Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Machine Learning Methods for Biomedical Data Analysis

Special Issue Editors
Special Issue Information
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Biomedical Sensors".

Deadline for manuscript submissions: closed (20 May 2023) | Viewed by 30466

Share This Special Issue

Special Issue Editors

Prof. Dr. Jordi Solé-Casals

E-Mail Website
Guest Editor

Department of Engineering, University of Vic - Central University of Catalonia, 08500 Vic, Barcelona, Spain
Interests: biomedical signal processing; machine learning; deep learning; signal processing theory and methods; neurosciences
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. César F. Caiafa

E-Mail Website
Guest Editor

IAR-CONICET / University of Buenos Aires, Buenos Aires, Argentina
Interests: machine learning; tensors decompositions; compressed sensing; sparse representations; brain diffusion MRI
Special Issues, Collections and Topics in MDPI journals

Dr. Zhe Sun

E-Mail Website
Guest Editor

RIKEN National Science Institute, Tokyo, Japan
Interests: brain simulation; connectome; brain mapping; brain signal processing
Special Issues, Collections and Topics in MDPI journals

Dr. Pere Marti-Puig

E-Mail Website
Guest Editor

Department of Engineering, University of Vic - Central University of Catalonia, Vic, Catalonia, Spain
Interests: signal processing; fast algorithms; tensor analysis; machine learn- ing/deep learning
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Toshihisa Tanaka

E-Mail Website
Guest Editor

Department of Electronic and Information Engineering, Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan
Interests: biomedical signal processing and machine learning for brain-computer interfaces; epilepsy; neuromusicology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning application to biomedical data is becoming increasingly popular. It is a very useful tool for medical decision making, to extract more information from an image, to automate tasks such as segmentation in radiological images, to determine the tracts in medical images, and so on. These systems are increasingly integrated into the daily routine of physicians and are part of many of the instruments used for disease diagnosis.

There are many types of machine learning algorithms, each one with different characteristics and exploiting different strategies. Moreover, biomedical data types and structure is highly diverse. They can be provided in the form of time series (ECG, EEG, speech, handwriting, etc.), multidimensional images (MRI/fMRI, XR, PET, etc.), omics data (genetic, proteomic, etc.) or questionnaires. Therefore, the approach to be used will very much depend on these factors and the final application.

Machine learning techniques are also highly dependent on the parameterization of the data to be processed. The appropriate choice of how the data is represented has a significant impact on the models' complexity, the time required to fit them, their explainability, and their performance. There are many possible ways to parameterize the same data for a given application. The appropriate choice is rarely trivial and almost always subject to improvement.

The aim of this Special Issue is to invite active researchers to submit original papers that focus on the development of machine learning algorithms for biomedical applications, to contribute to the dissemination of new ideas on this field and to encourage their application in real scenarios.

Potential topics include, but are not limited to, the following:

Supervised and unsupervised learning with data obtained through electrodes recordings: EEG, EcoG, ECG, etc.;
Intelligent blind source separation of biomedical data;
Multidimensional Image based Artificial Intelligence: MRI, fMRI, dMRI, XR, PET;
Ill-defined inverse problems solving through machine learning (e.g. tomography);
Interpretive Artificial Intelligence in biomedical applications;
Sparse coding representations of biomedical data;
Matrix and tensor factorization methods applied to biomedical data;
Bayesian learning applied to biomedical data;
Machine learning methods in drug discovery;
Machine learning methods in remote health monitoring and data processing.

Prof. Dr. Jordi Solé-Casals
Prof. Dr. César F. Caiafa
Dr. Sun Zhe
Dr. Pere Marti-Puig
Prof. Dr. Toshihisa Tanaka
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. Sensors 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.

