Network-based dimensionality reduction of high-dimensional, low-sample-size datasets

Kosztyán, Zsolt Tibor; Kurbucz, Marcell T.; Katona, Attila Imre

doi:10.1016/j.knosys.2022.109180

Cited by 9 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future studies, we would like to apply both SVM and GCN to a sample of adolescent subjects to determine whether our findings carry over to younger subject cohort. Classifying a young high-risk cohort has the potential to increase early intervention therapies and possibly improve psychosis outcomes (Khosla, 2006;Kosztyán, Kurbucz, & Katona, 2022).…”

Section: Discussionmentioning

confidence: 99%

Classification of psychosis spectrum disorders using graph convolutional networks with structurally constrained functional connectomes

Lewis,

Jiang,

Theis

et al. 2024

Preprint

View full text Add to dashboard Cite

To improve diagnostic strategies for psychiatric disorders, machine learning methods are being increasingly used. Recently, brain network features are being used as biological substrates to predict the diagnostic categories. Previous studies have predicted psychiatric disorders from controls with reasonable precision. Our goal was to classify a broad spectrum of psychotic disorders including those experiencing subsyndromal psychotic-like symptoms. Given the broader phenomenology, we used support vector machines (SVM) and graph convolutional networks (GCN) with a variety of edge selection methods and compared the accuracy of these models. Additionally, the MultiVERSE algorithm was used to generate network embeddings of the functional and structural networks for each subject as inputs for SVM. GCN yielded the highest classification accuracy of 70% compared with traditional and MultiVERSE inputs of SVM (about 50%) on all samples. For the GCN algorithm, the choice of edge selection was important in maximizing model accuracy. Investigation of network connectivity between patients and controls who were classified correctly identified the left and right Auditory 4 Complex as central regions of functional network communication. Our study shows the possibility of using deep learning methods to distinguish persons with subclinical psychosis symptoms and diagnosable disorders from controls which could help improve accuracy and reliability of clinical diagnosis and potentially help initiate early intervention or preventative strategies. Since GCN exploits graph structure and neighborhood relationships to classify and exceeded the accuracy of SVM, our findings suggest that graph structure and connectivity contribute to more accurate prediction of psychosis spectrum disorders from controls.

show abstract

Section: Discussionmentioning

confidence: 99%

Classification of psychosis spectrum disorders using graph convolutional networks with structurally constrained functional connectomes

Lewis,

Jiang,

Theis

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This package not only collects the up-to-date annual indicators from the aforementioned platforms but also preprocesses them for further analysis. This package is based on an improved version of a widely used R script [10,11,16] published together with the common database of COVID-19 reports and data360 indicators (see Kurbucz, 2020 [17]).…”

Section: Motivation and Significancementioning

confidence: 99%

“…The hdData360r package is based on an improved version of a widely used R script [10,11,16] published together with the common database of COVID-19 reports and data360 indicators (see Kurbucz, 2020 [17]).…”

Section: Impact and Conclusionmentioning

confidence: 99%

hdData360r: A high-dimensional panel data compiler for governance, trade, and competitiveness indicators of World Bank Group platforms

Kurbucz¹

2023

SoftwareX

Self Cite

View full text Add to dashboard Cite

“…[ 22 ] proposed a new interactive feature selection dimension reduction method, and compared it with LASSO, subset selection by validating on the given dataset. [ 23 ] developed a novel network-based dimensionality reduction method and applied it to the actual dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

Mortality prediction in ICU Using a Stacked Ensemble Model

Ren

Zhao

Zhang

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Artificial intelligence (AI) technology has huge scope in developing models to predict the survival rate of critically ill patients in the intensive care unit (ICU). The availability of electronic clinical data has led to the widespread use of various machine learning approaches in this field. Innovative algorithms play a crucial role in boosting the performance of models. This study uses a stacked ensemble model to predict mortality in ICU by incorporating the clinical severity scoring results, in which several machine learning algorithms are employed to compare the performance. The experimental results show that the stacked ensemble model achieves good performance compared with the model without integrating the severity scoring results, which has the area under curve (AUC) of 0.879 and 0.862, respectively. To improve the performance of prediction, two feature subsets are obtained based on different feature selection techniques, labeled as SetS and SetT. Evaluation performances show that the SEM based on the SetS achieves a higher AUC value (0.879 and 0.860). Finally, the SHapley Additive exPlanations (SHAP) analysis is employed to interpret the correlation between the risk features and the outcome.

show abstract

Network-based dimensionality reduction of high-dimensional, low-sample-size datasets

Cited by 9 publications

References 34 publications

Classification of psychosis spectrum disorders using graph convolutional networks with structurally constrained functional connectomes

Classification of psychosis spectrum disorders using graph convolutional networks with structurally constrained functional connectomes

hdData360r: A high-dimensional panel data compiler for governance, trade, and competitiveness indicators of World Bank Group platforms

Mortality prediction in ICU Using a Stacked Ensemble Model

Contact Info

Product

Resources

About