The Internet of Medical Things (IoMT). Группа авторов
platform is proposed by the authors that can be used to store electronic medical records in cloud environments and management. In this study, they have proposed a model for the health data Blockchain-based structure for cloud computing environments. Their contributions include the proposed solution and the presentation of the future direction of medical data at Blockchain. This paper provides an overview of the handling of heterogeneous health data, and a description of internal functions and protocols.
Authors in [7] presented a fuzzy-based method for iterative image reconstruction in Emission Tomography (ET). In this, two simple operations, fuzzy filtering and fuzzy smoothing, are performed. Fuzzy filtering is used for reconstruction to identify edges, while fuzzy smoothing is used for penalizing only those pixels for which the edges are missing in the nearest neighborhood. These operations are performed iteratively until appropriate convergence is achieved.
Authors in [8] developed image segmentation techniques using fuzzy-based artificial bee colony (FABC). In that research, the author has combined the fuzzy c-means (FCM) and artificial bee colony (ABC) optimization to search for better cluster century. The proposed method FABC is more reliable than other optimization approaches like GA and PSO (particle swarm optimization). The experiment performed on grayscale images includes some synthetic medical and texture images. The proposed method has the advantages of fast convergence and low computational cost.
Authors in [9] preserved the useful data; the suggested adaptive fuzzy hexagonal bilateral filter eliminates the Gaussian noise. The local and global evaluation metrics are used to create the fuzzy hexagonal membership function. The recommended method combines the median filter and the bilateral filter in an adaptive way. The bilateral filter is often used to retain the edges by smoothing the noise in the MRI image and by using a local filter to maintain the edges and obtain structural information. The proposed approach and the existing approach performed a series of experiments on synthetic and clinical brain MRI data at various noise levels. The outcome demonstrates that the proposed method restores the image to improved quality of the image which can be used for the diagnostic purpose well at both low and high Gaussian noise densities.
In [10], the authors conceptualized the proposed use of share information on the protection of health and health data to share any individual technology line dynamic Blockchain transparent cloud storage. In addition, they also provide quality control checking module machine learning data quality engineering data base. The main objective of the proposed system will allow us to share our personal health data in accordance with the GDPR for each common interest of each dataset, control, and security. This allows researchers for high quality research to effectively protect personal health data through consumer and commercial data for commercial purposes. The first characters of data from this work, personal data of health (grouped into different categories of dynamic and static data), and a method for health-related data capable of data acquisition) enabled mobile devices (continuous data and real time). In the case of a solution that has been integrated, using a pointer hash for storage space in a variety of sizes has been integrated. First, they proposed to use different sizes of dynamic run sharing. Second, they proposed dynamic system Blockchain and cloud storage of health data. They also proposed the size of cloud-shaped Blockchain health encrypted data that can be stored in both formats data. To control the inherent quality of the proposed system, the data module is recognized, and Lions and stock may also be associated with the transactions and metadata. Third, the machine is supported by hardware and software technology.
Authors proposed system for medical image classification, a robust sparse representation is presented based on the adaptive type-2 fuzzy learning (T2-FDL) method. In the current procedure, sparse coding and dictionary learning method are iteratively performed until a near-optimum dictionary is produced. Two open-access brain tumor MRI databases, “REMBRANDT and TCGA-LGG,” from the Cancer Imaging Archive (TCIA), are used to conduct the experiments. The research findings of a classification task for brain tumors indicate that the implemented T2-FDL approach can effectively mitigate the adverse impacts of ambiguity in images data. The outcomes show the performance of the T2-FDL in terms of accuracy, specificity, and sensitivity compared to other relevant classification methods in the literature.
The authors proposed the framework to introduce briefly the various soft computing methodologies and to present various applications in medicine. The scope is to demonstrate the possibilities of applying soft computing to medicine related problems. The recent published knowledge about use of soft computing in medicine is observed from the literature surveyed and reviewed. This study detects which methodology or methodologies of soft computing are used frequently together to solve the special problems of medicine. According to database searches, the rates of preference of soft computing methodologies in medicine are found as 70% of fuzzy logic-neural networks, 27% of neural networks-genetic algorithms and 3% of fuzzy logic-genetic algorithms in our study results. So far, fuzzy logic-neural networks methodology was significantly used in clinical science of medicine. On the other hand neural networks-genetic algorithms and fuzzy logic-genetic algorithms methodologies were mostly preferred by basic science of medicine. The study showed that there is undeniable interest in studying soft computing methodologies in genetics, physiology, radiology, cardiology, and neurology disciplines.
The authors have proposed an automatically analyzing machine learning prediction results. Predictive modeling is a process that uses data mining and probability to forecast outcomes. Each model is made up of several predictors, which are variables that are likely to influence future results. Once data has been collected for relevant predictors, a statistical model is formulated. The model may employ a simple linear equation, or it may be a complex Neural Network, mapped out by sophisticated software. As additional data becomes available, the statistical analysis model is validated or revised. Predictive analytics can support population health management, financial success, and better outcomes across the value-based care sequence. Instead of simply presenting information about past events to a user, predictive analytics estimates the likelihood of a future outcome based on patterns in the historical data. The electronic medical record data set from the Practice Fusion diabetes classification competition containing patient records from all 50 states in the United States were utilized in this work and illustrated the method of predicting type 2 diabetes diagnosis within the next year. The prediction was done using two models, one for prediction and another for the explanation. The first model is used only for making predictions and aims at maximizing accuracy without being concerned about interpretability. It can be any machine learning model and arbitrarily complex. The second model is a rule-based associative classifier used only for explaining the first model’s results without being concerned about its accuracy.
The authors also described a decentralized system of managing personal data that users create themselves and control their data. They implement the protocol to change the automatic access control manager on Blockchain, which does not require a third-party trust. Unlike Bitcoin, its system is not strictly a financial transaction; it has to carry instructions for use, such as shared storage, query, and data. Finally, they discussed the extent of future potential Blockchain which can be used as the solution round for reliable computing problems in the community. The platform enables more: Blockchain intended as an access control itself with storage solutions in conjunction with Blockchain. Users rely on third parties and can always be aware of what kind of data is being collected about them and do not need to use them. Additionally, users of Blockchain recognize as the owner of their personal data. Companies, in turn, can focus on helping protect data properly and how to specifically use it without the bins being concerned. In addition, with the decentralization platform, sensitive data is gathered; it should be simple for legal rulings and rules on storage and sharing. In addition, laws and regulations can be programmed in Blockchain, so that they can be applied automatically. In other cases, access to data (or storage) may serve as evidence of that law, as it would be compromised.
In this review proposed a machine learning-based framework to identify type2 diabetes using EHR. This work utilized 3 years of EHR data. The data was stored in the central repository, which has been managed by the District Bureau of Health in Changning, Shanghai since 2008. The EHR data generated from 10 local EHR systems are automatically deposited into the centralized repository hourly. The machine learning models within the framework, including K-Nearest-Neighbors, Naïve Bayes, Decision Tree, Random Forest,