Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Browser

Advances in Biomedical Signal Processing in Health Care

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

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Biomedical Engineering".

Deadline for manuscript submissions: closed (10 May 2022) | Viewed by 18236

Share This Special Issue

Special Issue Editors

Prof. Dr. Dimitrios Dionisios Koutsouris

E-Mail Website
Guest Editor

Division of Information Transmission Systems and Material Technology, National Technical University of Athens, 10682 Athens, Greece
Interests: biomedical signal processing; clinical engineering; image processing
Special Issues, Collections and Topics in MDPI journals

Dr. Athanasios Anastasiou

E-Mail
Guest Editor

Biomedical Engineering Laboratory, School of Electrical Engineering, National Technical University of Athens, 10682 Athens, Greece
Interests: M-health; E-health; biomedical engineering; software engineering
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Nitrides, a few of which are known to occur in nature, have attracted huge and ever-increasing interest from scientists from broadly different scientific communities. They are a large class of compounds with a wide range of properties and neural applications. Even though nitride chemistry shares some similarities with that of oxides, the unfavorable electron affinity and high dissociation energy of nitrogen highlight the differences: they lead not only to comparably low thermal stabilities and small band gaps, but also to a completely new structural and redox chemistry, as well as physics. Solid solutions of nitrides and oxides allow precisely controlling properties, such as band gap sizes and band edge positions. Within the past few decades, nitride chemistry has emerged into a fruitful area of research, today covering widely different disciplines, such as synthetic and structural chemistry, physics, materials research and theoretical chemistry. The large variety of highly attractive combinations of properties, such as high magnetic moments, luminescence, ionic or electric conductivity, versatile redox and catalytic properties, excellent chemical stability and high hardness, to name only a few, provide innumerable possibilities for novel applications and devices. At the same time, the still-underexplored material class of nitrides, in general, offers a broad spectrum of opportunities for basic explorative chemistry, as well as new and exciting physics and property investigations. Some of the most recent developments in nitride chemistry are the following: a) emerging trends in multiparametric biomedical sensors based on nitride materials, b) decision support systems (DSSs) for medical diagnosis or the detection of disorders based on the feature extraction and classification of nitrides, and c) acoustic signal processing to incorporate techniques based on surface acoustic wave (SAW) devices with nitrides. In addition, nitride chemistry could take advantage of edge computing in the context of enhancing and extending cloud-computing capabilities. The focus of this Special Issue is on the latest advances made in nitride chemistry. These advances cover novel synthetic techniques, structure and property determination, and possible applications in all fields of chemistry, physics and beyond.

Prof. Dimitris Dionissios Koutsouris
Dr. Athanasios Anastasiou
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. Applied Sciences 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 2400 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

Multiparametric biomedical sensors
Feature extraction
Neural applications
Acoustic signal processing
Decision support system
Edge computing.

Published Papers (7 papers)

Download All Papers

Research

Jump to: Review

15 pages, 3363 KiB

Open AccessArticle

Very Short-Term Photoplethysmography-Based Heart Rate Variability for Continuous Autoregulation Assessment

by Po-Hsun Huang and Tzu-Chien Hsiao

Appl. Sci. 2022, 12(13), 6469; https://0-doi-org.brum.beds.ac.uk/10.3390/app12136469 - 25 Jun 2022

