to improve medical diagnosis.

An ultrafast-response and flexible humidity sensor for human respiration monitoring and noncontact safety warning

The humidity sensor is an essential sensing node in medical diagnosis and industrial processing control. To date, most of the reported relative humidity sensors have a long response time of several seconds or even hundreds of seconds, which would limit their real application for certain critical areas with fast-varying signals. In this paper, we propose a flexible and low-cost humidity sensor using vertically aligned carbon nanotubes (VACNTs) as electrodes, a PDMS-Parylene C double layer as the flexible substrate, and graphene oxide as the sensing material. The humidity sensor has an ultrafast response of ~20 ms, which is more than two orders faster than most of the previously reported flexible humidity sensors. Moreover, the sensor has a high sensitivity (16.7 pF/% RH), low hysteresis (<0.44%), high repeatability (2.7%), good long-term stability, and outstanding flexibility. Benefiting from these advantages, especially the fast response, the device has been demonstrated in precise human respiration monitoring (fast breathing, normal breathing, deep breathing, asthma, choking, and apnea), noncontact electrical safety warning for bare hand and wet gloves, and noncontact pipe leakage detection. In addition, the facile fabrication of the flexible platform with the PDMS-Parylene C double layer can be easily integrated with multisensing functions such as pH sensing, ammonium ion sensing, and temperature sensing, all of which are useful for more pattern recognition of human activity.

An ontology network for Diabetes Mellitus in Mexico

BackgroundMedical experts in the domain of Diabetes Mellitus (DM) acquire specific knowledge from diabetic patients through monitoring and interaction. This allows them to know the disease and information about other conditions or comorbidities, treatments, and typical consequences of the Mexican population. This indicates that an expert in a domain knows technical information about the domain and contextual factors that interact with it in the real world, contributing to new knowledge generation. For capturing and managing information about the DM, it is necessary to design and implement techniques and methods that allow: determining the most relevant conceptual dimensions and their correct organization, the integration of existing medical and clinical information from different resources, and the generation of structures that represent the deduction process of the doctor. An Ontology Network is a collection of ontologies of diverse knowledge domains which can be interconnected by meta-relations. This article describes an Ontology Network for representing DM in Mexico, designed by a proposed methodology. The information used for Ontology Network building include the ontological resource reuse and non-ontological resource transformation for ontology design and ontology extending by natural language processing techniques. These are medical information extracted from vocabularies, taxonomies, medical dictionaries, ontologies, among others. Additionally, a set of semantic rules has been defined within the Ontology Network to derive new knowledge.ResultsAn Ontology Network for DM in Mexico has been built from six well-defined domains, resulting in new classes, using ontological and non-ontological resources to offer a semantic structure for assisting in the medical diagnosis process. The network comprises 1367 classes, 20 object properties, 63 data properties, and 4268 individuals from seven different ontologies. Ontology Network evaluation was carried out by verifying the purpose for its design and some quality criteria.ConclusionsThe composition of the Ontology Network offers a set of well-defined ontological modules facilitating the reuse of one or more of them. The inclusion of international vocabularies as SNOMED CT or ICD-10 reinforces the representation by international standards. It increases the semantic interoperability of the network, providing the opportunity to integrate other ontologies with the same vocabularies. The ontology network design methodology offers a guide for ontology developers about how to use ontological and non-ontological resources in order to exploit the maximum of information and knowledge from a set of domains that share or not information.

A novel self-adaptive convolutional neural network model using spatial pyramid pooling for 3D lung nodule computer-aided diagnosis

This research proposes a novel self-adaptive convolutional neural network (Adap-Net) model for lung nodule diagnosis on 3D computed tomography (CT) images. Lung cancer is one of the most common cancers with a high mortality rate. Therefore, there is an urgent need to diagnose lung nodules to improve the survival rate, which is challenging because of the nodule heterogeneity and the lack of annotated lung nodule images. Prevailing research for lung nodule diagnosis usually ignores the nodule heterogeneity problem and enlarges the model complexity that degrades the lung nodule diagnosis performance given limited annotated training samples. To overcome the challenges, a transverse layer pooling (TLP) algorithm is proposed and the spatial pyramid pooling (SPP) scheme is integrated, which makes it possible to adaptively extract equal-dimensional feature representations from arbitrary-sized 3D lung nodule images. Meanwhile, the TLP algorithm introduces a layer compression architecture that dramatically reduces the model complexity. Moreover, K-means clustering is adopted to assign appropriate input image sizes for each lung nodule, allowing the mini-batch-based model training. The proposed Adap-Net is comprehensively evaluated and compared to other deep learning (DL) models using 3D CT images from a public dataset. Experimental results show that the proposed Adap-Net model improves the lung nodule diagnosis accuracy up to 12.12% with less than 10% of parameters that are involved in other DL models. In practice, the proposed Adap-Net model can offer complementary opinions in computer-aided diagnosis (CAD) systems as a supportive tool for radiologists and physicians in the medical image interpretation, analysis, and diagnosis process.

