Medical Healthcare Applications Research Articles

PSO-XnB: a proposed model for predicting hospital stay of CAD patients.

Coronary artery disease poses a significant challenge in decision-making when predicting the length of stay for a hospitalized patient. This study presents a predictive model-a Particle Swarm Optimized-Enhanced NeuroBoost-that combines the deep autoencoder with an eXtreme gradient boosting model optimized using particle swarm optimization. The model uses a fuzzy set of rules to categorize the length of stay into four distinct classes, followed by data preparation and preprocessing. In this study, the dimensionality of the data is reduced using deep neural autoencoders. The reconstructed data obtained from autoencoders is given as input to an eXtreme gradient boosting model. Finally, the model is tuned with particle swarm optimization to obtain optimal hyperparameters. With the proposed technique, the model achieved superior performance with an overall accuracy of 98.8% compared to traditional ensemble models and past research works. The model also scored highest in other metrics such as precision, recall, and particularly F1 scores for all categories of hospital stay. These scores validate the suitability of our proposed model in medical healthcare applications.

Heart Rate Monitoring using Arduino

Pulse rate sensor is utilised in our project to measure heartbeat with the help of fingers. Patient heart beat needs to be continuously checked. This project uses sensors to measure heart rate. These sensors are connected to lcd to analyse the conditions of a patient. This module is an Arduino based which uses microcontroller and sensors to monitor patients heart rate. It supports very low data rates for sensor and medical healthcare applications.

Antibacterial self-fused supramolecular polymer hydrogel for infected wound healing

Wound treatment is a huge challenge for healthcare systems, especially when the wound suffered infection. Therefore, it is essential to develop materials with antibacterial properties for wound repair. Herein, we integrated antimicrobial peptides with self-healing hydrogel for infectious wound treatment. The synthetic hydrogel was made by polymerizing N-acryloyl glycinamide (NAGA) monomers and doped with antimicrobial peptide Polymyxin E. Additionally, because of the bisamide structure of the side chains of the NAGA monomers, the hydrogen bond was formed and caused the supramolecular structure. The resulted hydrogel showed excellent self-healing property, biocompatibility, and antimicrobial property, which allowed it to be used as hydrogel dressing. In vivo experiment demonstrated that the hydrogel had the significant capability in promoting infectious wound healing. Therefore, this type of antibacterial self-healing supramolecular hydrogel is expected to serve as infectious wound dressing for medical healthcare applications.

A Novel Adaptive Battery-Aware Algorithm for Data Transmission in IoT-Based Healthcare Applications

The internet of things (IoT) comprises various sensor nodes for monitoring physiological signals, for instance, electrocardiogram (ECG), electroencephalogram (EEG), blood pressure, and temperature, etc., with various emerging technologies such as Wi-Fi, Bluetooth and cellular networks. The IoT for medical healthcare applications forms the internet of medical things (IoMT), which comprises multiple resource-restricted wearable devices for health monitoring due to heterogeneous technological trends. The main challenge for IoMT is the energy drain and battery charge consumption in the tiny sensor devices. The non-linear behavior of the battery uses less charge; additionally, an idle time is introduced for optimizing the charge and battery lifetime, and hence the efficient recovery mechanism. The contribution of this paper is three-fold. First, a novel adaptive battery-aware algorithm (ABA) is proposed, which utilizes the charges up to its maximum limit and recovers those charges that remain unused. The proposed ABA adopts this recovery effect for enhancing energy efficiency, battery lifetime and throughput. Secondly, we propose a novel framework for IoMT based pervasive healthcare. Thirdly, we test and implement the proposed ABA and framework in a hardware platform for energy efficiency and longer battery lifetime in the IoMT. Furthermore, the transition of states is modeled by the deterministic mealy finite state machine. The Convex optimization tool in MATLAB is adopted and the proposed ABA is compared with other conventional methods such as battery recovery lifetime enhancement (BRLE). Finally, the proposed ABA enhances the energy efficiency, battery lifetime, and reliability for intelligent pervasive healthcare.

Gaussian Noise Removal in an Image using Fast Guided Filter and its Method Noise Thresholding in Medical Healthcare Application.

