Search

Abstract Deep learning is a highly significant technology in clinical treatment and diagnostics nowadays. Convolutional Neural Network (CNN) is a new idea in deep learning that is being used in the area of computer vision. The COVID-19 detection is the subject of our medical study. Researchers attempted to increase the detection accuracy but at the cost of high model complexity. In this paper, we desire to achieve better accuracy with little training space and time so that this model easily deployed in edge devices. In this paper, a new CNN design is proposed that has three stages: pre-processing, which removes the black padding on the side initially; convolution, which employs filter banks; and feature extraction, which makes use of deep convolutional layers with skip connections. In order to train the model, chest X-ray images are partitioned into three sets: learning(0.7), validation(0.1), and testing(0.2). The models are then evaluated using the test and training data. The LMNet, CoroNet, CVDNet, and Deep GRU-CNN models are the other four models used in the same experiment. The propose model achieved 99.47% & 98.91% accuracy on training and testing respectively. Additionally, it achieved 97.54%, 98.19%, 99.49%, and 97.86% scores for precision, recall, specificity, and f1-score respectively. The proposed model obtained nearly equivalent accuracy and other similar metrics when compared with other models but greatly reduced the model complexity. Moreover, it is found that proposed model is less prone to over fitting as compared to other models.

Introduction: Chronic Kidney Disease (CKD) is one of the fastest-growing causes of death worldwide. Monitoring biochemical parameters such as liver function tests, kidney function tests, and lipid profiles is crucial for early identification of health complications, prevention, and prompt management in CKD patients. Aim: To investigate the association of sociodemographic factors and serum biochemical indicators with Glomerular Filtration Rate (GFR) among CKD patients in rural Odisha, India. Materials and Methods: A cross-sectional study was conducted in a rural cohort of the Model Rural Health Research Unit (MRHRU) established in Cuttack district, Odisha, India, from March 2021 to April 2021. A total of 530 registered CKD patients were enrolled in the study. Sociodemographic data and blood samples were collected for lipid profile, kidney function, and liver function analysis. The data were analysed using STATA 15.1 and RStudio 2021.09.0+351. Results: The mean age of the study participants was 51.2±14.1 years, with 330 (62.26%) being male. A total of 74% of the participants showed abnormal Estimated Glomerular Filtration Rate (eGFR). Abnormal eGFR was found to be more common among the older age group (>45 years), those who were literate, and those in private jobs, compared to their counterparts. Both lipid profile and liver function abnormalities were significantly associated with individuals having normal eGFR. Conclusion: The positive association of eGFR with lipid profile and liver function enzymes highlights the importance of regular screening of these parameters among CKD patients for early prevention and control of future complications.

Abstract Physical activity and mental well-being play an important role in reducing the risk of various diseases and in promoting independence among older adults. Appropriate physical activity, including yoga and mindfulness practices, can help rectify the loss of independence due to aging and have a positive influence on physical health and functional activities. This study assessed rural–urban differences in yoga and mindfulness practices and their associated factors among middle-aged and older Indian adults. The total sample size considered for the current analysis was 72,250 middle-aged and older adults (aged ≥ 45 years). Bivariate and multivariable logistic regression analyses were used to estimate the prevalence of yoga and mindfulness practices and examine the associations of selected variables with yoga and mindfulness practices among the participants. Further, we used the Fairley decomposition technique to determine the factors contributing to rural–urban differences in the prevalence of yoga and mindfulness practices among middle-aged and older adults. More than 9% of middle-aged and older adults in rural areas and 14% in urban areas reported practicing yoga and mindfulness activities more than once per week. Adults aged ≥ 65 years were more likely to practice yoga and mindfulness activities than those who age 45–54 years were. Those with an education of ten years and above were 2.3 and 2.1 times higher likely to practice yoga in rural (AOR: 2.28; CI: 2.07–2.52) and urban (AOR: 2.13; CI: 1.91–2.37) areas compared to their uneducated peers, respectively. The largest contributors in diminishing the gap in yoga practice among participants were education (44.2%), caste (2.5%), chronic diseases such as hypertension (4.53%), diabetes (1.71%), high cholesterol (3.08%), self-reported pain (5.76%), and difficulties in instrumental activities of daily living (1.22%). The findings suggest that middle-aged and older adults in urban areas practice yoga and mindfulness activities more than their peers in rural areas do. Education level, household characteristics, and health outcomes such as chronic conditions, pain, and functional difficulties explain the observed differences in yoga and mindfulness practices across rural and urban areas. Age-appropriate healthy practices such as yoga and mindfulness should be encouraged to enhance the physical and mental well-being of middle-aged and older adults, especially in rural areas.

