Applied Sciences

Research

Jump to: Other

28 pages, 4077 KiB

Open AccessArticle

A Hybrid Deep Learning Approach for Improved Detection and Prediction of Brain Stroke

by Gayatri Thakre, Rohini Raut, Chetan Puri and Prateek Verma

Appl. Sci. 2025, 15(9), 4639; https://doi.org/10.3390/app15094639 - 22 Apr 2025

Viewed by 855

Abstract

Brain stroke is the leading cause of death and disability globally; hence, early identification and prediction are critical for better patient outcomes. Traditional diagnostic procedures, such as manually interpreting clinical images, are time consuming and error prone. This research investigates the use of [...] Read more.

Brain stroke is the leading cause of death and disability globally; hence, early identification and prediction are critical for better patient outcomes. Traditional diagnostic procedures, such as manually interpreting clinical images, are time consuming and error prone. This research investigates the use of hybrid deep learning models, such as recurrent neural networks (RNNs), long short-term memory (LSTM), and convolutional neural networks (CNNs), to improve stroke prediction accuracy. The current study compared the performance of these individual models with the developed hybrid model on the brain stroke dataset. By merging these models, we reached an overall accuracy of 96% in identifying stroke risk as low, medium, or high. This categorization may offer healthcare practitioners actionable insights by assisting them and allowing them to make better decisions. This technique represents a substantial improvement in stroke prediction and preventive healthcare practices. The model’s performance can further be tested with more complicated clinical and demographic data that will help to generalize the model for real-world clinical applications. Furthermore, combining this hybrid model with electronic health records (EHR) systems can also assist in early identification, tailored therapies, and improved stroke management, enhancing patient outcomes and lowering healthcare costs. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

18 pages, 954 KiB

Open AccessArticle

Integrating Machine Learning Algorithms: A Hybrid Model for Lung Cancer Outcome Improvement

by Pradnyawant M. Gote, Praveen Kumar, Hemant Kumar, Prateek Verma and Moses Makuei Jiet

Appl. Sci. 2025, 15(9), 4637; https://doi.org/10.3390/app15094637 - 22 Apr 2025

Viewed by 871

Abstract

Lung cancer is a major global health threat, affecting millions annually and resulting in severe complications and high mortality rates, particularly when diagnosed late. It remains one of the leading causes of cancer-related deaths worldwide, often detected at advanced stages due to the [...] Read more.

Lung cancer is a major global health threat, affecting millions annually and resulting in severe complications and high mortality rates, particularly when diagnosed late. It remains one of the leading causes of cancer-related deaths worldwide, often detected at advanced stages due to the lack of early symptoms. This study introduces a novel hybrid machine learning model aimed at enhancing early detection accuracy and improving patient outcomes. By integrating traditional machine learning classifiers with deep learning techniques, the proposed framework optimizes feature selection, hyperparameter tuning, and data-balancing strategies, such as Adaptive Synthetic Sampling (ADASYN). A comparative evaluation with existing models demonstrated substantial improvements in predictive accuracy, ranging from 0.44% to 9.69%, with Gradient Boosting and Random Forest models achieving the highest classification performance. The study highlights the importance of hybrid methodologies in refining lung cancer diagnostics, ensuring robust, scalable, and clinically viable predictive models. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

11 pages, 1461 KiB

Open AccessArticle

Influence of Posture and Sleep Duration on Heart Rate Variability in Older Subjects

by Emi Yuda and Yutaka Yoshida

Appl. Sci. 2025, 15(5), 2504; https://doi.org/10.3390/app15052504 - 26 Feb 2025

Viewed by 1212

Abstract

Japan is facing challenges associated with its super-aging society, including increased social security burdens and a rise in the elderly workforce due to a declining younger labor force. Extending the healthy life expectancy is one countermeasure, necessitating lifestyle improvements such as frailty prevention [...] Read more.

