BioMedInformatics

Research

21 pages, 2314 KiB

Open AccessArticle

High Accuracy of Epileptic Seizure Detection Using Tiny Machine Learning Technology for Implantable Closed-Loop Neurostimulation Systems

by Evangelia Tsakanika, Vasileios Tsoukas, Athanasios Kakarountas and Vasileios Kokkinos

BioMedInformatics 2025, 5(1), 14; https://doi.org/10.3390/biomedinformatics5010014 - 10 Mar 2025

Viewed by 1212

Abstract

Background: Epilepsy is one of the most common and devastating neurological disorders, manifesting with seizures and affecting approximately 1–2% of the world’s population. The criticality of seizure occurrence and associated risks, combined with the overwhelming need for more precise and innovative treatment methods, [...] Read more.

Background: Epilepsy is one of the most common and devastating neurological disorders, manifesting with seizures and affecting approximately 1–2% of the world’s population. The criticality of seizure occurrence and associated risks, combined with the overwhelming need for more precise and innovative treatment methods, has led to the development of invasive neurostimulation devices programmed to detect and apply electrical stimulation therapy to suppress seizures and reduce the seizure burden. Tiny Machine Learning (TinyML) is a rapidly growing branch of machine learning. One of its key characteristics is the ability to run machine learning algorithms without the need for high computational complexity and powerful hardware resources. The featured work utilizes TinyML technology to implement an algorithm that can be integrated into the microprocessor of an implantable closed-loop brain neurostimulation system to accurately detect seizures in real-time by analyzing intracranial EEG (iEEG) signals. Methods: A dataset containing iEEG signal values from both non-epileptic and epileptic individuals was utilized for the implementation of the proposed algorithm. Appropriate data preprocessing was performed, and two training datasets with 1000 records of non-epileptic and epileptic iEEG signals were created. A test dataset with an independent dataset of 500 records was also created. The web-based platform Edge Impulse was used for model generation and visualization, and different model architectures were explored and tested. Finally, metrics of accuracy, confusion matrices, and ROC curves were used to evaluate the performance of the model. Results: Our model demonstrated high performance, achieving 98% and 99% accuracy on the validation and test EEG datasets, respectively. Our results support the use of TinyML technology in closed-loop neurostimulation devices for epilepsy, as it contributes significantly to the speed and accuracy of seizure detection. Conclusions: The proposed TinyML model demonstrated reliable seizure detection in real-time by analyzing EEG signals and distinguishing epileptic activity from normal brain electrical activity. These findings highlight the potential of TinyML in closed-loop neurostimulation systems for epilepsy, enhancing both speed and accuracy in seizure detection. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

13 pages, 2163 KiB

Open AccessArticle

ViBEx: A Visualization Tool for Gene Expression Analysis

by Michael H. Terrefortes-Rosado, Andrea V. Nieves-Rivera, Humberto Ortiz-Zuazaga and Marie Lluberes-Contreras

BioMedInformatics 2025, 5(1), 13; https://doi.org/10.3390/biomedinformatics5010013 - 7 Mar 2025

Viewed by 556

Abstract

Background: Variations in the states of Gene Regulatory Networks significantly influence disease outcomes and drug development. Boolean Networks serve as a tool to conceptualize and understand the complex relationships between genes. Threshold computation methods are used for the binarization of gene expression and [...] Read more.