Deep learning is a very important technique in clinical diagnosis and therapy in the present world. Convolutional Neural Network (CNN) is a recent development in deep learning that is used in computer vision. Our medical investigation focuses on the identification of brain tumour. To improve the brain tumour classification performance a Balanced binary Tree CNN (BT-CNN) which is framed in a binary tree-like structure is proposed. It has a two distinct modules-the convolution and the depthwise separable convolution group. The usage of convolution group achieves lower time and higher memory, while the opposite is true for the depthwise separable convolution group. This balanced binarty tree inspired CNN balances both the groups to achieve maximum performance in terms of time and space. The proposed model along with state-of-the-art models like CNN-KNN and models proposed by Musallam et al., Saikat et al., and Amin et al. are experimented on public datasets. Before we feed the data into model the images are pre-processed using CLAHE, denoising, cropping, and scaling. The pre-processed dataset is partitioned into training and testing datasets as per 5 fold cross validation. The proposed model is trained and compared its perforarmance with state-of-the-art models like CNN-KNN and models proposed by Musallam et al., Saikat et al., and Amin et al. The proposed model reported average training accuracy of 99.61% compared to other models. The proposed model achieved 96.06% test accuracy where as other models achieved 68.86%, 85.8%, 86.88%, and 90.41% respectively. Further, the proposed model obtained lowest standard deviation on training and test accuracies across all folds, making it invariable to dataset.

Abstract Medical images such as CT and X-ray have been widely used for the detection of several chest infections and lung diseases. However, these images are susceptible to different types of noise, and it is hard to remove these noises due to their complex distribution. The presence of such noise significantly deteriorates the quality of the images and significantly affects the diagnosis performance. Hence, the design of an effective de-noising technique is highly essential to remove the noise from chest CT and X-ray images prior to further processing. Deep learning methods, mainly, CNN have shown tremendous progress on de-noising tasks. However, existing CNN based models estimate the noise from the final layers, which may not carry adequate details of the image. To tackle this issue, in this paper a deep multi-level semantic fusion network is proposed, called DMF-Net for the removal of noise from chest CT and X-ray images. The DMF-Net mainly comprises of a dilated convolutional feature extraction block, a cascaded feature learning block (CFLB) and a noise fusion block (NFB) followed by a prominent feature extraction block. The CFLB cascades the features from different levels (convolutional layers) which are later fed to NFB to attain correct noise prediction. Finally, the Prominent Feature Extraction Block(PFEB) produces the clean image. To validate the proposed de-noising technique, a separate and a mixed dataset containing high-resolution CT and X-ray images with specific and blind noise are used. Experimental results indicate the effectiveness of the DMF-Net compared to other state-of-the-art methods in the context of peak signal-to-noise ratio (PSNR) and structural similarity measurement (SSIM) while drastically cutting down on the processing power needed.

As a huge number of satellites revolve around the earth, a great probability exists to observe and determine the change phenomena on the earth through the analysis of satellite images on a real-time basis. Therefore, classifying satellite images plays strong assistance in remote sensing communities for predicting tropical cyclones. In this article, a classification approach is proposed using Deep Convolutional Neural Network (DCNN), comprising numerous layers, which extract the features through a downsampling process for classifying satellite cloud images. DCNN is trained marvelously on cloud images with an impressive amount of prediction accuracy. Delivery time decreases for testing images, whereas prediction accuracy increases using an appropriate deep convolutional network with a huge number of training dataset instances. The satellite images are taken from the Meteorological & Oceanographic Satellite Data Archival Centre, the organization is responsible for availing satellite cloud images of India and its subcontinent. The proposed cloud image classification shows 94% prediction accuracy with the DCNN framework.

