Recently, Artificial Intelligence (AI) has been used widely in medicine and health care sector. In machine learning, the classification or prediction is a major field of AI. Today, the study of existing predictive models based on machine learning methods is extremely active. Doctors need accurate predictions for the outcomes of their patients' diseases. In addition, for accurate predictions, timing is another significant factor that influences treatment decisions. In this paper, existing predictive models in medicine and health care have critically reviewed. Furthermore, the most famous machine learning methods have explained, and the confusion between a statistical approach and machine learning has clarified. A review of related literature reveals that the predictions of existing predictive models differ even when the same dataset is used. Therefore, existing predictive models are essential, and current methods must be improved.
Blockchain in healthcare applications requires robust security and privacy mechanism for high-level authentication, interoperability and medical records sharing to comply with the strict legal requirements of the Health Insurance Portability and Accountability Act of 1996. Blockchain technology in the healthcare industry has received considerable research attention in recent years. This study conducts a review to substantially analyse and map the research landscape of current technologies, mainly the use of blockchain in healthcare applications, into a coherent taxonomy. The present study systematically searches all relevant research articles on blockchain in healthcare applications in three accessible databases, namely, ScienceDirect, IEEE and Web of Science, by using the defined keywords 'blockchain', 'healthcare' and 'electronic health records' and their variations. The final set of collected articles related to the use of blockchain in healthcare application is divided into three categories. The first category includes articles (i.e. 43/58 scientific articles) that attempted to develop and design healthcare applications integrating blockchain, particularly those on new architecture, system designs, framework, scheme, model, platform, approach, protocol and algorithm. The second category includes studies (i.e., 6/58 scientific articles) that attempted to evaluate and analyse the adoption of blockchain in the healthcare system. Finally, the third category comprises review and survey articles (i.e., 6/58 scientific articles) related to the integration of blockchain into healthcare applications. The final articles for review are discussed on the basis of five aspects: (1) year of publication, (2) nationality of authors, (3) publishing house or journal, (4) purpose of using blockchain in health applications and the corresponding contributions and (5) problem types and proposed solutions. Additionally, this study provides identified motivations, open challenges and recommendations on the use of blockchain in healthcare applications. The current research contributes to the literature by providing a detailed review of feasible alternatives and identifying the research gaps. Accordingly, researchers and developers are provided with appealing opportunities to further develop decentralised healthcare applications through a comprehensive discussion of about the importance of blockchain and its integration into various healthcare applications.
The study of electroencephalography (EEG) signals is not a new topic. However, the analysis of human emotions upon exposure to music considered as important direction. Although distributed in various academic databases, research on this concept is limited. To extend research in this area, the researchers explored and analysed the academic articles published within the mentioned scope. Thus, in this paper a systematic review is carried out to map and draw the research scenery for EEG human emotion into a taxonomy. Systematically searched all articles about the, EEG human emotion based music in three main databases: ScienceDirect, Web of Science and IEEE Xplore from 1999 to 2016. These databases feature academic studies that used EEG to measure brain signals, with a focus on the effects of music on human emotions. The screening and filtering of articles were performed in three iterations. In the first iteration, duplicate articles were excluded. In the second iteration, the articles were filtered according to their titles and abstracts, and articles outside of the scope of our domain were excluded. In the third iteration, the articles were filtered by reading the full text and excluding articles outside of the scope of our domain and which do not meet our criteria. Based on inclusion and exclusion criteria, 100 articles were selected and separated into five classes. The first class includes 39 articles (39%) consists of emotion, wherein various emotions are classified using artificial intelligence (AI). The second class includes 21 articles (21%) is composed of studies that use EEG techniques. This class is named 'brain condition'. The third class includes eight articles (8%) is related to feature extraction, which is a step before emotion classification. That this process makes use of classifiers should be noted. However, these articles are not listed under the first class because these eight articles focus on feature extraction rather than classifier accuracy. The fourth class includes 26 articles (26%) comprises studies that compare between or among two or more groups to identify and discover human emotion-based EEG. The final class includes six articles (6%) represents articles that study music as a stimulus and its impact on brain signals. Then, discussed the five main categories which are action types, age of the participants, and number size of the participants, duration of recording and listening to music and lastly countries or authors' nationality that published these previous studies. it afterward recognizes the main characteristics of this promising area of science in: motivation of using EEG process for measuring human brain signals, open challenges obstructing employment and recommendations to improve the utilization of EEG process.