Japan is facing challenges associated with its super-aging society, including increased social security burdens and a rise in the elderly workforce due to a declining younger labor force. Extending the healthy life expectancy is one countermeasure, necessitating lifestyle improvements such as frailty prevention and ensuring adequate sleep duration. This study investigated the relationship between heart rate variability (HRV) and sleep duration among older adults (aged ≥ 65) using electrocardiogram (ECG) and three-axis accelerometer data from the Allostatic State Mapping by the Ambulatory ECG Repository (ALLSTAR) database, recorded between January 2019 and March 2021. Inclusion criteria required a sinus rhythm and recording durations ≥80%. Continuous 24 h ECG and accelerometer data were analyzed for 55,154 participants (mean age 76 ± 6). The results consistently showed significant differences in HRV metrics, including MRRI, SDRR, ULF, LF, HF, and LF/HF, across sleep duration groups (G1–G4). Short-sleep groups (G4) exhibited decreased MRRI and SDRR and increased LF/HF, suggesting active lifestyles but reduced HRV. Conversely, long-sleep groups (G1) showed increased MRRI and reduced LF/HF but exhibited age-related declines in SDRR and ULF. These findings indicate that both insufficient and excessive sleep may contribute to HRV reduction in older adults. This study provides critical insights for improving elderly lifestyles through tailored interventions in exercise and sleep management. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

14 pages, 3098 KiB

Open AccessArticle

Aesthetic Speech Therapy: A New Protocol of Exercises Against Facial Aging, Focusing on Facial Muscles

by Luca Levrini, Andrea Carganico, Margherita Caccia, Alessandro Deppieri, Federica Marullo, Stefano Saran, Giorgio Binelli, Marco Iera and Piero Antonio Zecca

Appl. Sci. 2025, 15(4), 1742; https://doi.org/10.3390/app15041742 - 8 Feb 2025

Viewed by 1472

Abstract

The increasing emphasis on appearance and well-being has underscored the significance of self-care. From an aesthetic perspective, this entails addressing the early onset of wrinkles and the initial signs of aging. In response, new techniques have been developed, supplementing existing methods, to mitigate [...] Read more.

The increasing emphasis on appearance and well-being has underscored the significance of self-care. From an aesthetic perspective, this entails addressing the early onset of wrinkles and the initial signs of aging. In response, new techniques have been developed, supplementing existing methods, to mitigate the signs of aging. Aesthetic speech therapy has emerged in recent years as a non-invasive procedure to combat facial aging. The objective of this study is to evaluate its effects on the signs of facial aging in participants subjected to an experimental exercise protocol over a three-month period, focusing on orbicularis and zygomatic muscles, using both a digital evaluation analysis and a self-assessment questionnaire. A cohort of 21 female subjects, aged between 50 and 65, was instructed to perform a series of 4 targeted exercises for 15 min daily over a span of three months. The participants underwent monthly evaluations, each involving the collection of standardized photographic documentation and a three-dimensional facial scan. These scans were subsequently overlaid and analyzed by a colorimetric assay at the conclusion of the study period. Statistical tests were carried out by two-way ANOVA. Additionally, during the final evaluation (T3), the participants completed a questionnaire assessing their satisfaction with their self-image and the non-invasive aesthetic treatment they received. The statistical analysis of the overlays of the collected three-dimensional scans revealed a significant volumetric change around the orbicularis oris muscle. The difference between green and blue pixels was statistically significant (p < 0.05), as was the difference between blue and yellow pixels (p < 0.05). This change did not achieve statistical significance around the zygomatic muscles. The analysis of the participants’ questionnaire responses indicated an increasing level of satisfaction with their self-image at the end of the study compared to T0. Personal confidence increased by 20%, and participants reported a 53% improvement in satisfaction with their appearance in photographs. The observed volumetric changes may be attributed to modifications in the facial muscles targeted by the exercise protocol undertaken by the participants. However, further studies are warranted to delve deeper into this issue, considering the intricate process of facial aging and the complex three-dimensional structure of the face with its various components. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