Cited by 1 | Viewed by 1257

Abstract

Background: Heart rate variability (HRV) has been widely applied for disease diagnosis. However, the 5 min signal length for HRV analysis is needed. Method: A signal processing procedure for very short-term photoplethysmography (PPG) signal for fever detection and autoregulation assessment was proposed. The Time-Shift Multiscale Entropy Analysis (TSME) was applied to instantaneous pulse rate time series (iPR) and normalized by the cumulative distribution function (CDF) of all scales to calculate novel indices. A total of 33 subjects were recruited for the study. Fifteen participants whose body temperatures were higher than 37.9 °C were served as the fever group. Others were served as the non-fever group. The total 15 s PPG signal with 200 sampling rates was used for iPR calculation. Result: The CDF value of entropy on the scale k = 19 (CDF(E(k = 19))) of iPR had the lowest p-value calculated by the Weltch t-test between two groups (p < 0.001). The Spearman correlation r between CDF(E(k = 19)) and body temperature is −0.757, 0.287, and −0.830 in all subjects, the non-fever group and the Fever group, respectively. The area under the curve, calculated from the receiver operating characteristic of CDF(E(k = 19)) of iPR is 0.915. Conclusion: The entropy of iPR is useful for detecting fever. Moreover, a short-term PPG signal is suitable to develop real-time applications, and multiscale entropy provides different scales of information for daily healthcare. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

20 pages, 4307 KiB

Open AccessArticle

Exploring the Utility of Anonymized EHR Datasets in Machine Learning Experiments in the Context of the MODELHealth Project

by Stavros Pitoglou, Arianna Filntisi, Athanasios Anastasiou, George K. Matsopoulos and Dimitrios Koutsouris

Appl. Sci. 2022, 12(12), 5942; https://0-doi-org.brum.beds.ac.uk/10.3390/app12125942 - 10 Jun 2022

Viewed by 1661

Abstract

The object of this paper was the application of machine learning to a clinical dataset that was anonymized using the Mondrian algorithm. (1) Background: The preservation of patient privacy is a necessity rising from the increasing digitization of health data; however, the effect of data anonymization on the performance of machine learning models remains to be explored. (2) Methods: The original EHR derived dataset was subjected to anonymization by applying the Mondrian algorithm for various k values and quasi identifier (QI) set attributes. The logistic regression, decision trees, k-nearest neighbors, Gaussian naive Bayes and support vector machine models were applied to the different dataset versions. (3) Results: The classifiers demonstrated different degrees of resilience to the anonymization, with the decision tree and the KNN models showing remarkably stable performance, as opposed to the Gaussian naïve Bayes model. The choice of the QI set attributes and the generalized information loss value played a more important role than the size of the QI set or the k value. (4) Conclusions: Data anonymization can reduce the performance of certain machine learning models, although the appropriate selection of classifier and parameter values can mitigate this effect. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

10 pages, 1649 KiB

Open AccessArticle

Efficacy of Two Toothpaste in Preventing Tooth Erosive Lesions Associated with Gastroesophageal Reflux Disease

by Francesco Saverio Ludovichetti, Giulia Zambon, Matteo Cimolai, Matteo Gallo, Anna Giulia Signoriello, Luca Pezzato, Rachele Bertolini and Sergio Mazzoleni

Appl. Sci. 2022, 12(3), 1023; https://0-doi-org.brum.beds.ac.uk/10.3390/app12031023 - 19 Jan 2022

Cited by 8 | Viewed by 2401

Abstract

Patients suffering from acid reflux due to endogenous causes are often affected by gastroesophageal reflux disease which, in the oral environment, causes lingual and palatal enamel erosion. As enamel does not have the intrinsic ability to repair itself, the application of alloplastic materials, such as toothpastes is suggestable. The aim of this “in vitro” study was to compare the effectiveness of two different toothpastes in preventing erosion due to gastroesophageal reflux disease. Six tooth elements from bovine jaws were prepared using a high-speed diamond bur and water irrigation. Acid attack simulation was carried out using a 15% HCl hydrochloric acid solution. After that, two different toothpastes with or without fluoride, were brushed at the sample surface using an electric toothbrush at standard position and force. SEM and profilometer analysis were performed. Statistically significant difference was found in average tooth surface roughness after using toothpaste with or without fluoride after the acid attack, as the former offered a greater remineralization. No difference was found in long-term prevention. Fluoridated toothpastes offer a greater degree of remineralization at a first acid attack, however, there is no difference in long-term prevention independently from the toothpaste type. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

