An IoT Framework for Heart Disease Prediction Based on MDCNN Classifier

Khan, Mohammad Ayoub

doi:10.1109/access.2020.2974687

Cited by 243 publications

(119 citation statements)

References 38 publications

Supporting

Mentioning

119

Contrasting

Order By: Relevance

“…In particular, several predictive models based on neural networks have been designed for accurately classifying heart disease [17]. In recent works, convolutional neural networks (CNN) have been implemented for identifying different categories of heartbeats in ECG signals [18], and a modified deep convolutional neural network has been utilized for classifying the ECG data into normal and abnormal [19]. Recurrent neural network (RNN) has also been employed for predicting future disease using robust patient representations of EHR [20] and modeling temporal relations among events in EHR data [21].…”

Section: Introductionmentioning

confidence: 99%

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

et al. 2020

View full text Add to dashboard Cite

Heart diseases are highly ranked among the leading causes of mortality in the world. They have various types including vascular, ischemic, and hypertensive heart disease. A large number of medical features are reported for patients in the Electronic Health Records (EHR) that allow physicians to diagnose and monitor heart disease. We collected a dataset from Medica Norte Hospital in Mexico that includes 800 records and 141 indicators such as age, weight, glucose, blood pressure rate, and clinical symptoms. Distribution of the collected records is very unbalanced on the different types of heart disease, where 17% of records have hypertensive heart disease, 16% of records have ischemic heart disease, 7% of records have mixed heart disease, and 8% of records have valvular heart disease. Herein, we propose an ensemble-learning framework of different neural network models, and a method of aggregating random under-sampling. To improve the performance of the classification algorithms, we implement a data preprocessing step with features selection. Experiments were conducted with unidirectional and bidirectional neural network models and results showed that an ensemble classifier with a BiLSTM or BiGRU model with a CNN model had the best classification performance with accuracy and F1-score between 91% and 96% for the different types of heart disease. These results are competitive and promising for heart disease dataset. We showed that ensemble-learning framework based on deep models could overcome the problem of classifying an unbalanced heart disease dataset. Our proposed framework can lead to highly accurate models that are adapted for clinical real data and diagnosis use.

show abstract

Section: Introductionmentioning

confidence: 99%

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Diverse applications have been developed for diabetes (Puri, Kumar, Le, Jagdev, & Sachdeva, 2020), heart disease (Khan, 2020), hypertension (Sood & Mahajan, 2018), Alzheimer (Varatharajan, Manogaran, Priyan, & Sundarasekar, 2018), epileptical patient monitoring (Gupta, Chakraborty, & Gupta, 2019), and so on.…”

Section: Literature Reviewmentioning

confidence: 99%

A semantic‐enabled and context‐aware monitoring system for the internet of medical things

et al. 2020

View full text Add to dashboard Cite

The emergence of the Internet of Things (IoT) in the medical field has led to the massive deployment of a myriad of medical connected objects (MCOs). These MCOs are being developed and implemented for remote healthcare monitoring purposes including elderly patients with chronic diseases, pregnant women, and patients with disabilities. Accordingly, different associated challenges are emerging and include the heterogeneity of the gathered health data from these MCOs with ever‐changing contexts. These contexts are relative to the continuous change of constraints and requirements of the MCOs deployment (time, location, state). Other contexts are related to the patient (medical record, state, age, sex, etc.) that should be taken into account to ensure a more precise and appropriate treatment of the patient. These challenges are difficult to address due to the absence of a reference model for describing the health data and their sources and linking these data with their contexts. This article addresses this problem and introduces a semantic‐based context‐aware system (IoT Medicare system) for patient monitoring with MCOs. This system is based on a core domain ontology (HealthIoT‐O), that is, designed to describe the semantic of heterogeneous MCOs and their data. Moreover, an efficient interpretation and management of this knowledge in diverse contexts are ensured through SWRL rules such as the verification of the proper functioning of the MCOs and the analysis of the health data for diagnosis and treatment purposes. A case study of gestational diabetes disease management is proposed to evaluate the effectiveness of the implemented IoT Medicare system. An evaluation phase is provided and focuses on the quality of the elaborated semantic model and the performance of the system.

show abstract

“…Thus, the output layer transfers its optimal output to the consecutive or successive layer. 30 The steps involved in the ADNN optimization approach is delineated in the following section.…”

Section: Adcnn Modelmentioning

confidence: 99%

“…In this section, the data that are collected from numerous sensors are further classified into three different groups namely normal, sensitive, and critical. 2,12,20,30 Tables 1-5 describe the categorized results based on the above three parameters. The details regarding the general data of the patients including Identification number, gender, age, and locality are mentioned in Table 1.…”

Section: Datasetsmentioning

confidence: 99%

Adaptive deep convolutional neural network‐based secure integration of fog to cloud supported Internet of Things for health monitoring system

Revathi¹,

Arumugam

2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In recent years, the healthcare monitoring system plays a significant role in providing early intervention for the people who are under risk. Several advanced technologies including the Internet of Things (IoT) are becoming accessible nowadays due to its high level and ubiquitous monitoring. The IoT also enables a structured and competent technique in handling the healthcare of the patients based on remote patient monitoring and mobile health. In addition to this, the deep learning approaches are employed in health‐based applications so as to achieve promising and satisfactory performances for a sizeable amount of data. While monitoring the health condition of the patients, there occur delays in data transferring to the cloud. So, to overcome such shortcomings, the proposed approach of this paper utilizes four different phases including data acquisition phase (DAP), fog to cloud phase (FCP), decision‐making phase (DMP), and execution phase (EP) in transferring the data to the cloud via the fog layer. The initial phase or DAP phase comprises of data storage and collection. The second phase or the FCP phase comprises of two different types of layers namely fog layer and the cloud layer along with that, secure integration of FCP is described. The third phase or the DMP phase involves feture extraction and classification. Here, Adaptive Deep Convolution Neural Network along with the Levy Flightbased Grey Wolf Optimization (LFGWO) are employed in the classification process to obtain the best optimal solution. The final phase or the EP phase provides notification or information to the doctor or the practitioner soon after the detection of any abnormality case. The experimental results are made by comparing various approaches with the proposed approach and the analysis reveals that the proposed approach provides better results with high accuracy, efficiency, response time with less computational cost in healthcare monitoring applications.

show abstract

An IoT Framework for Heart Disease Prediction Based on MDCNN Classifier

Cited by 243 publications

References 38 publications

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

A semantic‐enabled and context‐aware monitoring system for the internet of medical things

Adaptive deep convolutional neural network‐based secure integration of fog to cloud supported Internet of Things for health monitoring system

Contact Info

Product

Resources

About