23 pages, 2010 KiB

Open AccessArticle

ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographies

by Costin F. Ciușdel, Alex Serban and Tiziano Passerini

Appl. Sci. 2025, 15(3), 1415; https://doi.org/10.3390/app15031415 - 30 Jan 2025

Viewed by 844

Abstract

While traditional self-supervised learning methods improve performance and robustness across various medical tasks, they rely on single-vector embeddings that may not capture fine-grained concepts such as anatomical structures or organs. The ability to identify such concepts and their characteristics without supervision has the [...] Read more.

While traditional self-supervised learning methods improve performance and robustness across various medical tasks, they rely on single-vector embeddings that may not capture fine-grained concepts such as anatomical structures or organs. The ability to identify such concepts and their characteristics without supervision has the potential to improve pre-training methods, and enable novel applications such as fine-grained image retrieval and concept-based outlier detection. In this paper, we introduce ConceptVAE, a novel pre-training framework that detects and disentangles fine-grained concepts from their style characteristics in a self-supervised manner. We present a suite of loss terms and model architecture primitives designed to discretise input data into a preset number of concepts along with their local style. We validate ConceptVAE both qualitatively and quantitatively, demonstrating its ability to detect fine-grained anatomical structures such as blood pools and septum walls from 2D cardiac echocardiographies. Quantitatively, ConceptVAE outperforms traditional self-supervised methods in tasks such as region-based instance retrieval, semantic segmentation, out-of-distribution detection, and object detection. Additionally, we explore the generation of in-distribution synthetic data that maintains the same concepts as the training data but with distinct styles, highlighting its potential for more calibrated data generation. Overall, our study introduces and validates a promising new pre-training technique based on concept-style disentanglement, opening multiple avenues for developing models for medical image analysis that are more interpretable and explainable than black-box approaches. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

31 pages, 2695 KiB

Open AccessArticle

Development of a Clinical Decision Support System Using Artificial Intelligence Methods for Liver Transplant Centers

by Mete Yağanoğlu, Gürkan Öztürk, Ferhat Bozkurt, Zeynep Bilen, Zühal Yetiş Demir, Sinan Kul, Emrah Şimşek, Salih Kara, Hakan Eygu, Necip Altundaş, Nurhak Aksungur, Ercan Korkut, Mehmet Sinan Başar and Nurinnisa Öztürk

Appl. Sci. 2025, 15(3), 1248; https://doi.org/10.3390/app15031248 - 26 Jan 2025

Viewed by 1011

Abstract

The objective of this study is to utilize artificial intelligence techniques for the diagnosis of complications and diseases that may arise after liver transplantation, as well as for the identification of patients in need of transplantation. To achieve this, an interface was developed [...] Read more.

The objective of this study is to utilize artificial intelligence techniques for the diagnosis of complications and diseases that may arise after liver transplantation, as well as for the identification of patients in need of transplantation. To achieve this, an interface was developed to collect patient information from Atatürk University Research Hospital, specifically focusing on individuals who have undergone liver transplantation. The collected data were subsequently entered into a comprehensive database. Additionally, relevant patient information was obtained through the hospital’s information processing system, which was used to create a data pool. The classification of data was based on four dependent variables, namely, the presence or absence of death (“exitus”), recurrence location, tumor recurrence, and cause of death. Techniques such as Principal Component Analysis and Linear Discriminant Analysis (LDA) were employed to enhance the performance of the models. Among the various methods employed, the LDA method consistently yielded superior results in terms of accuracy during k-fold cross-validation. Following k-fold cross-validation, the model achieved the highest accuracy of 98% for the dependent variable “exitus”. For the dependent variable “recurrence location”, the highest accuracy obtained after k-fold cross-validation was 91%. Furthermore, the highest accuracy of 99% was achieved for both the dependent variables “tumor recurrence” and “cause of death” after k-fold cross-validation. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