Objectives: The present study was carried out to evaluate diagnostic accuracy of ultrasound (US) in delineating various rotator cuff and associated non rotator cuff pathologies (RCPs) of shoulder joint compared to Magnetic Resonance Imaging (MRI). Methods: Fifty consecutive symptomatic subjects in age-group 18-75 years (mean ±SD: 56.0±13.6 years; 39-male, 11-female) were evaluated. US performer and MRI reporting radiologists were blinded to results of each-other. The sensitivity, specificity, and accuracy of US was measured for diagnosing various musculo-tendinous pathologies of shoulder against MRI gold standard. Results: MRI detected RCPs in all subjects while US was abnormal in 46(92%) cases. Supraspinatus was the most frequently affected tendon. Remarkably, 28% patient had polytendon abnormalities. US showed sensitivity of 84% and specificity of 87.5% for tendinosis; sensitivity of 78.1% and specificity of 94.4% for partial thickness tear (PTT) and 100% sensitivity and specificity for diagnosing full thickness tear. However, sensitivity of US for diagnosing PTT of infraspinatus tendon, subscapularis tendinosis and teres-minor atrophy was low. US had high specificity for diagnosing non-RCPs but sensitivity was low. Conclusions: A normal shoulder US may not rule out with certainty some rotator cuff and associated non-rotator cuff abnormalities. It is suggested to search for polytendon abnormalities which may be missed.

IntroductionChronic kidney disease (CKD) is mostly asymptomatic until reaching an advanced stage. Although conditions such as hypertension and diabetes can cause it, CKD can itself lead to secondary hypertension and cardiovascular disease (CVD). Understanding the types and prevalence of associated chronic conditions among CKD patient could help improve screening for early detection and case management.MethodsA cross sectional study of 252 CKD patients in Cuttack, Odisha (from the last 4 years CKD data base) was telephonically carried out using a validated Multimorbidity Assessment Questionnaire for Primary Care (MAQ-PC) tool with the help of an android Open Data Kit (ODK). Univariate descriptive analysis was done to determine the socio-demographic distribution of CKD patients. A Cramer’s heat map was generated for showing Cramer’s coefficient value of association of each diseases.ResultsThe mean age of participants was 54.11 (±11.5) years and 83.7% were male. Among the participants, 92.9% had chronic conditions (24.2% with one, 26.2% with two and 42.5% with three or more chronic conditions). Most prevalent chronic conditions were hypertension (48.4%), peptic ulcer disease (29.4%), osteoarthritis (27.8%) and diabetes (13.1%). Hypertension and osteoarthritis were found to be most commonly associated (Cramer’s V coefficient = 0.3).ConclusionIncreased vulnerability to chronic conditions among CKD patients make them at higher risk for mortality and compromised quality of life. Regular screening of CKD patient for other chronic conditions (hypertension, diabetes, peptic ulcer disease, osteoarthritis and heart diseases) would help in detecting them early and undertake prompt management. The existing national program could be leveraged to achieve this.

BackgroundChronic kidney disease (CKD), associated with other chronic conditions affects the physical, behavioral, and psychological aspects of an individual, leading to poor self-rated health. Hence, we aimed to assess the factors associated with poor self-rated health (SRH) in CKD patients. Additionally, we assessed their health care utilization.MethodsThis is an observational study consisting of 527 CKD patients from Longitudinal Aging Study in India (LASI), 2017-2018. A descriptive statistic computed prevalence. Regression analysis assessed the association between poor SRH and socio-demographic variables presented as adjusted odds ratio with a confidence interval of 95%. Health care utilization among CKD patients was graphically presented.ResultsAround 64% of CKD patients had poor SRH. Aged 75 years and above (AOR=1.8, 95% CI= 0.5-6.8), rural residents (AOR= AOR 1.8, 95% CI =1.0 -3.1) and those with other chronic conditions (AOR=5.1, 95% CI= 2.3-11.0) were associated with poor SRH. Overall 79% of the CKD patients availed health care facility, most (44.8%) of those visit private facility.ConclusionWe observed older adults, females, rural residents, and having other chronic conditions were associated with poor SRH among CKD patients which highlights the need for equitable and strengthened health care system. There is an urgent need to provide accessible, affordable and quality healthcare services for these individuals so as to maintain continuity of care.

Plain language summary Contraceptive discontinuation is major issue of family planning of India. Without getting proper knowledge of modern spacing method, women facing serious health related issues so that they tend to discontinue their family planning method. We examine the spatial heterogeneity of discontinuation of modern spacing method in 640 district of India. Using secondary data of NFHS-4 (2015–16), we calculated 12-month discontinuation rate of any method and any modern spacing method by reason of discontinuation, also we presented discontinuation pattern by regions of India. To measure the spill over effect and associated factor of discontinuation of modern spacing method, we used OLS model and estimated Impact result. The findings of our study conveys that desire to become pregnant is the leading cause of discontinuation for both any method and any modern spacing method (12.43%), followed by other fertility related reasons and methods relates reason’s (4.40%). Method failure, side effect of method and method related reason together accounts 12% of contraceptive discontinuation in India. Very low use of modern spacing method of districts should be given more attention for policy maker and planner to increase the use of modern spacing method. The districts of high discontinuation of modern spacing method need programmatic intervention. More attention for counselling to client, health worker outreach to user and better quality care services will stimulate non-user of contraception.