Background: Variations in the states of Gene Regulatory Networks significantly influence disease outcomes and drug development. Boolean Networks serve as a tool to conceptualize and understand the complex relationships between genes. Threshold computation methods are used for the binarization of gene expression and the Boolean representation of its Gene Regulatory Network. This study aims to provide a platform that facilitates the exploration of the impact of different threshold computation methods on the binarization of gene expression and the subsequent Boolean representation of Gene Regulatory Networks. Methods: Threshold computation methods are implemented for binarizing gene expression, enabling the Boolean representation of the Gene Regulatory Networks. Variations in gene expression discretization and threshold computation methods often lead to differing Boolean representations, which may affect the subsequent analysis. Lluberes proposed a framework for analyzing gene expression when binarization varies based on these factors. This theoretical framework was implemented using the Python Dash framework. Results: A visualization tool has been developed to implement this framework. The tool allows users to upload gene expression datasets and interact with a dashboard to explore gene expression binarization and the inferred Boolean Networks. Conclusions: The developed visualization tool provides a platform that facilitates the exploration of how different binarization methods impact the interpretation of Gene Regulatory Networks, offering insights for disease research and drug development. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

16 pages, 525 KiB

Open AccessArticle

Evaluating COVID-19 Vaccine Efficacy Using Kaplan–Meier Survival Analysis

by Waleed Hilal, Michael G. Chislett, Yuandi Wu, Brett Snider, Edward A. McBean, John Yawney and Stephen Andrew Gadsden

BioMedInformatics 2024, 4(4), 2117-2132; https://doi.org/10.3390/biomedinformatics4040113 - 12 Oct 2024

Viewed by 1958

Abstract

Analyses of COVID-19 vaccines have become a forefront of pandemic-related research, as jurisdictions around the world encourage vaccinations as the most assured method to curtail the need for stringent public health measures. Kaplan–Meier models, a form of “survival analysis”, provide a statistical approach [...] Read more.

Analyses of COVID-19 vaccines have become a forefront of pandemic-related research, as jurisdictions around the world encourage vaccinations as the most assured method to curtail the need for stringent public health measures. Kaplan–Meier models, a form of “survival analysis”, provide a statistical approach to improve the understanding of time-to-event probabilities of occurrence. In applications of epidemiology and the study of vaccines, survival analyses can be implemented to quantify the probability of testing positive for SARS-CoV-2, given a population’s vaccination status. In this study, a large proportion of Ontario COVID-19 testing data is used to derive Kaplan–Meier probability curves for individuals who received two doses of a vaccine during a period of peak Delta variant cases, and again for those receiving three doses during a peak time of the Omicron variant. Data consisting of 614,470 individuals with two doses of a COVID-19 vaccine, and 49,551 individuals with three-doses of vaccine, show that recipients of the Moderna vaccine are slightly less likely to test positive for the virus in a 38-day period following their last vaccination than recipients of the Pfizer vaccine, although the difference between the two is marginal in most age groups. This result is largely consistent for two doses of the vaccines during a Delta variant period, as well as an Omicron variant period. The evaluated probabilities of testing positive align with the publicly reported vaccine efficacies of the mRNA vaccines, supporting the resolution that Kaplan–Meier methods in determining vaccine benefits are a justifiable and useful approach in addressing vaccine-related concerns in the COVID-19 landscape. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

34 pages, 3635 KiB

Open AccessArticle

Machine Learning for Extraction of Image Features Associated with Progression of Geographic Atrophy

by Janan Arslan and Kurt Benke

BioMedInformatics 2024, 4(3), 1638-1671; https://doi.org/10.3390/biomedinformatics4030089 - 2 Jul 2024

Cited by 1 | Viewed by 1316

Abstract

Background: Several studies have investigated various features and models in order to understand the growth and progression of the ocular disease geographic atrophy (GA). Commonly assessed features include age, sex, smoking, alcohol consumption, sedentary lifestyle, hypertension, and diabetes. There have been inconsistencies regarding [...] Read more.

Background: Several studies have investigated various features and models in order to understand the growth and progression of the ocular disease geographic atrophy (GA). Commonly assessed features include age, sex, smoking, alcohol consumption, sedentary lifestyle, hypertension, and diabetes. There have been inconsistencies regarding which features correlate with GA progression. Chief amongst these inconsistencies is whether the investigated features are readily available for analysis across various ophthalmic institutions. Methods:In this study, we focused our attention on the association of fundus autofluorescence (FAF) imaging features and GA progression. Our method included feature extraction using radiomic processes and feature ranking by machine learning incorporating the algorithm XGBoost to determine the best-ranked features. This led to the development of an image-based linear mixed-effects model, which was designed to account for slope change based on within-subject variability and inter-eye correlation. Metrics used to assess the linear mixed-effects model included marginal and conditional

R^{2}

, Pearson’s correlation coefficient (

r

), root mean square error (RMSE), mean error (ME), mean absolute error (MAE), mean absolute deviation (MAD), the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and loglikelihood. Results: We developed a linear mixed-effects model with 15 image-based features. The model results were as follows:

R^{2}

= 0.96,

r

= 0.981, RMSE = 1.32, ME = −7.3 × 10⁻¹⁵, MAE = 0.94, MAD = 0.999, AIC = 2084.93, BIC = 2169.97, and log likelihood = −1022.46. Conclusions: The advantage of our method is that it relies on the inherent properties of the image itself, rather than the availability of clinical or demographic data. Thus, the image features discovered in this study are universally and readily available across the board. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

12 pages, 514 KiB

Open AccessArticle

Calibrating Glucose Sensors at the Edge: A Stress Generation Model for Tiny ML Drift Compensation

by Anna Sabatini, Costanza Cenerini, Luca Vollero and Danilo Pau

BioMedInformatics 2024, 4(2), 1519-1530; https://doi.org/10.3390/biomedinformatics4020083 - 9 Jun 2024

Cited by 1 | Viewed by 1001

Abstract

Background: Continuous glucose monitoring (CGM) systems offer the advantage of noninvasive monitoring and continuous data on glucose fluctuations. This study introduces a new model that enables the generation of synthetic but realistic databases that integrate physiological variables and sensor attributes into a [...] Read more.

Background: Continuous glucose monitoring (CGM) systems offer the advantage of noninvasive monitoring and continuous data on glucose fluctuations. This study introduces a new model that enables the generation of synthetic but realistic databases that integrate physiological variables and sensor attributes into a dataset generation model and this, in turn, enables the design of improved CGM systems. Methods: The presented approach uses a combination of physiological data and sensor characteristics to construct a model that considers the impact of these variables on the accuracy of CGM measures. A dataset of 500 sensor responses over a 15-day period is generated and analyzed using machine learning algorithms (random forest regressor and support vector regressor). Results: The random forest and support vector regression models achieved Mean Absolute Errors (MAEs) of

16.13

mg/dL and

16.22

mg/dL, respectively. In contrast, models trained solely on single sensor outputs recorded an average MAE of

11.01 \pm 5.12

mg/dL. These findings demonstrate the variable impact of integrating multiple data sources on the predictive accuracy of CGM systems, as well as the complexity of the dataset. Conclusions: This approach provides a foundation for developing more precise algorithms and introduces its initial application of Tiny Machine Control Units (MCUs). More research is recommended to refine these models and validate their effectiveness in clinical settings. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

15 pages, 2325 KiB

Open AccessArticle

Machine Learning in Allergic Contact Dermatitis: Identifying (Dis)similarities between Polysensitized and Monosensitized Patients

by Aikaterini Kyritsi, Anna Tagka, Alexander Stratigos and Vangelis D. Karalis

BioMedInformatics 2024, 4(2), 1348-1362; https://doi.org/10.3390/biomedinformatics4020074 - 17 May 2024

Viewed by 1557

Abstract

Background: Allergic contact dermatitis (ACD) is a delayed hypersensitivity reaction occurring in sensitized individuals due to exposure to allergens. Polysensitization, defined as positive reactions to multiple unrelated haptens, increases the risk of ACD development and affects patients’ quality of life. The aim of [...] Read more.

Background: Allergic contact dermatitis (ACD) is a delayed hypersensitivity reaction occurring in sensitized individuals due to exposure to allergens. Polysensitization, defined as positive reactions to multiple unrelated haptens, increases the risk of ACD development and affects patients’ quality of life. The aim of this study is to apply machine learning in order to analyze the association between ACD, polysensitization, individual susceptibility, and patients’ characteristics. Methods: Patch test results and demographics from 400 ACD patients (Study protocol Nr. 3765/2022), categorized as polysensitized or monosensitized, were analyzed. Classic statistical analysis and multiple correspondence analysis (MCA) were utilized to explore relationships among variables. Results: The findings revealed significant associations between patient characteristics and ACD patterns, with hand dermatitis showing the strongest correlation. MCA provided insights into the complex interplay of demographic and clinical factors influencing ACD prevalence. Conclusion: Overall, this study highlights the potential of machine learning in unveiling hidden patterns within dermatological data, paving the way for future advancements in the field. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

13 pages, 2093 KiB

Open AccessArticle

A Smartphone-Based Algorithm for L Test Subtask Segmentation

by Alexis L. McCreath Frangakis, Edward D. Lemaire and Natalie Baddour

BioMedInformatics 2024, 4(2), 1262-1274; https://doi.org/10.3390/biomedinformatics4020069 - 10 May 2024

Cited by 1 | Viewed by 1289

Abstract

Background: Subtask segmentation can provide useful information from clinical tests, allowing clinicians to better assess a patient’s mobility status. A new smartphone-based algorithm was developed to segment the L Test of functional mobility into stand-up, sit-down, and turn subtasks. Methods: Twenty-one able-bodied participants [...] Read more.

Background: Subtask segmentation can provide useful information from clinical tests, allowing clinicians to better assess a patient’s mobility status. A new smartphone-based algorithm was developed to segment the L Test of functional mobility into stand-up, sit-down, and turn subtasks. Methods: Twenty-one able-bodied participants each completed five L Test trials, with a smartphone attached to their posterior pelvis. The smartphone used a custom-designed application that collected linear acceleration, gyroscope, and magnetometer data, which were then put into a threshold-based algorithm for subtask segmentation. Results: The algorithm produced good results (>97% accuracy, >98% specificity, >74% sensitivity) for all subtasks. Conclusions: These results were a substantial improvement compared with previously published results for the L Test, as well as similar functional mobility tests. This smartphone-based approach is an accessible method for providing useful metrics from the L Test that can lead to better clinical decision-making. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

11 pages, 3190 KiB

Open AccessArticle

Assaying and Classifying T Cell Function by Cell Morphology

by Xin Wang, Stacey M. Fernandes, Jennifer R. Brown and Lance C. Kam

BioMedInformatics 2024, 4(2), 1144-1154; https://doi.org/10.3390/biomedinformatics4020063 - 26 Apr 2024

Viewed by 2178

Abstract

Immune cell function varies tremendously between individuals, posing a major challenge to emerging cellular immunotherapies. This report pursues the use of cell morphology as an indicator of high-level T cell function. Short-term spreading of T cells on planar, elastic surfaces was quantified by [...] Read more.

Immune cell function varies tremendously between individuals, posing a major challenge to emerging cellular immunotherapies. This report pursues the use of cell morphology as an indicator of high-level T cell function. Short-term spreading of T cells on planar, elastic surfaces was quantified by 11 morphological parameters and analyzed to identify effects of both intrinsic and extrinsic factors. Our findings identified morphological features that varied between T cells isolated from healthy donors and those from patients being treated for Chronic Lymphocytic Leukemia (CLL). This approach also identified differences between cell responses to substrates of different elastic modulus. Combining multiple features through a machine learning approach such as Decision Tree or Random Forest provided an effective means for identifying whether T cells came from healthy or CLL donors. Further development of this approach could lead to a rapid assay of T cell function to guide cellular immunotherapy. Full article

(This article belongs to the Special Issue Editor's Choices Series for Methods in Biomedical Informatics Section)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor's Choices Series for Methods in Biomedical Informatics Section

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI