Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Browser

Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Point-of-Care Diagnostics and Devices".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 18207

Share This Special Issue

Special Issue Editors

Dr. Venkatesan Rajinikanth

E-Mail Website
Guest Editor

M.E., Ph.D, Professor, Department of Electronics and Instrumentation Engg., St. Joseph's College of Engineering, Chennai, India
Interests: mathematical modelling; medical data assesment; machine learning; deep learning; heuristic algorithm based optimization

Prof. Dr. Hong Lin

E-Mail Website
Co-Guest Editor

Department of Computer Science and Engineering Technology, University of Houston-Downtown, Houston, TX, USA
Interests: brain signal evaluation; sleep EEG pattern detection; meditation signal evaluation; medical image analysis
Special Issues, Collections and Topics in MDPI journals

Dr. Snehalatha Umapathy

E-Mail Website
Co-Guest Editor

Department of Biomedical Engineering, SRM Institute of Science and Technology, Kattankulathur, Chennai 603203, Tamil Nadu, India
Interests: biosignal processing; medical image processing; thermal imaging; machine-learning; deep-learning

Special Issue Information

Dear Colleagues,

The advancement in smart wearable devices (SWD) has improved the patient monitoring process, and SWD integrated with artificial intelligence (AI) and medical cloud environment further reduced the burden in patient care system. The modern SWD supports the facilities, such as automatic monitoring, alert during abnormal condition, web-based monitoring, health-app integration and automatic patient condition recording to inspect the recovery rate. The integration of various modern schemes will support the handling of different health data with appropriate care, and this facility also supports the handling of the offline/online data coming out from the AI-integrated SWD. When the health data is integrated with medical-cloud, the doctor can monitor the condition from the remote location and provide necessary suggestions.

This Special Issue invites researchers, scientists and medical professionals to submit their innovative ideas and experimental works related to health condition monitoring using smart wearable devices, SWD data processing with machine-learning and deep-learning methods, recent developments in SWD design and implementation, and integration of SWD with AI and cloud for remote patient care. This Special Issue also welcomes clinical trials executed with SWD, AI and the medical-cloud, remote monitoring of SWD data and mobile-app development for the SWD and AI.

Topics of interest include:

Design and development of smart health devices for complete health diagnosis development of advanced wearable devices with cloud connectivity;
Advanced AI algorithms for automatic diagnosis of health data obtained from wearable-devices;
Integration of recent heuristic algorithms to optimize the collected healthcare data;
Pre-processing, post processing and registration of healthcare data;
Integration of AI and cloud for healthcare data processing and decision making;
Recent machine-learning and deep-learning approaches for healthcare data assessment;
Automating the Intensive Care Unit with smart wearable devices with self-monitoring facility;
Detection of EEG, EMG, ECG and other physiological conditions using smart wearable-devices and AI;
Recent advancements in AI schemes to support the individuals to have a healthier living environment.

Dr. Venkatesan Rajinkanth
Prof. Dr. Hong Lin
Dr. Snehalatha Umapathy
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

health condition
physiological signals
smart health band
machine learning
deep learning
medical cloud

Published Papers (7 papers)

Download All Papers

Research

Jump to: Review

12 pages, 2363 KiB

Open AccessArticle

Ultrasound Control of Cervical Regeneration after Large Loop Excision of the Transformation Zone: Results of an Innovative Measurement Technique

by Vincenzo Pinto, Miriam Dellino, Carla Mariaflavia Santarsiero, Gennaro Cormio, Vera Loizzi, Valentina Griseta, Antonella Vimercati, Gerardo Cazzato, Eliano Cascardi and Ettore Cicinelli

Diagnostics 2023, 13(4), 791; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13040791 - 20 Feb 2023