11 pages, 540 KiB

Open AccessArticle

Reliability and Validity of the Ground Reaction Force Asymmetric Index at Seat-Off as a Measure of Lower Limb Functional Muscle Strength: A Preliminary Study

by Ae-Ryoung Kim, Dougho Park and Yang-Soo Lee

Appl. Sci. 2021, 11(14), 6527; https://0-doi-org.brum.beds.ac.uk/10.3390/app11146527 - 15 Jul 2021

Cited by 1 | Viewed by 1548

Abstract

This study examined the reliability of the newly developed ground reaction force asymmetry index (GRF AI) at seat-off using a low-cost force plate and the validity of this new test by comparing it with other muscle strength-measuring methods and walking speed. This study was a cross-sectional design in general hospital setting. A convenience sample of 47 community-dwelling adults aged ≥40 years was performed. GRF AI is the measurement value obtained by shifting the weight to the right and left while performing sit-to-stand (STS). GRF AI assessed using GRF data at seat-off during an STS test with maximal weight shift to the right and left side and repeated 4 weeks later. Hip and knee extensor strength were measured using hand-held dynamometry; hand grip strength and walking speed were measured using a standardized method. Intrasessional intrarater reliability of the right and left side at Sessions 1 and 2 were high (intraclass correlation coefficients [ICC] = 0.947 and 0.974; 0.931 and 0.970, respectively). In addition, the intersessional intrarater reliability of a single test trial (ICC = 0.911 and 0.930) and the mean of three test trials (ICC = 0.965 and 0.979) was also high. There was a low correlation between right-side GRF AI and right hand grip strength (r = 0.268) and between left-side GRF AI and left hand grip strength (r = 0.316). No significant correlations were found between the GRF AI and other parameters. Although the reliability of the GRF AI was high, the validity was poor. To be clinically useful, this test should be further refined by modifying the test protocol. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

16 pages, 3450 KiB

Open AccessArticle

Informative Biomarkers for Autism Spectrum Disorder Diagnosis in Functional Magnetic Resonance Imaging Data on the Default Mode Network

by Aikaterini S. Karampasi, Antonis D. Savva, Vasileios Ch. Korfiatis, Ioannis Kakkos and George K. Matsopoulos

Appl. Sci. 2021, 11(13), 6216; https://0-doi-org.brum.beds.ac.uk/10.3390/app11136216 - 05 Jul 2021

Cited by 7 | Viewed by 3668

Abstract

Effective detection of autism spectrum disorder (ASD) is a complicated procedure, due to the hundreds of parameters suggested to be implicated in its etiology. As such, machine learning methods have been consistently applied to facilitate diagnosis, although the scarcity of potent autism-related biomarkers is a bottleneck. More importantly, the variability of the imported attributes among different sites (e.g., acquisition parameters) and different individuals (e.g., demographics, movement, etc.) pose additional challenges, eluding adequate generalization and universal modeling. The present study focuses on a data-driven approach for the identification of efficacious biomarkers for the classification between typically developed (TD) and ASD individuals utilizing functional magnetic resonance imaging (fMRI) data on the default mode network (DMN) and non-physiological parameters. From the fMRI data, static and dynamic connectivity were calculated and fed to a feature selection and classification framework along with the demographic, acquisition and motion information to obtain the most prominent features in regard to autism discrimination. The acquired results provided high classification accuracy of 76.63%, while revealing static and dynamic connectivity as the most prominent indicators. Subsequent analysis illustrated the bilateral parahippocampal gyrus, right precuneus, midline frontal, and paracingulate as the most significant brain regions, in addition to an overall connectivity increment. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

22 pages, 3604 KiB

Open AccessArticle

VBM-Based Alzheimer’s Disease Detection from the Region of Interest of T1 MRI with Supportive Gaussian Smoothing and a Bayesian Regularized Neural Network

by Bijen Khagi, Kun Ho Lee, Kyu Yeong Choi, Jang Jae Lee, Goo-Rak Kwon and Hee-Deok Yang

