Machine Learning Techniques for the Diagnosis of Schizophrenia Based on Event-Related Potentials

Febles, Elsa Santos; Ortega, Marlis Ontivero; Sosa, Michell Valdés; Sahli, Hichem

doi:10.3389/fninf.2022.893788

Cited by 9 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the above purpose, wrappers and embedded methods are applicable because they are model‐dependent methods. In the present study, Boruta [25], which is a wrapper method based on the tree‐based model to measure the importance of features [26], was used, because it enables the feature selection based on the RF classifiers. In Boruta, the original features are shuffled to create randomized shadow features and compute the importance scores.…”

Section: Introductionmentioning

confidence: 99%

Feature importance‐based interpretation of UMAP‐visualized polymer space

Ehiro

2023

Molecular Informatics

View full text Add to dashboard Cite

Dimensionality reduction (DR) techniques are used for various purposes such as exploratory data analysis. A commonly employed linear DR technique is principal component analysis (PCA), which is one of the most popular methods for DR. Owing to its linear nature, PCA enables the determination of axes in a low‐dimensional space and the calculation of corresponding loading vectors. However, PCA cannot necessarily extract important features of non‐linearly distributed data. This study presents a technique aimed at aiding the interpretation of data reduced through non‐linear DR methods. In the proposed method, non‐linear dimensionally reduced data was clustered via a density‐based clustering method. Thereafter, the obtained cluster labels were classified by random forest (RF) classifiers. Further, feature importance (FI) of RF classifiers and Spearman's rank correlation coefficients between predictive probabilities to obtained clusters and original feature values were utilized for characterizing the visualized dimensionally reduced data. The results revealed that the proposed method can provide the interpretable FI‐based images of the handwritten digits dataset. Moreover, the proposed method was also applied to the polymer dataset. The study found that incorporating signed FI was advantageous in achieving a meaningful interpretation. Furthermore, Gaussian process regression was utilized to produce intuitive FI‐based heatmaps on a 2‐dimensional space for greater ease of understanding. Additionally, to enhance the interpretability of the obtained clusters, a feature selection technique called Boruta was applied. The Boruta feature selection method worked effectively to interpret the obtained clusters with limited and commonly important features. Additionally, the study suggested that computing FI solely from substructure‐based descriptors could further enhance the interpretability of the results. Finally, the automation of the proposed method was investigated, and through maximizing the target score based on the quality of both the DR and clustering, indicative results were automatically obtained for both the handwritten digits and polymer datasets.

show abstract

Section: Introductionmentioning

confidence: 99%