Variable weight algorithm for convolutional neural networks and its applications to classification of seizure phases and types

Deep learning techniques have recently achieved impressive results and raised expectations in the domains of medical diagnosis and physiological signal processing. The widely adopted methods include convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the existing models possess static connection weights between layers, which might limit the generalization capability and the classification performance of the models as the weights of different layers are fixed after training. Furthermore, to deal with a large amount of data, a neural network with a sufficiently large size is required. This paper proposes the variable weight convolutional neural networks (VWCNNs), which are a type of network structure employing dynamic weights instead of static weights in their convolutional layers and fully-connected layers. VWCNNs are able to adapt to different characteristics of input data and can be viewed as an infinite number of traditional, fixed-weight CNNs. We will show that the proposed VWCNN structure outperforms the conventional CNN in terms of the classification accuracy, generalization capability, and robustness when the inputs are contaminated by noise. In this paper, VWCNNs are applied to the classification of three seizure phases (seizure-free, pre-seizure and seizure) based on measured electroencephalography (EEG) data. VWCNNs achieve 100% test accuracy and show strong robustness in the classification of the three seizure phases, and thus show the potential to be a useful classification tool for medical diagnosis. Furthermore, the classification of seven types of seizures is investigated in this paper using the world’s largest open source database of seizure recordings, TUH EEG seizure corpus. Comparisons with conventional CNNs, RNN, MobileNet, ResNet, DenseNet and traditional machine learning methods including random forest, decision tree, support vector machine, K-nearest neighbours, standard neural networks, and Naïve Bayes are being conducted using realistic test data sets. The results demonstrate that VWCNNs have advantages over other classifiers in terms of classification accuracy and robustness.

Privacy-Preserving Behavioral Correctness Verification of Cross-Organizational Workflow With Task Synchronization Patterns

Workflow management technology has become a key means to improve enterprise productivity. More and more workflow systems are crossing organizational boundaries and may involve multiple interacting organizations. This article focuses on a type of loosely coupled workflow architecture with collaborative tasks, i.e., each business partner owns its private business process and is able to operate independently, and all involved organizations need to be synchronized at a certain point to complete certain public tasks. Because of each organization’s privacy consideration, they are unwilling to share the business details with others. In this way, traditional correctness verification approaches via reachability analysis are not practical as a global business process model is unavailable for privacy preservation. To ensure its globally correct execution, this work establishes a correctness verification approach for the cross-organizational workflow with task synchronization patterns. Its core idea is to use local correctness of each suborganizational workflow process to guarantee its global correctness. We prove that the proposed approach can be used to investigate the behavioral property preservation when synthesizing suborganizational workflows via collaborative tasks. A medical diagnosis running case is used to illustrate the applicability of the proposed approaches. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Cross-organizational workflow verification techniques play an increasingly important role in ensuring the correct execution of collaborative enterprise businesses. This work addresses the issue of correctness verification for loosely coupled interactive workflows with collaborative tasks. To ensure the globally correct execution, a behavioral correctness verification approach is established. All proposed concepts and techniques are supported by open-source tools, and evaluation over a medical diagnosis process case has shown their applicability. The proposed methodology is readily applicable to industrial-size workflow correctness verification problems.

