Applications of Multivariate Statistical and Data Mining Analyses to the Search for Biomarkers of Sensorineural Hearing Loss, Tinnitus, and Vestibular Dysfunction

Biomarkers: Promising and valuable tools towards diagnosis, prognosis and treatment of Covid-19 and other diseases

The use of biomarkers as early warning systems in the evaluation of disease risk has increased markedly in the last decade. Biomarkers are indicators of typical biological processes, pathogenic processes, or pharmacological reactions to therapy. The application and identification of biomarkers in the medical and clinical fields have an enormous impact on society. In this review, we discuss the history, various definitions, classifications, characteristics, and discovery of biomarkers. Furthermore, the potential application of biomarkers in the diagnosis, prognosis, and treatment of various diseases over the last decade are reviewed. The present review aims to inspire readers to explore new avenues in biomarker research and development.

Exploring the Mechanism and Suggesting Combination Therapies for HDAC Inhibitors in Androgen Receptor-Null Prostate Cancer Using Multivariate Statistical Analysis and Data Mining Techniques

Previously, we showed that novel histone deacetylase (HDAC) inhibitors, N1-hydroxy-N ⁸-(4-(pyridine-2-carbothioamido)phenyl)octanediamide (Jazz90) and [chlorido(η⁵-pentamethylcyclopentadienyl)(N1-hydroxy-N8-(4-(pyridine-2-carbothioamido-κ² N, S)phenyl)octanediamide)rhodium(III)] chloride (Jazz167), have cytostatic and anti-angiogenic effects in androgen receptor-negative prostate cancer cells and are also non-toxic in BALB/c mice. However, only univariate statistical analysis was carried out to determine the role of individual proteins. In this study, multivariate statistical analyses (MVAs) and data mining procedures were carried out with the objective of determining the molecular networks that explain the growth inhibitory potential of Jazz90 and Jazz167 in PC3 cells and to determine potential inhibitors that can be used in combination with these HDAC inhibitors. Lasso regression revealed that angiogenic factors, vascular endothelial growth factor-A (VEGF-A), and vascular endothelial growth factor receptor-2 (VEGFR-2), alongside HDAC inhibition, predicted the reduction in cell number with an adjusted R ² value of 0.99 following Jazz90 treatment, whereas VEGFR-2, acetylation of histone-3, and HDAC inhibition predicted cell number with an adjusted R ² value of 0.84 following Jazz167 treatment. These results were further followed up with ridge regression, hierarchical cluster analysis, random forest classification (RFC), and support vector machines. RFC and support vector machines also predicted the treatment groups with a 100% accuracy. MVAs also revealed that Jazz90 should be examined in combination with epithelial to mesenchymal transitioning inhibitors, such as simvastatin and olaparib, whereas Jazz167 should be examined with venetoclax or navitoclax. Future studies should also address the roles of VEGF-A and VEGFR-2 in cellular proliferation, whereas p27 function should be examined for its role in PC3 cell migration.

Using Base-ml to Learn Classification of Common Vestibular Disorders on DizzyReg Registry Data

Background: Multivariable analyses (MVA) and machine learning (ML) applied on large datasets may have a high potential to provide clinical decision support in neuro-otology and reveal further avenues for vestibular research. To this end, we build base-ml, a comprehensive MVA/ML software tool, and applied it to three increasingly difficult clinical objectives in differentiation of common vestibular disorders, using data from a large prospective clinical patient registry (DizzyReg).

Methods: Base-ml features a full MVA/ML pipeline for classification of multimodal patient data, comprising tools for data loading and pre-processing; a stringent scheme for nested and stratified cross-validation including hyper-parameter optimization; a set of 11 classifiers, ranging from commonly used algorithms like logistic regression and random forests, to artificial neural network models, including a graph-based deep learning model which we recently proposed; a multi-faceted evaluation of classification metrics; tools from the domain of “Explainable AI” that illustrate the input distribution and a statistical analysis of the most important features identified by multiple classifiers.

Results: In the first clinical task, classification of the bilateral vestibular failure (N = 66) vs. functional dizziness (N = 346) was possible with a classification accuracy ranging up to 92.5% (Random Forest). In the second task, primary functional dizziness (N = 151) vs. secondary functional dizziness (following an organic vestibular syndrome) (N = 204), was classifiable with an accuracy ranging from 56.5 to 64.2% (k-nearest neighbors/logistic regression). The third task compared four episodic disorders, benign paroxysmal positional vertigo (N = 134), vestibular paroxysmia (N = 49), Menière disease (N = 142) and vestibular migraine (N = 215). Classification accuracy ranged between 25.9 and 50.4% (Naïve Bayes/Support Vector Machine). Recent (graph-) deep learning models classified well in all three tasks, but not significantly better than more traditional ML methods. Classifiers reliably identified clinically relevant features as most important toward classification.

Conclusion: The three clinical tasks yielded classification results that correlate with the clinical intuition regarding the difficulty of diagnosis. It is favorable to apply an array of MVA/ML algorithms rather than a single one, to avoid under-estimation of classification accuracy. Base-ml provides a systematic benchmarking of classifiers, with a standardized output of MVA/ML performance on clinical tasks. To alleviate re-implementation efforts, we provide base-ml as an open-source tool for the community.