Glaucoma is a type of eye condition which may result in partial or consummate vision loss. Higher intraocular pressure is the leading cause for this condition. Screening for glaucoma and early detection can avert vision loss. Computer aided diagnosis (CAD) is an automated process with the potential to identify glaucoma early through quantitative analysis of digital fundus images. Preparing an effective model for CAD requires a large database. This study presents a CAD tool for the precise detection of glaucoma using a machine learning approach. An autoencoder is trained to determine effective and important features from fundus images. These features are used to develop classes of glaucoma for testing. The method achieved an F - measure value of 0.95 utilizing 1426 digital fundus images (589 control and 837 glaucoma). The efficacy of the system is evident, and is suggestive of its possible utility as an additional tool for verification of clinical decisions.
The increasing number of diabetic retinopathy (DR) cases world wide demands the development of an automated decision support system for quick and cost-effective screening of DR. We present an automatic screening system for detecting the early stage of DR, which is known as non-proliferative diabetic retinopathy (NPDR). The proposed system involves processing of fundus images for extraction of abnormal signs, such as hard exudates, cotton wool spots, and large plaque of hard exudates. A rule based classifier is used for classifying the DR into two classes, namely, normal and abnormal. The abnormal NPDR is further classified into three levels, namely, mild, moderate, and severe. To evaluate the performance of the proposed decision support framework, the algorithms have been tested on the images of STARE database. The results obtained from this study show that the proposed system can detect the bright lesions with an average accuracy of about 97%. The study further shows promising results in classifying the bright lesions correctly according to NPDR severity levels.
Current trends in medicine, specifically in the electronic handling of medical applications, ranging from digital imaging, paperless hospital administration and electronic medical records, telemedicine, to computer-aided diagnosis, creates a burden on the network. Distributed Service Architectures, such as Intelligent Network (IN), Telecommunication Information Networking Architecture (TINA) and Open Service Access (OSA), are able to meet this new challenge. Distribution enables computational tasks to be spread among multiple processors; hence, performance is an important issue. This paper proposes a novel approach in load balancing, the Random Sender Initiated Algorithm, for distribution of tasks among several nodes sharing the same computational object (CO) instances in Distributed Service Architectures. Simulations illustrate that the proposed algorithm produces better network performance than the benchmark load balancing algorithms-the Random Node Selection Algorithm and the Shortest Queue Algorithm, especially under medium and heavily loaded conditions.
For a given DNA sequence, it is well known that pair wise alignment schemes are used to determine the similarity with the DNA sequences available in the databanks. The efficiency of the alignment decides the type of amino acids and its corresponding proteins. In order to evaluate the given DNA sequence for its proteomic identity, a pattern matching approach is proposed in this paper. A block based semi-global alignment scheme is introduced to determine the similarity between the DNA sequences (known and given). The two DNA sequences are divided into blocks of equal length and alignment is performed which minimizes the computational complexity. The efficiency of the alignment scheme is evaluated using the parameter, percentage of similarity (POS). Four essential DNA version of the amino acids that emphasize the importance of proteomic functionalities are chosen as patterns and matching is performed with the known and given DNA sequences to determine the similarity between them. The ratio of amino acid counts between the two sequences is estimated and the results are compared with that of the POS value. It is found from the experimental results that higher the POS value and the pattern matching higher are the similarity between the two DNA sequences. The optimal block is also identified based on the POS value and amino acids count.
This study focuses on the situation of health information exchange (HIE) in the context of a nationwide network. It aims to create a security framework that can be implemented to ensure the safe transmission of health information across the boundaries of care providers in Malaysia and other countries. First, a critique of the major elements of nationwide health information networks is presented from the perspective of security, along with such topics as the importance of HIE, issues, and main approaches. Second, a systematic evaluation is conducted on the security solutions that can be utilized in the proposed nationwide network. Finally, a secure framework for health information transmission is proposed within a central cloud-based model, which is compatible with the Malaysian telehealth strategy. The outcome of this analysis indicates that a complete security framework for a global structure of HIE is yet to be defined and implemented. Our proposed framework represents such an endeavor and suggests specific techniques to achieve this goal.
The investments and costs of infrastructure, communication, medical-related equipments, and software within the global healthcare ecosystem portray a rather significant increase. The emergence of this proliferation is then expected to grow. As a result, information and cross-system communication became challenging due to the detached independent systems and subsystems which are not connected. The overall model fit expending over a sample size of 320 were tested with structural equation modelling (SEM) using AMOS 20.0 as the modelling tool. SPSS 20.0 is used to analyse the descriptive statistics and dimension reliability. Results of the study show that system utilisation and system impact dimension influences the overall level of services of the healthcare providers. In addition to that, the findings also suggest that systems integration and security plays a pivotal role for IT resources in healthcare organisations. Through this study, a basis for investigation on the need to improvise the Malaysian healthcare ecosystem and the introduction of a cloud computing platform to host the national healthcare information exchange has been successfully established.