MoMAC: Multi-objective optimization to combine multiple association rules into an interpretable classification

A crucial characteristic of machine learning models in various domains (such as medical diagnosis, financial analysis, or real-time process monitoring) is the interpretability. The interpretation supports humans in understanding the meaning behind every single prediction made by the machine, and enables the user to assess trustworthiness before acting on the predictions. This article presents our work in building an interpretable classification model based on association rule mining and multi-objective optimization. The classification model itself is a rule list, making a single prediction based on multiple rules. The rule list consists of If ... THEN statements that are understandable to humans. We choose these rules from a large set of pre-mined rules according to an interestingness measure which is formulated as a function of basic probabilities related to the rules. We learned the interestingness measure through multi-objective optimization, concentrating on two objectives: the classifier’s size in terms of number of rules and prediction accuracy. The model is called MoMAC, “Multi-Objective optimization to combine Multiple Association rules into an interpretable Classification”. The experimental results on benchmark datasets demonstrate that MoMAC outperforms other existing rule-based classification methods in terms of classification accuracy.

A Study of Fuzzy Relation and Its Application in Medical Diagnosis

Objective: Medical diagnosis process extends within the degree to which they plan to affect different complicating aspects of diagnosis. In this research work, the concept of fuzzy relation with medical diagnosis is studied and the application of fuzzy relations to such problems by extending the Sanchez’s approach is introduced.&#x0D; Method: An application of fuzzy relation with Sanchez's approach for medical diagnosis is presented. Based on the composition of the fuzzy relations, an algorithm for medical diagnosis as follows- first input the number of objects and attributes to obtain patient symptom matrix, symptom-disease matrix and the composition of fuzzy relations to get the patient-diagnosis matrix. Then find the maximum value to evaluate which patient is suffering from what disease.&#x0D; Result: Using the algorithm for medical diagnosis, the disease for which the membership value is maximum gives the final decision. If almost equal values for different diagnosis in composition are obtained, the case for which non-membership is minimum and hesitation is least is considered. The output matched well with the doctor’s diagnosis.&#x0D; Conclusion: In the process of medical diagnosis, state of patient are given by the patient through linguistic terminology like as temperature, cough, stomach pain etc., consideration of fuzzy sets as grades for association instead of membership grades in [0,1] is more advantageous to model the state of the patient. Similarly fuzzy relation has been introduced representing the association between symptoms and diseases. Sanchez’s approach has been extended for medical diagnosis in this reference. The approach used to form fuzzy matrix showing the association of symptoms and diseases is based on the sanchez’s approach.

Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases.

Artificial intelligence (AI)-based diagnostic tools have been accepted in ophthalmology. The use of retinal images, such as fundus photographs, is a promising approach for the development of AI-based diagnostic platforms. Retinal pathologies usually occur in a broad spectrum of eye diseases, including neovascular or dry age-related macular degeneration, epiretinal membrane, rhegmatogenous retinal detachment, retinitis pigmentosa, macular hole, retinal vein occlusions, and diabetic retinopathy. Here, we report a fundus image-based AI model for differential diagnosis of retinal diseases. We classified retinal images with three convolutional neural network models: ResNet50, VGG19, and Inception v3. Furthermore, the performance of several dense (fully connected) layers was compared. The prediction accuracy for diagnosis of nine classes of eight retinal diseases and normal control was 87.42% in the ResNet50 model, which added a dense layer with 128 nodes. Furthermore, our AI tool augments ophthalmologist’s performance in the diagnosis of retinal disease. These results suggested that the fundus image-based AI tool is applicable for the medical diagnosis process of retinal diseases.

Deep convolutional neural network architecture design as a bi-level optimization problem

During the last decade, deep neural networks have shown a great performance in many machine learning tasks such as classification and clustering. One of the most successful networks is the CNN (Convolutional Neural Network), which has been applied in many application domains such as pattern recognition, medical diagnosis, and signal processing. Despite the very interesting performance of CNNs, their architecture design is still so far a major challenge for researchers and practitioners. Several works have been proposed in the literature with the aim to find optimized architectures such as ResNet and VGGNet. Unfortunately, most of these architectures are either manually defined by experts or automatically designed by greedy induction algorithms. Recent works suggest the use of Evolutionary Algorithms (EAs) thanks to their ability to escape locally-optimal architectures. Despite the fact that EAs have shown interesting performance, researchers in this direction have considered the design task as a single-level optimization problem; which represents the main research gap we tackle in this paper. The main contribution behind our work consists in the fact that CNN architecture design has a hierarchical nature and thus could be seen as a Bi-Level Optimization Problem (BLOP) where: (1) the upper level minimizes the network complexity defined by the number of blocks and the number of nodes per block; and (2) the lower level optimizes the convolution block ‘graphs’ topologies by maximizing the classification accuracy. Motivated by the originality of our observation with respect to the state of the art, we frame for the first time the CNN architecture design problem as a BLOP and then solve it using an adapted version of an existing efficient bi-level EA; through the definition of the solution encoding, the fitness function, and the variation operators at each level. The adapted EA is named BLOP-CNN and is assessed on the image classification task using the commonly employed CIFAR-10 and CIFAR-100 benchmark data sets. The analysis of our experimental results show the merits of our proposed method in providing the user with optimized architectures that outperform many recent and prominent architectures coming from the three different approaches, namely: manual design, reinforcement learning-based generation, and evolutionary optimization. Moreover, to show the applicability of our approach, we have conducted a case study on the detection of the COVID-19 using a set of benchmark chest X-ray and Computed Tomography (CT) images.