Cited by 2 | Viewed by 1619

Abstract

The objective of this research is to evaluate cervical regeneration after large loop excision of the transformation zone (LLETZ) through the identification of a new sonographic reference point at the level of the uterine margins. In the period March 2021–January 2022, a total of 42 patients affected by CIN 2–3 were treated with LLETZ at the University Hospital of Bari (Italy). Before performing LLETZ, cervical length and volume were measured with trans-vaginal 3D ultrasound. From the multiplanar images, the cervical volume was obtained using the Virtual Organ Computer-aided AnaLysis (VOCAL™) program with manual contour mode. The line that connects the points where the common trunk of the uterine arteries reaches the uterus splitting into the ascending major branch and the cervical branch was considered as the upper limit of the cervical canal. From the acquired 3D volume, the length and the volume of the cervix were measured between this line and the external uterine os. Immediately after LLETZ, the removed cone was measured using Vernier’s caliper, and before fixation in formalin, the volume of the excised tissue was evaluated by the fluid displacement technique based on the Archimedes principle. The proportion of excised cervical volume was 25.50 ± 17.43%. The volume and the height of the excised cone were 1.61 ± 0.82 mL and 9.65 ± 2.49 mm corresponding to 14.74 ± 11.91% and 36.26 ± 15.49% of baseline values, respectively. The volume and length of the residual cervix were also assessed using 3D ultrasound up to the sixth month after excision. At 6 weeks, about 50% of cases reported an unchanged or lower cervical volume compared to the baseline pre-LLETZ values. The average percentage of volume regeneration in examined patients was equal to 9.77 ± 55.33%. In the same period, the cervical length regeneration rate was 69.41 ± 14.8%. Three months after LLETZ, a volume regeneration rate of 41.36 ± 28.31% was found. For the length, an average regeneration rate of 82.48 ± 15.25% was calculated. Finally, at 6 months, the percentage of regeneration of the excised volume was 90.99 ± 34.91%. The regrowth percentage of the cervical length was 91.07 ± 8.03%. The cervix measurement technique that we have proposed has the advantage of identifying an unequivocal reference point in 3D cervical measurement. Ultrasound 3D evaluation could be useful in the clinical practice to evaluate the cervical tissue deficit and express the “potential of cervical regeneration” as well as provide the surgeon useful information about the cervical length. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

27 pages, 4379 KiB

Open AccessArticle

Ensemble Model for Diagnostic Classification of Alzheimer’s Disease Based on Brain Anatomical Magnetic Resonance Imaging

by Yusera Farooq Khan, Baijnath Kaushik, Chiranji Lal Chowdhary and Gautam Srivastava

Diagnostics 2022, 12(12), 3193; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12123193 - 16 Dec 2022

Cited by 16 | Viewed by 2253

Abstract

Alzheimer’s is one of the fast-growing diseases among people worldwide leading to brain atrophy. Neuroimaging reveals extensive information about the brain’s anatomy and enables the identification of diagnostic features. Artificial intelligence (AI) in neuroimaging has the potential to significantly enhance the treatment process for Alzheimer’s disease (AD). The objective of this study is two-fold: (1) to compare existing Machine Learning (ML) algorithms for the classification of AD. (2) To propose an effective ensemble-based model for the same and to perform its comparative analysis. In this study, data from the Alzheimer’s Diseases Neuroimaging Initiative (ADNI), an online repository, is utilized for experimentation consisting of 2125 neuroimages of Alzheimer’s disease (n = 975), mild cognitive impairment (n = 538) and cognitive normal (n = 612). For classification, the framework incorporates a Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (K-NN) followed by some variations of Support Vector Machine (SVM), such as SVM (RBF kernel), SVM (Polynomial Kernel), and SVM (Sigmoid kernel), as well as Gradient Boost (GB), Extreme Gradient Boosting (XGB) and Multi-layer Perceptron Neural Network (MLP-NN). Afterwards, an Ensemble Based Generic Kernel is presented where Master-Slave architecture is combined to attain better performance. The proposed model is an ensemble of Extreme Gradient Boosting, Decision Tree and SVM_Polynomial kernel (XGB + DT + SVM). At last, the proposed method is evaluated using cross-validation using statistical techniques along with other ML models. The presented ensemble model (XGB + DT + SVM) outperformed existing state-of-the-art algorithms with an accuracy of 89.77%. The efficiency of all the models was optimized using Grid-based tuning, and the results obtained after such process showed significant improvement. XGB + DT + SVM with optimized parameters outperformed all other models with an efficiency of 95.75%. The implication of the proposed ensemble-based learning approach clearly shows the best results compared to other ML models. This experimental comparative analysis improved understanding of the above-defined methods and enhanced their scope and significance in the early detection of Alzheimer’s disease. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

19 pages, 3573 KiB

Open AccessArticle

A Robust Framework for Data Generative and Heart Disease Prediction Based on Efficient Deep Learning Models

by Raniya R. Sarra, Ahmed M. Dinar, Mazin Abed Mohammed, Mohd Khanapi Abd Ghani and Marwan Ali Albahar