This paper aims at identifying the factors that would help to diagnose acute myocardial infarction (AMI) using data from an electronic medical record system (EMR) and then generating structure decisions in the form of linguistic fuzzy rules to help predict and understand the outcome of the diagnosis. Since there is a tradeoff in the fuzzy system between the accuracy which measures the capability of the system to predict the diagnosis of AMI and transparency which reflects its ability to describe the symptoms-diagnosis relation in an understandable way, the proposed fuzzy rules are designed in a such a way to find an appropriate balance between these two conflicting modeling objectives using multi-objective genetic algorithms. The main advantage of the generated linguistic fuzzy rules is their ability to describe the relation between the symptoms and the outcome of the diagnosis in an understandable way, close to human thinking and this feature may help doctors to understand the decision process of the fuzzy rules.
This study presents a systematic literature review of access control for electronic health record systems to protect patient's privacy. Articles from 2006 to 2016 were extracted from the ACM Digital Library, IEEE Xplore Digital Library, Science Direct, MEDLINE, and MetaPress using broad eligibility criteria, and chosen for inclusion based on analysis of ISO22600. Cryptographic standards and methods were left outside the scope of this review. Three broad classes of models are being actively investigated and developed: access control for electronic health records, access control for interoperability, and access control for risk analysis. Traditional role-based access control models are extended with spatial, temporal, probabilistic, dynamic, and semantic aspects to capture contextual information and provide granular access control. Maintenance of audit trails and facilities for overriding normal roles to allow full access in emergency cases are common features. Access privilege frameworks utilizing ontology-based knowledge representation for defining the rules have attracted considerable interest, due to the higher level of abstraction that makes it possible to model domain knowledge and validate access requests efficiently.
This study aims to provide security solutions for implementing electronic medical records (EMRs). E-Health organizations could utilize the proposed method and implement recommended solutions in medical/health systems. Majority of the required security features of EMRs were noted. The methods used were tested against each of these security features. In implementing the system, the combination that satisfied all of the security features of EMRs was selected. Secure implementation and management of EMRs facilitate the safeguarding of the confidentiality, integrity, and availability of e-health organization systems. Health practitioners, patients, and visitors can use the information system facilities safely and with confidence anytime and anywhere. After critically reviewing security and data transmission methods, a new hybrid method was proposed to be implemented on EMR systems. This method will enhance the robustness, security, and integration of EMR systems. The hybrid of simple object access protocol/extensible markup language (XML) with advanced encryption standard and secure hash algorithm version 1 has achieved the security requirements of an EMR system with the capability of integrating with other systems through the design of XML messages.
An important preliminary step in the diagnosis of leukemia is the visual examination of the patient's peripheral blood smear under the microscope. Morphological changes in the white blood cells can be an indicator of the nature and severity of the disease. Manual techniques are labor intensive, slow, error prone and costly. A computerized system can be used as a supportive tool for the specialist in order to enhance and accelerate the morphological analysis process. This research present a new method that integrates color features with the morphological reconstruction to localize and isolate lymphoblast cells from a microscope image that contains many cells. The localization and segmentation are conducted using a proposed method that consists of an integration of several digital image processing techniques. 180 microscopic blood images were tested, and the proposed framework managed to obtain 100% accuracy for the localization of the lymphoblast cells and separate it from the image scene. The results obtained indicate that the proposed method can be safely used for the purpose of lymphoblast cells localization and segmentation and subsequently, aiding the diagnosis of leukemia.
Worldwide healthcare delivery trends are undergoing a subtle paradigm shift--patient centered services as opposed to provider centered services and wellness maintenance as opposed to illness management. In this paper we present a Tele-Healthcare project TIDE--Tele-Healthcare Information and Diagnostic Environment. TIDE manifests an 'intelligent' healthcare environment that aims to ensure lifelong coverage of person-specific health maintenance decision-support services--i.e., both wellness maintenance and illness management services--ubiquitously available via the Internet/WWW. Taking on an all-encompassing health maintenance role--spanning from wellness to illness issues--the functionality of TIDE involves the generation and delivery of (a) Personalized, Pro-active, Persistent, Perpetual, and Present wellness maintenance services, and (b) remote diagnostic services for managing noncritical illnesses. Technically, TIDE is an amalgamation of diverse computer technologies--Artificial Intelligence, Internet, Multimedia, Databases, and Medical Informatics--to implement a sophisticated healthcare delivery infostructure.