Exploring sMRI Biomarkers for Diagnosis of Autism Spectrum Disorders Based on Multi Class Activation Mapping Models

Due to the complexity of the etiology of autism spectrum disorders, the existing autism diagnosis method is still based on scales. With the continuous development of artificial intelligence, image-aided diagnosis of brain diseases has been widely studied and concerned. However, many doctors and researchers still doubt the diagnosis basis of the neural network and think that the neural network belongs to a limited interpretable black-box function approximator. They are not sure whether the neural network has learned some interpretive image features like humans. In order to solve this problem, three new models (2D CAM, 3D CAM and 3D Grad-CAM) are proposed for structural Magnetic Resonance Imaging (sMRI) data. The Regions Of Interest (ROI) of subcortical tissues among models and between groups are analyzed based on the heat maps of the three models. The experimental results show that these models mainly distinguish the autism group and the control group according to the voxel value of these ROIs. There are significant differences in mean voxel value and standard deviation of voxel value between the autism group and the control group, such as in the left amygdala, optic chiasm and right hippocampus. According to medical references, these ROIs are closely related to people’s speech, cognition and behavior. This can partly explain why autistic patients have unusual symptoms such as speech communication disorder, stereotyped repetitive behavior and so on. The proposed visualization models can provide a good bridge for doctors to understand the brain features learned by the neural network. The research method of this paper may provide a new way for doctors and researchers to find the diagnostic biomarkers of autism, which can greatly speed up the process of modern medical diagnosis and treatment strategies, and liberate doctors from the traditional trial and error.

WITHDRAWN: Breast cancers detection using deep learning algorithm

Abstract Deep learning method is the process of detection of breast cancer, it consist of many hidden layers to produce most appropriate outputs. This paper shows how to detect breast cancers at a very early stage using this algorithm that mostly uses computer vision, image processing, medical diagnosis and neural language processing. As like supervised learning method, it maps the input data-mammogram scanned image to a certain trained data to produce a proper result that classifies the output as benign or malignant type of tumor present in breast else it is normal. A cluster of 400 women were recruited for this research with proper ethical approval and consents from the concerned authorities. The study has succeeded in achieving its overall aim. Along with the main objective, this research has also differentiated the type of tumor that has been diagnosed.

Outlier Detection of Mixed Data Based on Neighborhood Combinatorial Entropy

Outlier detection is a key research area in data mining technologies, as outlier detection can identify data inconsistent within a data set. Outlier detection aims to find an abnormal data size from a large data size and has been applied in many fields including fraud detection, network intrusion detection, disaster prediction, medical diagnosis, public security, and image processing. While outlier detection has been widely applied in real systems, its effectiveness is challenged by higher dimensions and redundant data attributes, leading to detection errors and complicated calculations. The prevalence of mixed data is a current issue for outlier detection algorithms. An outlier detection method of mixed data based on neighborhood combinatorial entropy is studied to improve outlier detection performance by reducing data dimension using an attribute reduction algorithm. The significance of attributes is determined, and fewer influencing attributes are removed based on neighborhood combinatorial entropy. Outlier detection is conducted using the algorithm of local outlier factor. The proposed outlier detection method can be applied effectively in numerical and mixed multidimensional data using neighborhood combinatorial entropy. In the experimental part of this paper, we give a comparison on outlier detection before and after attribute reduction. In a comparative analysis, we give results of the enhanced outlier detection accuracy by removing the fewer influencing attributes in numerical and mixed multidimensional data.