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (11 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Editorial

Jump to: Research

4 pages, 209 KiB

Open AccessEditorial

Special Issue “Machine Learning Methods for Biomedical Data Analysis”

by Cesar F. Caiafa, Zhe Sun, Toshihisa Tanaka, Pere Marti-Puig and Jordi Solé-Casals

Sensors 2023, 23(23), 9377; https://doi.org/10.3390/s23239377 - 24 Nov 2023

Cited by 1 | Viewed by 1261

Abstract

Machine learning is an effective method for developing automatic algorithms for analysing sophisticated biomedical data [...] Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

Research

Jump to: Editorial

13 pages, 610 KiB

Open AccessArticle

Prediction of Preterm Labor from the Electrohysterogram Signals Based on Different Gestational Weeks

by Somayeh Mohammadi Far, Matin Beiramvand, Mohammad Shahbakhti and Piotr Augustyniak

Sensors 2023, 23(13), 5965; https://doi.org/10.3390/s23135965 - 27 Jun 2023

Cited by 2 | Viewed by 1890

Abstract

Timely preterm labor prediction plays an important role for increasing the chance of neonate survival, the mother’s mental health, and reducing financial burdens imposed on the family. The objective of this study is to propose a method for the reliable prediction of preterm labor from the electrohysterogram (EHG) signals based on different pregnancy weeks. In this paper, EHG signals recorded from 300 subjects were split into 2 groups: (I) those with preterm and term labor EHG data that were recorded prior to the 26th week of pregnancy (referred to as the PE-TE group), and (II) those with preterm and term labor EHG data that were recorded after the 26th week of pregnancy (referred to as the PL-TL group). After decomposing each EHG signal into four intrinsic mode functions (IMFs) by empirical mode decomposition (EMD), several linear and nonlinear features were extracted. Then, a self-adaptive synthetic over-sampling method was used to balance the feature vector for each group. Finally, a feature selection method was performed and the prominent ones were fed to different classifiers for discriminating between term and preterm labor. For both groups, the AdaBoost classifier achieved the best results with a mean accuracy, sensitivity, specificity, and area under the curve (AUC) of 95%, 92%, 97%, and 0.99 for the PE-TE group and a mean accuracy, sensitivity, specificity, and AUC of 93%, 90%, 94%, and 0.98 for the PL-TL group. The similarity between the obtained results indicates the feasibility of the proposed method for the prediction of preterm labor based on different pregnancy weeks. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

16 pages, 1136 KiB

Open AccessArticle

Prediction of Diabetes Mellitus Progression Using Supervised Machine Learning

by Apoorva S. Chauhan, Mathew S. Varre, Kenneth Izuora, Mohamed B. Trabia and Janet S. Dufek

Sensors 2023, 23(10), 4658; https://doi.org/10.3390/s23104658 - 11 May 2023

Cited by 4 | Viewed by 2219

Abstract

Diabetic peripheral neuropathy (DN) is a serious complication of diabetes mellitus (DM) that can lead to foot ulceration and eventual amputation if not treated properly. Therefore, detecting DN early is important. This study presents an approach for diagnosing various stages of the progression of DM in lower extremities using machine learning to classify individuals with prediabetes (PD; n = 19), diabetes without (D; n = 62), and diabetes with peripheral neuropathy (DN; n = 29) based on dynamic pressure distribution collected using pressure-measuring insoles. Dynamic plantar pressure measurements were recorded bilaterally (60 Hz) for several steps during the support phase of walking while participants walked at self-selected speeds over a straight path. Pressure data were grouped and divided into three plantar regions: rearfoot, midfoot, and forefoot. For each region, peak plantar pressure, peak pressure gradient, and pressure–time integral were calculated. A variety of supervised machine learning algorithms were used to assess the performance of models trained using different combinations of pressure and non-pressure features to predict diagnoses. The effects of choosing various subsets of these features on the model’s accuracy were also considered. The best performing models produced accuracies between 94–100%, showing the proposed approach can be used to augment current diagnostic methods. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

13 pages, 1845 KiB

Open AccessArticle

Estimation of Respiratory Rate during Biking with a Single Sensor Functional Near-Infrared Spectroscopy (fNIRS) System

by Mohammad Shahbakhti, Naser Hakimi, Jörn M. Horschig, Marianne Floor-Westerdijk, Jurgen Claassen and Willy N. J. M. Colier