Diagnostics 2022, 12(12), 2899; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12122899 - 22 Nov 2022

Cited by 14 | Viewed by 2595

Abstract

Biomarkers including fasting blood sugar, heart rate, electrocardiogram (ECG), blood pressure, etc. are essential in the heart disease (HD) diagnosing. Using wearable sensors, these measures are collected and applied as inputs to a deep learning (DL) model for HD diagnosis. However, it is observed that model accuracy weakens when the data gathered are scarce or imbalanced. Therefore, this work proposes two DL-based frameworks, GAN-1D-CNN, and GAN-Bi-LSTM. These frameworks contain: (1) a generative adversarial network (GAN) and (2) a one-dimensional convolutional neural network (1D-CNN) or bi-directional long short-term memory (Bi-LSTM). The GAN model is utilized to augment the small and imbalanced dataset, which is the Cleveland dataset. The 1D-CNN and Bi-LSTM models are then trained using the enlarged dataset to diagnose HD. Unlike previous works, the proposed frameworks increase the dataset first to avoid the prediction bias caused by the limited data. The GAN-1D-CNN achieved 99.1% accuracy, specificity, sensitivity, F1-score, and 100% area under the curve (AUC). Similarly, the GAN-Bi-LSTM obtained 99.3% accuracy, 99.2% specificity, 99.3% sensitivity, 99.2% F1-score, and 100% AUC. Furthermore, time complexity of proposed frameworks is investigated with and without principal component analysis (PCA). The PCA method reduced prediction times for 61 samples using GAN-1D-CNN and GAN-Bi-LSTM to 68.8 and 74.8 ms, respectively. These results show that it is reliable to use our frameworks for augmenting limited data and predicting heart disease. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

18 pages, 2275 KiB

Open AccessArticle

A Fair Performance Comparison between Complex-Valued and Real-Valued Neural Networks for Disease Detection

by Mario Jojoa, Begonya Garcia-Zapirain and Winston Percybrooks

Diagnostics 2022, 12(8), 1893; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12081893 - 4 Aug 2022

Cited by 3 | Viewed by 1536

Abstract

Our aim is to contribute to the classification of anomalous patterns in biosignals using this novel approach. We specifically focus on melanoma and heart murmurs. We use a comparative study of two convolution networks in the Complex and Real numerical domains. The idea is to obtain a powerful approach for building portable systems for early disease detection. Two similar algorithmic structures were chosen so that there is no bias determined by the number of parameters to train. Three clinical data sets, ISIC2017, PH2, and Pascal, were used to carry out the experiments. Mean comparison hypothesis tests were performed to ensure statistical objectivity in the conclusions. In all cases, complex-valued networks presented a superior performance for the Precision, Recall, F1 Score, Accuracy, and Specificity metrics in the detection of associated anomalies. The best complex number-based classifier obtained in the Receiving Operating Characteristic (ROC) space presents a Euclidean distance of 0.26127 with respect to the ideal classifier, as opposed to the best real number-based classifier, whose Euclidean distance to the ideal is 0.36022 for the same task of melanoma detection. The 27.46% superiority in this metric, as in the others reported in this work, suggests that complex-valued networks have a greater ability to extract features for more efficient discrimination in the dataset. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

21 pages, 564 KiB

Open AccessArticle

A Novel Fuzzy Parameterized Fuzzy Hypersoft Set and Riesz Summability Approach Based Decision Support System for Diagnosis of Heart Diseases

by Atiqe Ur Rahman, Muhammad Saeed, Mazin Abed Mohammed, Mustafa Musa Jaber and Begonya Garcia-Zapirain

Diagnostics 2022, 12(7), 1546; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12071546 - 24 Jun 2022

Cited by 22 | Viewed by 1945

Abstract

Fuzzy parameterized fuzzy hypersoft set (

Δ

Fuzzy parameterized fuzzy hypersoft set (

Δ

-set) is more flexible and reliable model as it is capable of tackling features such as the assortment of attributes into their relevant subattributes and the determination of vague nature of parameters and their subparametric-valued tuples by employing the concept of fuzzy parameterization and multiargument approximations, respectively. The existing literature on medical diagnosis paid no attention to such features. Riesz Summability (a classical concept of mathematical analysis) is meant to cope with the sequential nature of data. This study aims to integrate these features collectively by using the concepts of fuzzy parameterized fuzzy hypersoft set (

