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

Feature importance-based interpretation of UMAP-visualized polymer space

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.

Application of Machine Learning to Diagnostics of Schizophrenia Patients Based on Event-Related Potentials

Schizophrenia is a major psychiatric disorder that significantly reduces the quality of life. Early treatment is extremely important in order to mitigate the long-term negative effects. In this paper, a machine learning based diagnostics of schizophrenia was designed. Classification models were applied to the event-related potentials (ERPs) of patients and healthy subjects performing the visual cued Go/NoGo task. The sample consisted of 200 adult individuals ranging in age from 18 to 50 years. In order to apply the machine learning models, various features were extracted from the ERPs. The process of feature extraction was parametrized through a special procedure and the parameters of this procedure were selected through a grid-search technique along with the model hyperparameters. Feature extraction was followed by sequential feature selection transformation in order to prevent overfitting and reduce the computational complexity. Various models were trained on the resulting feature set. The best model was support vector machines with a sensitivity and specificity of 91% and 90.8%, respectively.