A new denoising algorithm using Fast Guided Filter and Discrete Wavelet Transform is proposed to remove Gaussian noise in an image. The Fast Guided Filter removes some part of the details in addition to noise. These details are estimated accurately and combined with the filtered image to get back the final denoised image. The proposed algorithm is compared with other existing filtering techniques such as Wiener filter, Non Local means filter and bilateral filter and it is observed that the performance of this algorithm is superior compared to the above mentioned Gaussian noise removal techniques. The resultant image obtained from this method is very good both from subjective and objective point of view. This algorithm has less computational complexity and preserves edges and other detail information in an image.

An adaptive QoS computation for medical data processing in intelligent healthcare applications

Efficient computation of quality of service (QoS) during medical data processing through intelligent measurement methods is one of the mandatory requirements of the medial healthcare world. However, emergency medical services often involve transmission of critical data, thus having stringent requirements for network quality of service (QoS). This paper contributes in three distinct ways. First, it proposes the novel adaptive QoS computation algorithm (AQCA) for fair and efficient monitoring of the performance indicators, i.e., transmission power, duty cycle and route selection during medical data processing in healthcare applications. Second, framework of QoS computation in medical applications is proposed at physical, medium access control (MAC) and network layers. Third, QoS computation mechanism with proposed AQCA and quality of experience (QoE) is developed. Besides, proper examination of QoS computation for medical healthcare application is evaluated with 4–10 inches large-screen user terminal (UT) devices (for example, LCD panel size, resolution, etc.). These devices are based on high visualization, battery lifetime and power optimization for ECG service in emergency condition. These UT devices are used to achieve highest level of satisfaction in terms, i.e., less power drain, extended battery lifetime and optimal route selection. QoS parameters with estimation of QoE perception identify the degree of influence of each QoS parameters on the medical data processing is analyzed. The experimental results indicate that QoS is computed at physical, MAC and network layers with transmission power (− 15 dBm), delay (100 ms), jitter (40 ms), throughput (200 Bytes), duty cycle (10%) and route selection (optimal). Thus it can be said that proposed AQCA is the potential candidate for QoS computation than Baseline for medical healthcare applications.

Mobile edge computing based QoS optimization in medical healthcare applications

Emerging trends in mobile edge computing for developing the efficient healthcare application such as, remote monitoring of the patients with central electronics clouds (e-Clouds) and their increasing voluminous multimedia have caught the attention of everyone in industry and academia. So, clear visualization, big sensing level, and better quality of service (QoS) is the foremost priority. This paper proposes the window-based Rate Control Algorithm (w-RCA) to optimize the medical quality of service (m-QoS) in the mobile edge computing based healthcare by considering the network parameters for instance, peak-to-mean ratio (PMR), standard deviation (Std.dev), delay and jitter during 8 min medical video stream named “Navigation to the Uterine Horn, transection of the horn and re-anastomosis’ transmission over 5 G networks. The performance of the proposed w-RCA is evaluated and compared with the conventional battery smoothing algorithm (BSA) and Baseline by using MPEG-4 encoder for optimizing m-QoS at the source or the server side. The experimental results demonstrate that the w-RCA outperforms the BSA and Baseline by optimizing QoS in remote healthcare application i.e., Tele-surgery. Besides, it is observed and analyzed that w-RCA produces better and effective results at small buffer and window sizes unlike BSA and Baseline by adopting large buffer size during QoS optimization.

Convergence of IoT and product lifecycle management in medical health care

Emerging trends in Internet of Medical Things (IoMT) or Medical Internet of Things (MIoT), and miniaturized devices with have entirely changed the landscape of the every corner. Main challenges that heterogeneous sensor-enabled devices are facing during the connectivity and convergence with other domains are, first, the information/knowledge sharing and collaboration between several communicating parties such as, from manufacturing engineer to medical expert, then from hospitals/healthcare centers to patients during disease diagnosis and treatment. Second, battery lifecycle and energy management of wearable/portable devices. This paper solves first problem by integrating IoMT with Product Lifecycle Management (PLM), to regulate the information transfer from one entity to another and between devices in an efficient and accurate way. While, second issue is resolved by proposing two, battery recovery-based algorithm (BRA), and joint energy harvesting and duty-cycle optimization-based (JEHDO) algorithm for managing the battery lifecycle and energy of the resource-constrained tiny wearable devices, respectively. Besides, a novel joint IoMT and PLM based framework is proposed for medical healthcare applications. Experimental results reveal that BRA and JEHDO are battery-efficient and energy-efficient respectively.