Small changes in retinal blood vessels may produce different pathological disorders which may further cause blindness. Therefore, accurate extraction of vasculature map of retinal fundus image has become a challenging task for analysis of different pathologies. The present study offers an unsupervised method for extraction of vasculature map from retinal fundus images. This paper presents the methodology for evolution of vessels using Modified Pixel Level Snake (MPLS) algorithm based on Black Top-Hat (BTH) transformation. In the proposed method, initially bimodal masking is used for extraction of the mask of the retinal fundus image. Then adaptive segmentation and global thresholding is applied on masked image to find the initial contour image. Finally, MPLS is used for evolution of contour in all four cardinal directions using external, internal and balloon potential. This proposed work is implemented using MATLAB software. DRIVE and STARE databases are used for checking the performance of the system. In the proposed work, various performance metrics such as sensitivity, specificity and accuracy are evaluated. The average sensitivity of 76.96%, average specificity of 98.34% and average accuracy of 96.30% is achieved for DRIVE database. This technique can also segment vessels of pathological images accurately; reaching the average sensitivity of 70.80%, average specificity of 96.40% and average accuracy of 94.41%. The present study provides a simple and accurate method for the detection of vasculature map for normal fundus images as well as pathological images. It can be helpful for the assessment of various retinal vascular attributes like length, diameter, width, tortuosity and branching angle.

In this paper, an adaptive depth and heading control of an autonomous underwater vehicle using the concept of an adaptive neuro-fuzzy inference system (ANFIS) is designed. The autonomous underwater vehicle dynamics have six degrees of freedom, which are highly nonlinear and time-varying. It is affected by environmental effects such as ocean currents and tidal waves. Due to nonlinear dynamics designing, a stable controller in an autonomous underwater vehicle is a difficult end to achieve. Fuzzy logic and neural network control blocks make up the proposed control design to control the depth and heading angle of autonomous underwater vehicle. The neural network is trained using the back-propagation algorithm. In the presence of noise and parameter variation, the proposed adaptive controller’s performance is compared with that of the self-tuning fuzzy-PID and fuzzy logic controller. Simulations are conducted to obtain the performance of both controller models in terms of overshoot, and the rise time and the result of the proposed adaptive controller exhibit superior control performance and can eliminate the effect of uncertainty.

Walking (gait) irregularities and abnormalities are predictors and symptoms of disorder and disability. In the past, elaborate video (camera-based) systems, pressure mats, or a mix of the two has been used in clinical settings to monitor and evaluate gait. This article presents an artificial intelligence-based comprehensive investigation of ground reaction force (GRF) pattern to classify the healthy control and gait disorders using the large-scale ground reaction force. The used dataset comprised GRF measurements from different patients. The article includes machine learning- and deep learning-based models to classify healthy and gait disorder patients using ground reaction force. A deep learning-based architecture GaitRec-Net is proposed for this classification. The classification results were evaluated using various metrics, and each experiment was analysed using a fivefold cross-validation approach. Compared to machine learning classifiers, the proposed deep learning model is found better for feature extraction resulting in high accuracy of classification. As a result, the proposed framework presents a promising step in the direction of automatic categorization of abnormal gait pattern.

The research community has recently shown significant interest in designing automated systems to detect coronavirus disease 2019 (COVID-19) using deep learning approaches and chest radiography images. However, state-of-the-art deep learning techniques, especially convolutional neural networks (CNNs), demand more learnable parameters and memory. Therefore, they may not be suitable for real-time diagnosis. Thus, the design of a lightweight CNN model for fast and accurate COVID-19 detection is an urgent need. In this paper, a lightweight CNN model called LW-CORONet is proposed that comprises a sequence of convolution, rectified linear unit (ReLU), and pooling layers followed by two fully connected layers. The proposed model facilitates extracting meaningful features from the chest X-ray (CXR) images with only five learnable layers. The proposed model is evaluated using two larger CXR datasets (Dataset-1: 2250 images and Dataset-2: 15,999 images) and the classification accuracy obtained are 98.67% and 99.00% on Dataset-1 and 95.67% and 96.25% on Dataset-2 for multi-class and binary classification cases, respectively. The results are compared with four contemporary pre-trained CNN models as well as state-of-the-art models. The effect of several hyperparameters: different optimization techniques, batch size, and learning rate have also been investigated. The proposed model demands fewer parameters and requires less memory space. Hence, it is effective for COVID-19 detection and can be utilized as a supplementary tool to assist radiologists in their diagnosis.