Sensors 2023, 23(7), 3632; https://doi.org/10.3390/s23073632 - 31 Mar 2023

Cited by 4 | Viewed by 3441

Abstract

Objective: The employment of wearable systems for continuous monitoring of vital signs is increasing. However, due to substantial susceptibility of conventional bio-signals recorded by wearable systems to motion artifacts, estimation of the respiratory rate (RR) during physical activities is a challenging task. Alternatively, functional Near-Infrared Spectroscopy (fNIRS) can be used, which has been proven less vulnerable to the subject’s movements. This paper proposes a fusion-based method for estimating RR during bicycling from fNIRS signals recorded by a wearable system. Methods: Firstly, five respiratory modulations are extracted, based on amplitude, frequency, and intensity of the oxygenated hemoglobin concentration (

O_{2} H b

) signal. Secondly, the dominant frequency of each modulation is computed using the fast Fourier transform. Finally, dominant frequencies of all modulations are fused, based on averaging, to estimate RR. The performance of the proposed method was validated on 22 young healthy subjects, whose respiratory and fNIRS signals were simultaneously recorded during a bicycling task, and compared against a zero delay Fourier domain band-pass filter. Results: The comparison between results obtained by the proposed method and band-pass filtering indicated the superiority of the former, with a lower mean absolute error (3.66 vs. 11.06 breaths per minute,

p < 0.05

). The proposed fusion strategy also outperformed RR estimations based on the analysis of individual modulation. Significance: This study orients towards the practical limitations of traditional bio-signals for RR estimation during physical activities. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Graphical abstract

18 pages, 4944 KiB

Open AccessArticle

HUMANISE: Human-Inspired Smart Management, towards a Healthy and Safe Industrial Collaborative Robotics

by Karmele Lopez-de-Ipina, Jon Iradi, Elsa Fernandez, Pilar M. Calvo, Damien Salle, Anujan Poologaindran, Ivan Villaverde, Paul Daelman, Emilio Sanchez, Catalina Requejo and John Suckling

Sensors 2023, 23(3), 1170; https://doi.org/10.3390/s23031170 - 19 Jan 2023

Cited by 5 | Viewed by 3288

Abstract

The workplace is evolving towards scenarios where humans are acquiring a more active and dynamic role alongside increasingly intelligent machines. Moreover, the active population is ageing and consequently emerging risks could appear due to health disorders of workers, which requires intelligent intervention both for production management and workers’ support. In this sense, the innovative and smart systems oriented towards monitoring and regulating workers’ well-being will become essential. This work presents HUMANISE, a novel proposal of an intelligent system for risk management, oriented to workers suffering from disease conditions. The developed support system is based on Computer Vision, Machine Learning and Intelligent Agents. Results: The system was applied to a two-arm Cobot scenario during a Learning from Demonstration task for collaborative parts transportation, where risk management is critical. In this environment with a worker suffering from a mental disorder, safety is successfully controlled by means of human/robot coordination, and risk levels are managed through the integration of human/robot behaviour models and worker’s models based on the workplace model of the World Health Organization. The results show a promising real-time support tool to coordinate and monitoring these scenarios by integrating workers’ health information towards a successful risk management strategy for safe industrial Cobot environments. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

19 pages, 7008 KiB

Open AccessArticle

Treatment Outcome Prediction Using Multi-Task Learning: Application to Botulinum Toxin in Gait Rehabilitation

by Adil Khan, Antoine Hazart, Omar Galarraga, Sonia Garcia-Salicetti and Vincent Vigneron