Autonomous robots: a new reality in healthcare? A project by European Association of Urology-Young Academic Urologist group.

Artificial intelligence appears as a potential revolution in the general process of medical training, disease diagnosis and treatment. A novel disruptive technology of the 21st century will be 'learner' robots from artificial intelligence systems able to use all the combination of the available knowledge in medical repositories to give the best standard of care. The autonomy level of robots depends on three factors: the complexity of the task; the environment in which the robot operates, and the required level of human-robot interaction. Autonomous robots in healthcare may be classified in delivery, nurse, and surgical robots. The increasing capability of robots to perform independent actions and complex tasks raises responsibility and accountability issues in a wide variety of application domains. Ethical analyses of these issues are underway and are mostly oriented toward the development of ethical policies requiring a law frame on robotic autonomous behaviors. Autonomous robots have the potential to improve current medical practice offering a more secure, reliable, and reproducible medicine. Many advancements are required for these new technologies to be fully integrated. Furthermore, the ethical implications of these technologies are yet to be evaluated.

Imaging Review of Peripheral Nerve Injuries in Patients with COVID-19

With surging numbers of coronavirus disease 2019 (COVID-19) patients throughout the world, neuromuscular complications and rehabilitation concerns are becoming more apparent. Peripheral nerve injury can occur in COVID-19 patients secondary to post-infectious inflammatory neuropathy, prone positioning-related stretch/compression injury, systemic neuropathy, or nerve entrapment from hematoma. Imaging of peripheral nerves in COVID-19 patients may help characterize nerve pathology, identify site and severity of nerve damage, and potentially elucidate mechanisms of injury thereby aiding the medical diagnosis and decisionmaking process. This review article aims to provide a first comprehensive summary of the current knowledge of COVID-19 and peripheral nerve imaging.

An e-Delphi Study on Software Virtualization in the Medical Diagnosis Process: The Experts' Perspective

The purpose of this qualitative e-Delphi study was to collect opinions and experiences from a group of expert panel members made up of physicians and virtualization experts. This e-Delphi research study provided information about the opinions and experiences from experts about the possible benefits for virtualization in medical facilities. The expert panel was comprised of 12 virtualization experts and physicians. Virtualization is a concept of technology where one physical hardware device, called a server, is configured with software that allows for multiple software servers to be installed or implemented. Virtualization may offer benefits to healthcare organizations including the ability to deliver patient data to physicians more quickly. Virtualization has demonstrated substantial benefits in many areas of information technology infrastructure in the medical informatics field. The expert panel members were chosen at random through existing professional relationships and previous employment. The expert panel members were provided three rounds of survey questions and were asked to complete all surveys in its entirety. The findings show that hospitals and medical facilities will benefit from virtualization and provide increased patient care by delivering faster data to the patient and physician. As leaders in hospitals and medical facilities continue to be well-informed, leaders will be better equipped to make more-informed decisions about virtualization and the positive relationship software virtualization has on patient care.

Specifics of Using Image Processing Techniques for Blood Smear Analysis

The process of medical diagnosis is an important stage in the study of human health. One of the directions of such diagnostics is the analysis of images of blood smears. In doing so, it is important to use different methods and analysis tools for image processing. It is also important to consider the specificity of blood smear imaging. The paper discusses various methods for analyzing blood smear images. The features of the application of the image processing technique for the analysis of a blood smear are highlighted. The results of processing blood smear images are presented.

Integrated Declarative Process and Decision Discovery of the Emergency Care Process

Deviations and variations are the norm rather than the exception in medical diagnosis and treatment processes. Physicians must leverage their knowledge and experience to choose an appropriate variation for each patient. However, this knowledge and experience is often tacit. Process modeling offers a way to convert tacit to explicit knowledge. Many process mining techniques have been developed due to the difficulty of doing this manually, yet, they often neglect the decisions themselves, and these proposed techniques are just one piece of a comprehensive process discovery method. In this paper, we use the Action Design Research methodology to develop a method for process and decision discovery of medical diagnosis and treatment processes. The method was iteratively improved and validated by applying it to a practical setting, which was the emergency medicine department of a hospital. An analysis of the resulting model shows that previously tacit knowledge was successfully made explicit.