Internet of Things (IoT) is one of the efflorescing technologies of recent years with splendid real-time applications in the fields of healthcare, agriculture, transportation, industry, and environmental monitoring. In addition to the dominant applications and services of IoT, many challenges exist. As there is a lack of standardization for IoT technologies, the architecture emerged as the foremost challenge. The salient issues in designing an IoT architecture encompass connectivity, data handling, heterogeneity, privacy, scalability, and security. The standard IoT architectures are the ETSI IoT Standard, the ITU-T IoT Reference Model, IoT-A Reference Model, Intel’s IoT Architecture, the Three-Layer Architecture, Middle-Based Architecture, Service-Oriented Architecture, Five-Layer Architecture, and IWF Architecture. In this paper, we have reviewed these architectures and concluded that IWF Architecture is most suitable for the effortless development of IoT applications because of its immediacy and depth of insight in dealing with IoT data. We carried out this review concerning smart healthcare as it is among the major industries that have been leaders and forerunners in IoT technologies. Motivated by this, we designed the novel Smart Healthcare Reference Architecture (SHRA) based on IWF Architecture. Finally, present the significance of smart healthcare during the COVID-19 pandemic. We have synthesized our findings in a systematic way for addressing the research questions on IoT challenges. To the best of our knowledge, our paper is the first to provide an exhaustive investigation on IoT architectural challenges with a use case in a smart healthcare system.

Background: The modern era of human society has seen the rise of a different variety of diseases. The mortality rate, therefore, increases without adequate care which consequently causes wealth loss. It has become a priority of humans to take care of health and wealth in a genuine way. Methods: In this article, the authors endeavored to design a hospital management system with secured data processing. The proposed approach consists of three different phases. In the first phase, a smart healthcare system is proposed for providing an effective health service, especially to patients with a brain tumor. An application is developed that is compatible with Android and Microsoft-based operating systems. Through this application, a patient can enter the system either in person or from a remote place. As a result, the patient data are secured with the hospital and the patient only. It consists of patient registration, diagnosis, pathology, admission, and an insurance service module. Secondly, deep-learning-based tumor detection from brain MRI and EEG signals is proposed. Lastly, a modified SHA-256 encryption algorithm is proposed for secured medical insurance data processing which will help detect the fraud happening in healthcare insurance services. Standard SHA-256 is an algorithm which is secured for short data. In this case, the security issue is enhanced with a long data encryption scheme. The algorithm is modified for the generation of a long key and its combination. This can be applicable for insurance data, and medical data for secured financial and disease-related data. Results: The deep-learning models provide highly accurate results that help in deciding whether the patient will be admitted or not. The details of the patient entered at the designed portal are encrypted in the form of a 256-bit hash value for secured data management.

Alzheimer’s disease (AD) is a degenerative condition of the brain that affects the memory and reasoning abilities of patients. Memory is steadily wiped out by this condition, which gradually affects the brain’s ability to think, recall, and form intentions. In order to properly identify this disease, a variety of manual imaging modalities including CT, MRI, PET, etc. are being used. These methods, however, are time-consuming and troublesome in the context of early diagnostics. This is why deep learning models have been devised that are less time-intensive, require less high-tech hardware or human interaction, continue to improve in performance, and are useful for the prediction of AD, which can also be verified by experimental results obtained by doctors in medical institutions or health care facilities. In this paper, we propose a hybrid-based AI-based model that includes the combination of both transfer learning (TL) and permutation-based machine learning (ML) voting classifier in terms of two basic phases. In the first phase of implementation, it comprises two TL-based models: namely, DenseNet-121 and Densenet-201 for features extraction, whereas in the second phase of implementation, it carries out three different ML classifiers like SVM, Naïve base and XGBoost for classification purposes. The final classifier outcomes are evaluated by means of permutations of the voting mechanism. The proposed model achieved accuracy of 91.75%, specificity of 96.5%, and an F1-score of 90.25. The dataset used for training was obtained from Kaggle and contains 6200 photos, including 896 images classified as mildly demented, 64 images classified as moderately demented, 3200 images classified as non-demented, and 1966 images classified as extremely mildly demented. The results show that the suggested model outperforms current state-of-the-art models. These models could be used to generate therapeutically viable methods for detecting AD in MRI images based on these results for clinical prospective.