Cluster-based real-time analysis of mobile healthcare application for prediction of physiological data

In recent years, interest in medical healthcare applications using Wireless Body Sensor Network (WBSN) has grown considerably. A WBSN can be used to develop a patient monitoring system, which offers flexibility and mobility to monitor patient’s health condition. When the value of the physiological signal reaches threshold, the system raises an alarm. However, earlier patient monitoring systems may not be accurate all the time and do not support mobility which lead to false positive prediction. This paper presents, a data mining algorithm to predict the health risk of the patient in real time with 96% accuracy using historical medical records. Proposed Online Distribution Resource Aware (ODRA) algorithm gives accurate condition of the patients so as to inform the status to physician whenever immediate attention is required. The worst health conditions are predicted by risk components which are extracted using signal windows of the vital signal. The proposed algorithm of real-time patient monitoring system uses online signals to monitor the patient’s physiological data with increased mobility even in the ubiquitous environment. HR, SpO2, and Blood Pressure signals of 64 patients with different illness have been tested and verified. Results confirmed that the proposed algorithm gives better accuracy and reduce False Positive Rate (FPR) for predicting risk status of the patient compared to Resource Aware High-Quality Clustering (RAH).

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification.

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients’ benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

IsMAC: An Adaptive and Energy-Efficient MAC Protocol Based on Multi-Channel Communication for Wireless Body Area Networks

Recently, the use of wireless body area networks (WBAN) has been increasing rapidly in medical healthcare applications. WBANs consist of smart nodes that can be used to sense and transmit vital data such as heart rate, temperature and ECG from a human body to a medical centre. WBANs depend on limited resources such as energy and bandwidth. In order to utilise these resources efficiently, a very well organized medium access control (MAC) protocol must be considered. In this paper, a new, adaptive and energy-efficient MAC protocol, entitled isMAC, is proposed for WBANs. The proposed MAC is based on multi-channel communication and aims to prolong the network lifetime by effectively employing (i) a collision prevention mechanism, (ii) a coordinator node (WCN) selection algorithm and (iii) a transmission power adjustment approach. The isMAC protocol has been developed and modelled, by using OPNET Modeler simulation software. It is based on a networking scenario that requires especially high data rates such as ECG, for performance evaluation purposes. Packet delay, network throughput and energy consumption have been chosen as performance metrics. The comparison between the simulation results of isMAC and classical IEEE 802.15.4 (ZigBee) protocol shows that isMAC significantly outperforms IEEE 802.15.4 in terms of packet delay, throughput and energy consumption.

Online medical healthcare application for cancer disease prediction based on pattern matching and SVM classifier with MVC (PMSMVC) framework

A web service is used to provide the appropriate treatment for a patient suffering from cancer. This paper proposes a web service oriented medical healthcare application for the cancer disease prediction, based on Pattern Matching and SVM Classifier with MVC (PMSMVC) framework. The collected patient’s data are compiled using SQL YOG, a visual query designer and query formatter. A set of questions (pre-condition pattern) related to the cancer disease are designed, using the MY SQL API scheduler, and it is maintained in the database as well as the MVC framework. The designed set of questionnaires is given to the users through the web browser, and their answers are considered as the input pattern. The pattern matching method is used to match the input pattern and the pre-condition pattern. The SVM will classify whether the pattern has cancer or not. The performance of the proposed method is validated both quantitatively and qualitatively using performance metrics, such as sensitivity, accuracy and specificity.

Characterization of Wireless On-Body Channel Under Specific Action Scenarios at Sub-GHz Bands

Body area network is an emerging area of wireless communication for medical healthcare applications. This paper characterizes the narrowband wireless on-body channels under specific action scenarios by measurement at the three different sub-GHz frequencies of 444.5, 611, and 953 MHz, which are the candidate frequency bands of narrowband body area network systems with low data rates in IEEE 802.15.6 standard. The channel responses at ten different antenna positions were measured in an office room environment for the two dynamic action scenarios of “walking on the spot” (Action I) and “standing up/sitting down” (Action II). This paper provides generalized on-body channel models of Nakagami- $m$ and Weibull distributions for Actions I and II, respectively. Notably, this paper shows that the shadowing effect due to body movement is dominant over the multipath fading. The results were obtained by the statistical analyses of channel fading properties at three different frequencies including level crossing rate, average fade duration and channel dwelling time.