Sensors 2022, 22(21), 8452; https://doi.org/10.3390/s22218452 - 3 Nov 2022

Cited by 2 | Viewed by 2321

Abstract

We propose a framework for optimizing personalized treatment outcomes for patients with neurological diseases. A typical consequence of such diseases is gait disorders, partially explained by command and muscle tone problems associated with spasticity. Intramuscular injection of botulinum toxin type A is a common treatment for spasticity. According to the patient’s profile, offering the optimal treatment combined with the highest possible benefit-risk ratio is important. For the prediction of knee and ankle kinematics after botulinum toxin type A (BTX-A) treatment, we propose: (1) a regression strategy based on a multi-task architecture composed of LSTM models; (2) to introduce medical treatment data (MTD) for context modeling; and (3) a gating mechanism to model treatment interaction more efficiently. The proposed models were compared with and without metadata describing treatments and with serial models. Multi-task learning (MTL) achieved the lowest root-mean-squared error (RMSE) (5.60°) for traumatic brain injury (TBI) patients on knee trajectories and the lowest RMSE (3.77°) for cerebral palsy (CP) patients on ankle trajectories, with only a difference of 5.60° between actual and predicted. Overall, the best RMSE ranged from 5.24° to 6.24° for the MTL models. To the best of our knowledge, this is the first time that MTL has been used for post-treatment gait trajectory prediction. The MTL models outperformed the serial models, particularly when introducing treatment metadata. The gating mechanism is efficient in modeling treatment interaction and improving trajectory prediction. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

16 pages, 3414 KiB

Open AccessArticle

Data Fusion-Based Musculoskeletal Synergies in the Grasping Hand

by Parthan Olikkal, Dingyi Pei, Tülay Adali, Nilanjan Banerjee and Ramana Vinjamuri

Sensors 2022, 22(19), 7417; https://doi.org/10.3390/s22197417 - 29 Sep 2022

Cited by 5 | Viewed by 1938

Abstract

The hypothesis that the central nervous system (CNS) makes use of synergies or movement primitives in achieving simple to complex movements has inspired the investigation of different types of synergies. Kinematic and muscle synergies have been extensively studied in the literature, but only a few studies have compared and combined both types of synergies during the control and coordination of the human hand. In this paper, synergies were extracted first independently (called kinematic and muscle synergies) and then combined through data fusion (called musculoskeletal synergies) from 26 activities of daily living in 22 individuals using principal component analysis (PCA) and independent component analysis (ICA). By a weighted linear combination of musculoskeletal synergies, the recorded kinematics and the recorded muscle activities were reconstructed. The performances of musculoskeletal synergies in reconstructing the movements were compared to the synergies reported previously in the literature by us and others. The results indicate that the musculoskeletal synergies performed better than the synergies extracted without fusion. We attribute this improvement in performance to the musculoskeletal synergies that were generated on the basis of the cross-information between muscle and kinematic activities. Moreover, the synergies extracted using ICA performed better than the synergies extracted using PCA. These musculoskeletal synergies can possibly improve the capabilities of the current methodologies used to control high dimensional prosthetics and exoskeletons. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

17 pages, 1040 KiB

Open AccessArticle

An Interpretable Two-Phase Modeling Approach for Lung Cancer Survivability Prediction

by Zahra Sedighi-Maman and Jonathan J. Heath

Sensors 2022, 22(18), 6783; https://doi.org/10.3390/s22186783 - 8 Sep 2022

Cited by 1 | Viewed by 2431

Abstract

Although lung cancer survival status and survival length predictions have primarily been studied individually, a scheme that leverages both fields in an interpretable way for physicians remains elusive. We propose a two-phase data analytic framework that is capable of classifying survival status for 0.5-, 1-, 1.5-, 2-, 2.5-, and 3-year time-points (phase I) and predicting the number of survival months within 3 years (phase II) using recent Surveillance, Epidemiology, and End Results data from 2010 to 2017. In this study, we employ three analytical models (general linear model, extreme gradient boosting, and artificial neural networks), five data balancing techniques (synthetic minority oversampling technique (SMOTE), relocating safe level SMOTE, borderline SMOTE, adaptive synthetic sampling, and majority weighted minority oversampling technique), two feature selection methods (least absolute shrinkage and selection operator (LASSO) and random forest), and the one-hot encoding approach. By implementing a comprehensive data preparation phase, we demonstrate that a computationally efficient and interpretable method such as GLM performs comparably to more complex models. Moreover, we quantify the effects of individual features in phase I and II by exploiting GLM coefficients. To the best of our knowledge, this study is the first to (a) implement a comprehensive data processing approach to develop performant, computationally efficient, and interpretable methods in comparison to black-box models, (b) visualize top factors impacting survival odds by utilizing the change in odds ratio, and (c) comprehensively explore short-term lung cancer survival using a two-phase approach. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