Skin cancer is the most commonly diagnosed and reported malignancy worldwide. To reduce the death rate from cancer, it is essential to diagnose skin cancer at a benign stage as soon as possible. To save lives, an automated system that can detect skin cancer in its earliest stages is necessary. For the diagnosis of skin cancer, various researchers have performed tasks using deep learning and transfer learning models. However, the existing literature is limited in terms of its accuracy and its troublesome and time-consuming process. As a result, it is critical to design an automatic system that can deliver a fast judgment and considerably reduce mistakes in diagnosis. In this work, a deep learning-based model has been designed for the identification of skin cancer at benign and malignant stages using the concept of transfer learning approach. For this, a pre-trained VGG16 model is improved by adding one flatten layer, two dense layers with activation function (LeakyReLU) and another dense layer with activation function (sigmoid) to enhance the accuracy of this model. This proposed model is evaluated on a dataset obtained from Kaggle. The techniques of data augmentation are applied in order to enhance the random-ness among the input dataset for model stability. The proposed model has been validated by considering several useful hyper parameters such as different batch sizes of 8, 16, 32, 64, and 128; different epochs and optimizers. The proposed model is working best with an overall accuracy of 89.09% on 128 batch size with the Adam optimizer and 10 epochs and outperforms state-of-the-art techniques. This model will help dermatologists in the early diagnosis of skin cancers.

People use mHealth applications to help manage and keep track of their health conditions more effectively. With the increase of mHealth applications, it has become more difficult to choose the best applications that are user-friendly and provide user satisfaction. The best techniques for any decision-making challenge are multi-criteria decision-making (MCDM) methodologies. However, traditional MCDM methods cannot provide accurate results in complex situations. Currently, researchers are focusing on the use of hybrid MCDM methods to provide accurate decisions for complex problems. Thus, the authors in this paper proposed two hybrid MCDM methods, CODAS-FAHP and MOORA-FAHP, to assess the usability of the five most familiar mHealth applications that focus on type 2 diabetes mellitus (T2DM), based on ten criteria. The fuzzy Analytic Hierarchy Process (FAHP) is applied for efficient weight estimation by removing the vagueness and ambiguity of expert judgment. The CODAS and MOORA MCDM methods are used to rank the mHealth applications, depending on the usability parameter, and to select the best application. The resulting analysis shows that the ranking from both hybrid models is sufficiently consistent. To assess the proposed framework’s stability and validity, a sensitivity analysis was performed. It showed that the result is consistent with the proposed hybrid model.

Dermoscopy images can be classified more accurately if skin lesions or nodules are segmented. Because of their fuzzy borders, irregular boundaries, inter- and intra-class variances, and so on, nodule segmentation is a difficult task. For the segmentation of skin lesions from dermoscopic pictures, several algorithms have been developed. However, their accuracy lags well behind the industry standard. In this paper, a modified U-Net architecture is proposed by modifying the feature map’s dimension for an accurate and automatic segmentation of dermoscopic images. Apart from this, more kernels to the feature map allowed for a more precise extraction of the nodule. We evaluated the effectiveness of the proposed model by considering several hyper parameters such as epochs, batch size, and the types of optimizers, testing it with augmentation techniques implemented to enhance the amount of photos available in the PH2 dataset. The best performance achieved by the proposed model is with an Adam optimizer using a batch size of 8 and 75 epochs.

The recent developments in the IT world have brought several changes in the medical industry. This research work focuses on few mHealth applications that work on the management of type 2 diabetes mellitus (T2DM) by the patients on their own. Looking into the present doctor-to-patient ratio in our country (1:1700 as per a Times of India report in 2021), it is very essential to develop self-management mHealth applications. Thus, there is a need to ensure simple and user-friendly mHealth applications to improve customer satisfaction. The goal of this study is to assess and appraise the usability and effectiveness of existing T2DM-focused mHealth applications. TOPSIS, VIKOR, and PROMETHEE II are three multi-criteria decision-making (MCDM) approaches considered in the proposed work for the evaluation of the usability of five existing T2DM mHealth applications, which include Glucose Buddy, mySugr, Diabetes: M, Blood Glucose Tracker, and OneTouch Reveal. The methodology used in the research work is a questionnaire-based evaluation that focuses on certain attributes and sub-attributes, identified based on the features of mHealth applications. CRITIC methodology is used for obtaining the attribute weights, which give the priority of the attributes. The resulting analysis signifies our proposed research by ranking the mHealth applications based on usability and customer satisfaction.