Δ

-set) and Riesz Summability. After investigating some properties and aggregations of

Δ

-set, two novel decision-support algorithms are proposed for medical diagnostic decision-making by using the aggregations of

Δ

-set and Riesz mean technique. These algorithms are then validated using a case study based on real attributes and subattributes of the Cleveland dataset for heart-ailments-based diagnosis. The real values of attributes and subattributes are transformed into fuzzy values by using appropriate transformation criteria. It is proved that both algorithms yield the same and reliable results while considering hypersoft settings. In order to judge flexibility and reliability, the preferential aspects of the proposed study are assessed by its structural comparison with some related pre-developed structures. The proposed approach ensures that reliable results can be obtained by taking a smaller number of evaluating traits and their related subvalues-based tuples for the diagnosis of heart-related ailments. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

Review

Jump to: Research

10 pages, 1255 KiB

Open AccessReview

Challenges for Artificial Intelligence in Recognizing Mental Disorders

by Wen-Jing Yan, Qian-Nan Ruan and Ke Jiang

Diagnostics 2023, 13(1), 2; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics13010002 - 20 Dec 2022

Cited by 10 | Viewed by 3359

Abstract

Artificial Intelligence (AI) appears to be making important advances in the prediction and diagnosis of mental disorders. Researchers have used visual, acoustic, verbal, and physiological features to train models to predict or aid in the diagnosis, with some success. However, such systems are rarely applied in clinical practice, mainly because of the many challenges that currently exist. First, mental disorders such as depression are highly subjective, with complex symptoms, individual differences, and strong socio-cultural ties, meaning that their diagnosis requires comprehensive consideration. Second, there are many problems with the current samples, such as artificiality, poor ecological validity, small sample size, and mandatory category simplification. In addition, annotations may be too subjective to meet the requirements of professional clinicians. Moreover, multimodal information does not solve the current challenges, and within-group variations are greater than between-group characteristics, also posing significant challenges for recognition. In conclusion, current AI is still far from effectively recognizing mental disorders and cannot replace clinicians’ diagnoses in the near future. The real challenge for AI-based mental disorder diagnosis is not a technical one, nor is it wholly about data, but rather our overall understanding of mental disorders in general. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures

Figure 1

16 pages, 2233 KiB

Open AccessReview

Asynclitism and Its Ultrasonographic Rediscovery in Labor Room to Date: A Systematic Review

by Antonio Malvasi, Marina Vinciguerra, Bruno Lamanna, Eliano Cascardi, Gianluca Raffaello Damiani, Giuseppe Muzzupapa, Ioannis Kosmas, Renata Beck, Maddalena Falagario, Antonella Vimercati, Ettore Cicinelli, Giuseppe Trojano, Andrea Tinelli, Gerardo Cazzato and Miriam Dellino

Diagnostics 2022, 12(12), 2998; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12122998 - 30 Nov 2022

Cited by 3 | Viewed by 3736

Abstract

Asynclitism, the most feared malposition of the fetal head during labor, still represents to date an unresolved field of interest, remaining one of the most common causes of prolonged or obstructed labor, dystocia, assisted delivery, and cesarean section. Traditionally asynclitism is diagnosed by vaginal examination, which is, however, burdened by a high grade of bias. On the contrary, the recent scientific evidence highly suggests the use of intrapartum ultrasonography, which would be more accurate and reliable when compared to the vaginal examination for malposition assessment. The early detection and characterization of asynclitism by intrapartum ultrasound would become a valid tool for intrapartum evaluation. In this way, it will be possible for physicians to opt for the safest way of delivery according to an accurate definition of the fetal head position and station, avoiding unnecessary operative procedures and medication while improving fetal and maternal outcomes. This review re-evaluated the literature of the last 30 years on asynclitism, focusing on the progressive imposition of ultrasound as an intrapartum diagnostic tool. All the evidence emerging from the literature is presented and evaluated from our point of view, describing the most employed technique and considering the future implication of the progressive worldwide consolidation of asynclitism and ultrasound. Full article

(This article belongs to the Special Issue Health Diagnosis with Smart Wearable Devices and AI Driven Medical Cloud)

► Show Figures