18 pages, 956 KiB

Open AccessArticle

Enabling Timely Medical Intervention by Exploring Health-Related Multivariate Time Series with a Hybrid Attentive Model

by Jia Xie, Zhu Wang, Zhiwen Yu and Bin Guo

Sensors 2022, 22(16), 6104; https://doi.org/10.3390/s22166104 - 15 Aug 2022

Cited by 2 | Viewed by 2136

Abstract

Modern healthcare practice, especially in intensive care units, produces a vast amount of multivariate time series of health-related data, e.g., multi-lead electrocardiogram (ECG), pulse waveform, blood pressure waveform and so on. As a result, timely and accurate prediction of medical intervention (e.g., intravenous injection) becomes possible, by exploring such semantic-rich time series. Existing works mainly focused on onset prediction at the granularity of hours that was not suitable for medication intervention in emergency medicine. This research proposes a Multi-Variable Hybrid Attentive Model (MVHA) to predict the impending need of medical intervention, by jointly mining multiple time series. Specifically, a two-level attention mechanism is designed to capture the pattern of fluctuations and trends of different time series. This work applied MVHA to the prediction of the impending intravenous injection need of critical patients at the intensive care units. Experiments on the MIMIC Waveform Database demonstrated that the proposed model achieves a prediction accuracy of 0.8475 and an ROC-AUC of 0.8318, which significantly outperforms baseline models. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

18 pages, 2366 KiB

Open AccessArticle

Spatiotemporal Eye-Tracking Feature Set for Improved Recognition of Dyslexic Reading Patterns in Children

by Ivan Vajs, Vanja Ković, Tamara Papić, Andrej M. Savić and Milica M. Janković

Sensors 2022, 22(13), 4900; https://doi.org/10.3390/s22134900 - 29 Jun 2022

Cited by 13 | Viewed by 3159

Abstract

Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Figure 1

14 pages, 1727 KiB

Open AccessArticle

A Machine Learning Approach for Predicting Non-Suicidal Self-Injury in Young Adults

by Pere Marti-Puig, Chiara Capra, Daniel Vega, Laia Llunas and Jordi Solé-Casals

Sensors 2022, 22(13), 4790; https://doi.org/10.3390/s22134790 - 24 Jun 2022

Cited by 8 | Viewed by 3005

Abstract

Artificial intelligence techniques were explored to assess the ability to anticipate self-harming behaviour in the mental health context using a database collected by an app previously designed to record the emotional states and activities of a group of subjects exhibiting self-harm. Specifically, the Leave-One-Subject-Out technique was used to train classification trees with a maximum of five splits. The results show an accuracy of 84.78%, a sensitivity of 64.64% and a specificity of 85.53%. In addition, positive and negative predictive values were also obtained, with results of 14.48% and 98.47%, respectively. These results are in line with those reported in previous work using a multilevel mixed-effect regression analysis. The combination of apps and AI techniques is a powerful way to improve the tools to accompany and support the care and treatment of patients with this type of behaviour. These studies also guide the improvement of apps on the user side, simplifying and collecting more meaningful data, and on the therapist side, progressing in pathology treatments. Traditional therapy involves observing and reconstructing what had happened before episodes once they have occurred. This new generation of tools will make it possible to monitor the pathology more closely and to act preventively. Full article

(This article belongs to the Special Issue Machine Learning Methods for Biomedical Data Analysis)

► Show Figures

Journal Menu

Journal Browser

Machine Learning Methods for Biomedical Data Analysis

Share This Special Issue

Special Issue Editors

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (11 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI