Feature group partitioning: an approach for depression severity prediction with class balancing using machine learning algorithms
Artículo
Materias > Ingeniería
Universidad Europea del Atlántico > Investigación > Producción Científica
Universidad Internacional Iberoamericana México > Investigación > Producción Científica
Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica
Universidad Internacional do Cuanza > Investigación > Artículos y libros
Universidad de La Romana > Investigación > Producción Científica
Abierto
Inglés
In contemporary society, depression has emerged as a prominent mental disorder that exhibits exponential growth and exerts a substantial influence on premature mortality. Although numerous research applied machine learning methods to forecast signs of depression. Nevertheless, only a limited number of research have taken into account the severity level as a multiclass variable. Besides, maintaining the equality of data distribution among all the classes rarely happens in practical communities. So, the inevitable class imbalance for multiple variables is considered a substantial challenge in this domain. Furthermore, this research emphasizes the significance of addressing class imbalance issues in the context of multiple classes. We introduced a new approach Feature group partitioning (FGP) in the data preprocessing phase which effectively reduces the dimensionality of features to a minimum. This study utilized synthetic oversampling techniques, specifically Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN), for class balancing. The dataset used in this research was collected from university students by administering the Burn Depression Checklist (BDC). For methodological modifications, we implemented heterogeneous ensemble learning stacking, homogeneous ensemble bagging, and five distinct supervised machine learning algorithms. The issue of overfitting was mitigated by evaluating the accuracy of the training, validation, and testing datasets. To justify the effectiveness of the prediction models, balanced accuracy, sensitivity, specificity, precision, and f1-score indices are used. Overall, comprehensive analysis demonstrates the discrimination between the Conventional Depression Screening (CDS) and FGP approach. In summary, the results show that the stacking classifier for FGP with SMOTE approach yields the highest balanced accuracy, with a rate of 92.81%. The empirical evidence has demonstrated that the FGP approach, when combined with the SMOTE, able to produce better performance in predicting the severity of depression. Most importantly the optimization of the training time of the FGP approach for all of the classifiers is a significant achievement of this research.
metadata
Shaha, Tumpa Rani; Begum, Momotaz; Uddin, Jia; Yélamos Torres, Vanessa; Alemany Iturriaga, Josep; Ashraf, Imran y Samad, Md. Abdus
mail
SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, vanessa.yelamos@funiber.org, josep.alemany@uneatlantico.es, SIN ESPECIFICAR, SIN ESPECIFICAR
(2024)
Feature group partitioning: an approach for depression severity prediction with class balancing using machine learning algorithms.
BMC Medical Research Methodology, 24 (1).
ISSN 1471-2288
![[img]](http://repositorio.unic.co.ao/style/images/fileicons/text.png) |
Texto
s12874-024-02249-8.pdf Available under License Creative Commons Attribution. Descargar (2MB) |
Resumen
In contemporary society, depression has emerged as a prominent mental disorder that exhibits exponential growth and exerts a substantial influence on premature mortality. Although numerous research applied machine learning methods to forecast signs of depression. Nevertheless, only a limited number of research have taken into account the severity level as a multiclass variable. Besides, maintaining the equality of data distribution among all the classes rarely happens in practical communities. So, the inevitable class imbalance for multiple variables is considered a substantial challenge in this domain. Furthermore, this research emphasizes the significance of addressing class imbalance issues in the context of multiple classes. We introduced a new approach Feature group partitioning (FGP) in the data preprocessing phase which effectively reduces the dimensionality of features to a minimum. This study utilized synthetic oversampling techniques, specifically Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN), for class balancing. The dataset used in this research was collected from university students by administering the Burn Depression Checklist (BDC). For methodological modifications, we implemented heterogeneous ensemble learning stacking, homogeneous ensemble bagging, and five distinct supervised machine learning algorithms. The issue of overfitting was mitigated by evaluating the accuracy of the training, validation, and testing datasets. To justify the effectiveness of the prediction models, balanced accuracy, sensitivity, specificity, precision, and f1-score indices are used. Overall, comprehensive analysis demonstrates the discrimination between the Conventional Depression Screening (CDS) and FGP approach. In summary, the results show that the stacking classifier for FGP with SMOTE approach yields the highest balanced accuracy, with a rate of 92.81%. The empirical evidence has demonstrated that the FGP approach, when combined with the SMOTE, able to produce better performance in predicting the severity of depression. Most importantly the optimization of the training time of the FGP approach for all of the classifiers is a significant achievement of this research.