9 pages, 298 KiB

Open AccessArticle

Exploring Generative Adversarial Network-Based Augmentation of Magnetic Resonance Brain Tumor Images

by Mahnoor Mahnoor, Oona Rainio and Riku Klén

Appl. Sci. 2024, 14(24), 11822; https://doi.org/10.3390/app142411822 - 18 Dec 2024

Viewed by 1159

Abstract

Background: A generative adversarial network (GAN) has gained popularity as a data augmentation technique in the medical field due to its efficiency in creating synthetic data for different machine learning models. In particular, the earlier literature suggests that the classification accuracy of a [...] Read more.

Background: A generative adversarial network (GAN) has gained popularity as a data augmentation technique in the medical field due to its efficiency in creating synthetic data for different machine learning models. In particular, the earlier literature suggests that the classification accuracy of a convolutional neural network (CNN) used for detecting brain tumors in magnetic resonance imaging (MRI) images increases when GAN-generated images are included in the training data together with the original images. However, there is little research about how the exact number of GAN-generated images and their ratio to the original images affects the results obtained. Materials and methods: Here, by using 1000 original images from a public repository with MRI images of patients with or without brain tumors, we built a GAN model to create synthetic brain MRI images. A modified U-Net CNN is trained multiple times with different training datasets and its classification accuracy is evaluated from a separate test set of another 1000 images. The Mann–Whitney U test is used to estimate whether the differences in the accuracy caused by different choices of training data are statistically significant. Results: According to our results, the use of GAN augmentation only sometimes produces a significant improvement. For instance, the classification accuracy significantly increases when 250–750 GAN-generated images are added to 1000 original images (p-values ≤ 0.0025) but decreases when 10 GAN-generated images are added to 500 original images (p-value: 0.03). Conclusions: Whenever GAN-based augmentation is used, the number of GAN-generated images should be carefully considered while accounting for the number of original images. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

20 pages, 1036 KiB

Open AccessArticle

Enhancing Breast Cancer Risk Prediction with Machine Learning: Integrating BMI, Smoking Habits, Hormonal Dynamics, and BRCA Gene Mutations—A Game-Changer Compared to Traditional Statistical Models?

by Luana Conte, Emanuele Rizzo, Emanuela Civino, Paolo Tarantino, Giorgio De Nunzio and Elisabetta De Matteis

Appl. Sci. 2024, 14(18), 8474; https://doi.org/10.3390/app14188474 - 20 Sep 2024

Cited by 3 | Viewed by 2882

Abstract

The association between genetics and lifestyle factors is crucial when determining breast cancer susceptibility, a leading cause of deaths globally. This research aimed to compare the body mass index, smoking behavior, hormonal influences, and BRCA gene mutations between affected patients and healthy individuals, [...] Read more.

The association between genetics and lifestyle factors is crucial when determining breast cancer susceptibility, a leading cause of deaths globally. This research aimed to compare the body mass index, smoking behavior, hormonal influences, and BRCA gene mutations between affected patients and healthy individuals, all with a family history of cancer. All these factors were then utilized as features to train a machine learning (ML) model to predict the risk of breast cancer development. Between 2020 and 2023, a total of 1389 women provided detailed lifestyle and risk factor data during visits to a familial cancer center in Italy. Descriptive and inferential statistics were assessed to explore the differences between the groups. Among the various classifiers used, the ensemble of decision trees was the best performer, with a 10-fold cross-validation scheme for training after normalizing the features. The performance of the model was evaluated using the receiver operating characteristic (ROC) curve and its area under the curve (AUC), alongside the accuracy, sensitivity, specificity, precision, and F1 score. Analysis revealed that individuals in the tumor group exhibited a higher risk profile when compared to their healthy counterparts, particularly in terms of the lifestyle and genetic markers. The ML model demonstrated predictive power, with an AUC of 81%, 88% sensitivity, 57% specificity, 78% accuracy, 80% precision, and an F1 score of 0.84. These metrics significantly outperformed traditional statistical prediction models, including the BOADICEA and BCRAT, which showed an AUC below 0.65. This study demonstrated the efficacy of an ML approach in identifying women at higher risk of breast cancer, leveraging lifestyle and genetic factors, with an improved predictive performance over traditional methods. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

9 pages, 240 KiB

Open AccessArticle

Impact of Hyperparameter Optimization to Enhance Machine Learning Performance: A Case Study on Breast Cancer Recurrence Prediction

by Lorena González-Castro, Marcela Chávez, Patrick Duflot, Valérie Bleret, Guilherme Del Fiol and Martín López-Nores

Appl. Sci. 2024, 14(13), 5909; https://doi.org/10.3390/app14135909 - 6 Jul 2024

Cited by 1 | Viewed by 2037

Abstract

Accurate and early prediction of breast cancer recurrence is crucial to guide medical decisions and treatment success. Machine learning (ML) has shown promise in this domain. However, its effectiveness critically depends on proper hyperparameter setting, a step that is not always performed systematically [...] Read more.

Accurate and early prediction of breast cancer recurrence is crucial to guide medical decisions and treatment success. Machine learning (ML) has shown promise in this domain. However, its effectiveness critically depends on proper hyperparameter setting, a step that is not always performed systematically in the development of ML models. In this study, we aimed to highlight the impact that this process has on the final performance of ML models through a real-world case study by predicting the five-year recurrence of breast cancer patients. We compared the performance of five ML algorithms (Logistic Regression, Decision Tree, Gradient Boosting, eXtreme Gradient Boost, and Deep Neural Network) before and after optimizing their hyperparameters. Simpler algorithms showed better performance using the default hyperparameters. However, after the optimization process, the more complex algorithms demonstrated superior performance. The AUCs obtained before and after adjustment were 0.7 vs. 0.84 for XGB, 0.64 vs. 0.75 for DNN, 0.7 vs. 0.8 for GB, 0.62 vs. 0.7 for DT, and 0.77 vs. 0.72 for LR. The results underscore the critical importance of hyperparameter selection in the development of ML algorithms for the prediction of cancer recurrence. Neglecting this step can undermine the potential of more powerful algorithms and lead to the choice of suboptimal models. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

16 pages, 1989 KiB

Open AccessArticle

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

by Sujiao Li, Wanjing Sun, Wei Li and Hongliu Yu

Appl. Sci. 2024, 14(8), 3417; https://doi.org/10.3390/app14083417 - 18 Apr 2024

Cited by 2 | Viewed by 1247

Abstract

Pattern recognition in myoelectric control that relies on the myoelectric activity associated with arm motions is an effective control method applied to myoelectric prostheses. Individuals with transhumeral amputation face significant challenges in effectively controlling their prosthetics, as muscle activation varies with changes in [...] Read more.

Pattern recognition in myoelectric control that relies on the myoelectric activity associated with arm motions is an effective control method applied to myoelectric prostheses. Individuals with transhumeral amputation face significant challenges in effectively controlling their prosthetics, as muscle activation varies with changes in arm positions, leading to a notable decrease in the accuracy of motion pattern recognition and consequently resulting in a high rejection rate of prosthetic devices. Therefore, to achieve high accuracy and arm position stability in upper-arm motion recognition, we propose a Deep Adversarial Inception Domain Adaptation (DAIDA) based on the Inception feature module to enhance the generalization ability of the model. Surface electromyography (sEMG) signals were collected from 10 healthy subjects and two transhumeral amputees while performing hand, wrist, and elbow motions at three arm positions. The recognition performance of different feature modules was compared, and ultimately, accurate recognition of upper-arm motions was achieved using the Inception C module with a recognition accuracy of 90.70% ± 9.27%. Subsequently, validation was performed using data from different arm positions as source and target domains, and the results showed that compared to the direct use of a convolutional neural network (CNN), the recognition accuracy on untrained arm positions increased by 75.71% (p < 0.05), with a recognition accuracy of 91.25% ± 6.59%. Similarly, in testing scenarios involving multiple arm positions, there was a significant improvement in recognition accuracy, with recognition accuracy exceeding 90% for both healthy subjects and transhumeral amputees. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