Acoustic analysis of infant cry signals has been proven to be an excellent tool in the area of automatic detection of pathological status of an infant. This paper investigates the application of parameter weighting for linear prediction cepstral coefficients (LPCCs) to provide the robust representation of infant cry signals. Three classes of infant cry signals were considered such as normal cry signals, cry signals from deaf babies and babies with asphyxia. A Probabilistic Neural Network (PNN) is suggested to classify the infant cry signals into normal and pathological cries. PNN is trained with different spread factor or smoothing parameter to obtain better classification accuracy. The experimental results demonstrate that the suggested features and classification algorithms give very promising classification accuracy of above 98% and it expounds that the suggested method can be used to help medical professionals for diagnosing pathological status of an infant from cry signals.
Electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. The long-term EEG recordings of an epileptic patient obtained from the ambulatory recording systems contain a large volume of EEG data. Detection of the epileptic activity requires a time consuming analysis of the entire length of the EEG data by an expert. The traditional methods of analysis being tedious, many automated diagnostic systems for epilepsy have emerged in recent years. This paper discusses an automated diagnostic method for epileptic detection using a special type of recurrent neural network known as Elman network. The experiments are carried out by using time-domain as well as frequency-domain features of the EEG signal. Experimental results show that Elman network yields epileptic detection accuracy rates as high as 99.6% with a single input feature which is better than the results obtained by using other types of neural networks with two and more input features.
The massive number of medical images produced by fluoroscopic and other conventional diagnostic imaging devices demand a considerable amount of space for data storage. This paper proposes an effective method for lossless compression of fluoroscopic images. The main contribution in this paper is the extraction of the regions of interest (ROI) in fluoroscopic images using appropriate shapes. The extracted ROI is then effectively compressed using customized correlation and the combination of Run Length and Huffman coding, to increase compression ratio. The experimental results achieved show that the proposed method is able to improve the compression ratio by 400 % as compared to that of traditional methods.
Depression affects large number of people across the world today and it is considered as the global problem. It is a mood disorder which can be detected using electroencephalogram (EEG) signals. The manual detection of depression by analyzing the EEG signals requires lot of experience, tedious and time consuming. Hence, a fully automated depression diagnosis system developed using EEG signals will help the clinicians. Therefore, we propose a deep hybrid model developed using convolutional neural network (CNN) and long-short term memory (LSTM) architectures to detect depression using EEG signals. In the deep model, temporal properties of the signals are learned with CNN layers and the sequence learning process is provided through the LSTM layers. In this work, we have used EEG signals obtained from left and right hemispheres of the brain. Our work has provided 99.12% and 97.66% classification accuracies for the right and left hemisphere EEG signals respectively. Hence, we can conclude that the developed CNN-LSTM model is accurate and fast in detecting the depression using EEG signals. It can be employed in psychiatry wards of the hospitals to detect the depression using EEG signals accurately and thus aid the psychiatrists.
The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer's disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student's t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer's diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54%, precision of 88.33%, sensitivity of 96.30% and specificity of 93.64%. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48%, 100%, 96.97% and 100%, respectively, with the benchmark MRI database.
Monitoring the depth of anesthesia (DOA) during surgery is very important in order to avoid patients' interoperative awareness. Since the traditional methods of assessing DOA which involve monitoring the heart rate, pupil size, sweating etc, may vary from patient to patient depending on the type of surgery and the type of drug administered, modern methods based on electroencephalogram (EEG) are preferred. EEG being a nonlinear signal, it is appropriate to use nonlinear chaotic parameters to identify the anesthetic depth levels. This paper discusses an automated detection method of anesthetic depth levels based on EEG recordings using non-linear chaotic features and neural network classifiers. Three nonlinear parameters, namely, correlation dimension (CD), Lyapunov exponent (LE) and Hurst exponent (HE) are used as features and two neural network models, namely, multi-layer perceptron network (feed forward model) and Elman network (feedback model) are used for classification. The neural network models are trained and tested with single and multiple features derived from chaotic parameters and the performances are evaluated in terms of sensitivity, specificity and overall accuracy. It is found from the experimental results that the Lyapunov exponent feature with Elman network yields an overall accuracy of 99% in detecting the anesthetic depth levels.