Appl. Sci. 2021, 11(13), 6175; https://0-doi-org.brum.beds.ac.uk/10.3390/app11136175 - 02 Jul 2021

Cited by 6 | Viewed by 2549

Abstract

This paper presents an efficient computer-aided diagnosis (CAD) approach for the automatic detection of Alzheimer’s disease in patients’ T1 MRI scans using the voxel-based morphometry (VBM) analysis of the region of interest (ROI) in the brain. The idea is to generate a normal distribution of feature vectors from ROIs then later use for classification via Bayesian regularized neural network (BR-NN). The first dataset consists of the magnetic resonance imaging (MRI) of 74 Alzheimer’s disease (AD), 42 mild cognitive impairment (MCI), and 74 control normal (CN) from the ADNI¹ dataset. The other dataset consists of the MRI of 42 Alzheimer’s disease dementia (ADD), 42 normal controls (NCs), and 39 MCI due to AD (mAD) from our GARD² database. We aim to create a generalized network to distinguish normal individuals (CN/NC) from dementia patients AD/ADD and MCI/mAD. Our performance relies on our feature extraction process and data smoothing process. Here the key process is to generate a Statistical Parametric Mapping (SPM) t-map image from VBM analysis and obtain the region of interest (ROI) that shows the optimistic result after two-sample t-tests for a smaller value of p < 0.001(AD vs. CN). The result was overwhelming for the distinction between AD/ADD and CN/NC, thus validating our idea for discriminative MRI features. Further, we compared our performance with other recent state-of-the-art methods, and it is comparatively better in many cases. We have experimented with two datasets to validate the process. To validate the network generalization, BR-NN is trained from 70% of the ADNI dataset and tested on 30% of the ADNI, 100% of the GARD dataset, and vice versa. Additionally, we identified the brain anatomical ROIs that may be relatively responsible for brain atrophy during the AD diagnosis. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures

Figure 1

Review

Jump to: Research

33 pages, 1391 KiB

Open AccessReview

Survey of Machine Learning Techniques in the Analysis of EEG Signals for Parkinson’s Disease: A Systematic Review

by Ana M. Maitin, Juan Pablo Romero Muñoz and Álvaro José García-Tejedor

Appl. Sci. 2022, 12(14), 6967; https://0-doi-org.brum.beds.ac.uk/10.3390/app12146967 - 09 Jul 2022

Cited by 17 | Viewed by 3555

Abstract

Background: Parkinson’s disease (PD) affects 7–10 million people worldwide. Its diagnosis is clinical and can be supported by image-based tests, which are expensive and not always accessible. Electroencephalograms (EEG) are non-invasive, widely accessible, low-cost tests. However, the signals obtained are difficult to analyze visually, so advanced techniques, such as Machine Learning (ML), need to be used. In this article, we review those studies that consider ML techniques to study the EEG of patients with PD. Methods: The review process was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, which are used to provide quality standards for the objective evaluation of various studies. All publications before February 2022 were included, and their main characteristics and results were evaluated and documented through three key points associated with the development of ML techniques: dataset quality, data preprocessing, and model evaluation. Results: 59 studies were included. The predominating models were Support Vector Machine (SVM) and Artificial Neural Networks (ANNs). In total, 31 articles diagnosed PD with a mean accuracy of 97.35 ± 3.46%. There was no standard cleaning protocol for EEG and a great heterogeneity in EEG characteristics was shown, although spectral features predominated by 88.37%. Conclusions: Neither the cleaning protocol nor the number of EEG channels influenced the classification results. A baseline value was provided for the PD diagnostic problem, although recent studies focus on the identification of cognitive impairment. Full article

(This article belongs to the Special Issue Advances in Biomedical Signal Processing in Health Care)

► Show Figures