| Tipo de Documento: | Artículo |
|---|---|
| Palabras Clave: | Machine learning; Depression prediction; Class balancing; Oversampling; SMOTE; ADASYN; Stratified cross validation; Burn depression checklist; Feature group partitioning |
| Clasificación temática: | Materias > Ingeniería |
| Divisiones: | Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Artículos y libros Universidad de La Romana > Investigación > Producción Científica |
| Depositado: | 17 Jun 2024 23:30 |
| Ultima Modificación: | 17 Jun 2024 23:30 |
| URI: | https://repositorio.unic.co.ao/id/eprint/12751 |
Acciones (logins necesarios)
 |
Ver Objeto |
<a href="/17849/1/1-s2.0-S2590005625001043-main.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>
en
open
Ultra Wideband radar-based gait analysis for gender classification using artificial intelligence
Gender classification plays a vital role in various applications, particularly in security and healthcare. While several biometric methods such as facial recognition, voice analysis, activity monitoring, and gait recognition are commonly used, their accuracy and reliability often suffer due to challenges like body part occlusion, high computational costs, and recognition errors. This study investigates gender classification using gait data captured by Ultra-Wideband radar, offering a non-intrusive and occlusion-resilient alternative to traditional biometric methods. A dataset comprising 163 participants was collected, and the radar signals underwent preprocessing, including clutter suppression and peak detection, to isolate meaningful gait cycles. Spectral features extracted from these cycles were transformed using a novel integration of Feedforward Artificial Neural Networks and Random Forests , enhancing discriminative power. Among the models evaluated, the Random Forest classifier demonstrated superior performance, achieving 94.68% accuracy and a cross-validation score of 0.93. The study highlights the effectiveness of Ultra-wideband radar and the proposed transformation framework in advancing robust gender classification.
Adil Ali Saleem mail , Hafeez Ur Rehman Siddiqui mail , Muhammad Amjad Raza mail , Sandra Dudley mail , Julio César Martínez Espinosa mail ulio.martinez@unini.edu.mx, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Isabel de la Torre Díez mail ,
Saleem
<a href="/17856/1/fpubh-13-1654645.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>
en
open
Background: Physical activity in children and adolescents represents one of the most important lifestyle factors to determine current and future health. Aim: The aim of the study is to assess the lifestyle and dietary factors linked to physical activity in younger populations across five countries in the Mediterranean region. Design: A total of 2,011 parents of children and adolescents (age range 6–17 years) participating to a preliminary survey of the DELICIOUS project were investigated to determine children's adequate physical activity level (identified using the short form of the international physical activity questionnaire) as well as diet quality parameters [measured as Youth-Healthy Eating Index (Y-HEI)] and eating and lifestyle factors (i.e., meal habits, sleep duration, screen time, etc.). Logistic regression analyses were performed to assess the odds ratios (ORs) and 95% confidence intervals (CIs) for the associations between variables of interest. Results: Younger children of younger parents currently working had higher rates and probability to have adequate physical activity. Multivariate analysis showed that children and adolescents who had breakfast (OR = 1.88, 95% CI: 1.38, 2.56) and often ate with their family (OR = 1.80, 95% CI: 0.90, 3.61) were more likely to have an adequate level of physical activity. Children and adolescents who reported a sleep duration (8–10 h) closest to the recommended one were significantly more likely to achieve adequate levels of physical activity (OR = 1.88, 95% CI: 1.38, 2.56). Conversely, those with more than 4 h of daily screen time were less likely to engage in adequate physical activity (OR = 0.77, 95% CI: 0.54, 1.10). Furthermore, children and adolescents in the highest tertile of YEHI scores showed a 60% greater likelihood of engaging in adequate physical activity (OR = 1.60, 95% CI: 1.27, 2.01). Conclusion: These results emphasize the importance of promoting healthy diet and lifestyle habits, including structured and high quality shared meals, sufficient sleep, and screen time moderation, as key strategies to support active behaviors in younger populations. Future interventions should focus on reinforcing these behaviors through parental guidance and community-based initiatives to foster lifelong healthy habits.
Alice Rosi mail , Francesca Scazzina mail , Maria Antonieta Touriz Bonifaz mail , Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Achraf Ammar mail , Khaled Trabelsi mail , Osama Abdelkarim mail , Mohamed Aly mail , Evelyn Frias-Toral mail , Juancho Pons mail , Laura Vázquez-Araújo mail , Josep Alemany Iturriaga mail josep.alemany@uneatlantico.es, Lorenzo Monasta mail , Nunzia Decembrino mail , Ana Mata mail , Adrián Chacón mail , Pablo Busó mail , Giuseppe Grosso mail ,
Rosi
<a class="ep_document_link" href="/17844/1/frai-1-1572645.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>
en
open
A systematic review of deep learning methods for community detection in social networks
Introduction: The rapid expansion of generated data through social networks has introduced significant challenges, which underscores the need for advanced methods to analyze and interpret these complex systems. Deep learning has emerged as an effective approach, offering robust capabilities to process large datasets, and uncover intricate relationships and patterns. Methods: In this systematic literature review, we explore research conducted over the past decade, focusing on the use of deep learning techniques for community detection in social networks. A total of 19 studies were carefully selected from reputable databases, including the ACM Library, Springer Link, Scopus, Science Direct, and IEEE Xplore. This review investigates the employed methodologies, evaluates their effectiveness, and discusses the challenges identified in these works. Results: Our review shows that models like graph neural networks (GNNs), autoencoders, and convolutional neural networks (CNNs) are some of the most commonly used approaches for community detection. It also examines the variety of social networks, datasets, evaluation metrics, and employed frameworks in these studies. Discussion: However, the analysis highlights several challenges, such as scalability, understanding how the models work (interpretability), and the need for solutions that can adapt to different types of networks. These issues stand out as important areas that need further attention and deeper research. This review provides meaningful insights for researchers working in social network analysis. It offers a detailed summary of recent developments, showcases the most impactful deep learning methods, and identifies key challenges that remain to be explored.
Mohamed El-Moussaoui mail , Mohamed Hanine mail , Ali Kartit mail , Mónica Gracia Villar mail monica.gracia@uneatlantico.es, Helena Garay mail helena.garay@uneatlantico.es, Isabel de la Torre Díez mail ,
El-Moussaoui
<a class="ep_document_link" href="/17825/1/foods-14-02648-v2.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>
en
open
Background: Western dietary patterns worldwide are increasingly dominated by energy-dense, nutrient-deficient industrial foods, often identified as ultra-processed foods (UPFs). Such products may have detrimental health implications, particularly if nutritionally inadequate. This study aimed to examine the intake of unhealthy UPFs among children and adolescents from five Mediterranean countries (Italy, Spain, Portugal, Egypt, and Lebanon) involved in the DELICIOUS project and to assess the association with dietary quality indicators. Methods: A survey was conducted with a sample of 2011 parents of children and adolescents aged 6 to 17 years to evaluate their dietary habits. Diet quality was assessed using the Youth Healthy Eating Index (Y-HEI), the KIDMED index to determine adherence to the Mediterranean diet, and compliance with national dietary guidelines. Results: Increased UPF consumption was not inherently associated with healthy or unhealthy specific food groups, although children and adolescents who consumed UPF daily were less likely to exhibit high overall diet quality and adherence to the Mediterranean diet. In all five countries, greater UPF intake was associated with poorer compliance with dietary recommendations concerning fats, sweets, meat, and legumes. Conclusions: Increased UPF consumption among Mediterranean children and adolescents is associated with an unhealthy dietary pattern, possibly marked by a high intake of fats, sweets, and meat, and a low consumption of legumes.
Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Alice Rosi mail , Evelyn Frias-Toral mail , Osama Abdelkarim mail , Mohamed Aly mail , Achraf Ammar mail , Raynier Zambrano-Villacres mail , Juancho Pons mail , Laura Vázquez-Araújo mail , Nunzia Decembrino mail , Alessandro Scuderi mail , Alice Leonardi mail , Lorenzo Monasta mail , Fernando Maniega Legarda mail , Ana Mata mail , Adrián Chacón mail , Pablo Busó mail , Giuseppe Grosso mail ,
Giampieri
<a href="/17831/1/s43856-025-01020-4.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>
en
open
Association between blood cortisol levels and numerical rating scale in prehospital pain assessment
Background Nowadays, there is no correlation between levels of cortisol and pain in the prehospital setting. The aim of this work was to determine the ability of prehospital cortisol levels to correlate to pain. Cortisol levels were compared with those of the numerical rating scale (NRS). Methods This is a prospective observational study looking at adult patients with acute disease managed by Emergency Medical Services (EMS) and transferred to the emergency department of two tertiary care hospitals. Epidemiological variables, vital signs, and prehospital blood analysis data were collected. A total of 1516 patients were included, the median age was 67 years (IQR: 51–79; range: 18–103) with 42.7% of females. The primary outcome was pain evaluation by NRS, which was categorized as pain-free (0 points), mild (1–3), moderate (4–6), or severe (≥7). Analysis of variance, correlation, and classification capacity in the form area under the curve of the receiver operating characteristic (AUC) curve were used to prospectively evaluate the association of cortisol with NRS. Results The median NRS and cortisol level are 1 point (IQR: 0–4) and 282 nmol/L (IQR: 143–433). There are 584 pain-free patients (38.5%), 525 mild (34.6%), 244 moderate (16.1%), and 163 severe pain (10.8%). Cortisol levels in each NRS category result in p < 0.001. The correlation coefficient between the cortisol level and NRS is 0.87 (p < 0.001). The AUC of cortisol to classify patients into each NRS category is 0.882 (95% CI: 0.853–0.910), 0.496 (95% CI: 0.446–0.545), 0.837 (95% CI: 0.803–0.872), and 0.981 (95% CI: 0.970–0.991) for the pain-free, mild, moderate, and severe categories, respectively. Conclusions Cortisol levels show similar pain evaluation as NRS, with high-correlation for NRS pain categories, except for mild-pain. Therefore, cortisol evaluation via the EMS could provide information regarding pain status.
Raúl López-Izquierdo mail , Elisa A. Ingelmo-Astorga mail , Carlos del Pozo Vegas mail , Santos Gracia Villar mail santos.gracia@uneatlantico.es, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Silvia Aparicio Obregón mail silvia.aparicio@uneatlantico.es, Rubén Calderón Iglesias mail ruben.calderon@uneatlantico.es, Ancor Sanz-García mail , Francisco Martín-Rodríguez mail ,
López-Izquierdo