18 pages, 3048 KiB

Open AccessArticle

Constructing Features for Screening Neurodevelopmental Disorders Using Grammatical Evolution

by Eugenia I. Toki, Giorgos Tatsis, Jenny Pange and Ioannis G. Tsoulos

Appl. Sci. 2024, 14(1), 305; https://doi.org/10.3390/app14010305 - 29 Dec 2023

Cited by 1 | Viewed by 1382

Abstract

Developmental domains refer to different areas of a child’s growth and maturation, including physical, language, cognitive, and social–emotional skills. Understanding these domains helps parents, caregivers, and professionals track a child’s progress and identify potential areas of concern. Nevertheless, due to the high level [...] Read more.

Developmental domains refer to different areas of a child’s growth and maturation, including physical, language, cognitive, and social–emotional skills. Understanding these domains helps parents, caregivers, and professionals track a child’s progress and identify potential areas of concern. Nevertheless, due to the high level of heterogeneity and overlap, neurodevelopmental disorders may go undiagnosed in children for a crucial period. Detecting neurodevelopmental disorders at an early stage is fundamental. Digital tools like artificial intelligence can help clinicians with the early detection process. To achieve this, a new method has been proposed that creates artificial features from the original ones derived from the SmartSpeech project, using a feature construction procedure guided by the Grammatical Evolution technique. The new features from a machine learning model are used to predict neurodevelopmental disorders. Comparative experiments demonstrated that using the feature creation method outperformed other machine learning methods for predicting neurodevelopmental disorders. In many cases, the reduction in the test error reaches up to 65% to the next better one. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

Other

Jump to: Research

24 pages, 991 KiB

Open AccessSystematic Review

Machine-Learning-Based-Approaches for Sleep Stage Classification Utilising a Combination of Physiological Signals: A Systematic Review

by Haifa Almutairi, Ghulam Mubashar Hassan and Amitava Datta

Appl. Sci. 2023, 13(24), 13280; https://doi.org/10.3390/app132413280 - 15 Dec 2023

Cited by 6 | Viewed by 7464

Abstract

Increasingly prevalent sleep disorders worldwide significantly affect the well-being of individuals. Sleep disorder can be detected by dividing sleep into different stages. Hence, the accurate classification of sleep stages is crucial for detecting sleep disorders. The use of machine learning techniques on physiological [...] Read more.

Increasingly prevalent sleep disorders worldwide significantly affect the well-being of individuals. Sleep disorder can be detected by dividing sleep into different stages. Hence, the accurate classification of sleep stages is crucial for detecting sleep disorders. The use of machine learning techniques on physiological signals has shown promising results in the automatic classification of sleep stages. The integration of information from multichannel physiological signals has shown to further enhance the accuracy of such classification. Existing literature reviews focus on studies utilising a single channel of EEG signals for sleep stage classification. However, other review studies focus on models developed for sleep stage classification, utilising either a single channel of physiological signals or a combination of various physiological signals. This review focuses on the classification of sleep stages through the integration of combined multichannel physiological signals and machine learning methods. We conducted a comprehensive review spanning from the year 2000 to 2023, aiming to provide a thorough and up-to-date resource for researchers in the field. We analysed approximately 38 papers investigating sleep stage classification employing various machine learning techniques integrated with combined signals. In this study, we describe the models proposed in the existing literature for sleep stage classification, discuss their limitations, and identify potential areas for future research. Full article

(This article belongs to the Special Issue Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence for Healthcare

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI