Technological advances have enabled the generation of unique and complementary types of data or views (e.g. genomics, proteomics, metabolomics) and opened up a new era in multiview learning research with the potential to lead to new biomedical discoveries. We propose iDeepViewLearn (Interpretable Deep Learning Method for Multiview Learning) for learning nonlinear relationships in data from multiple views while achieving feature selection. iDeepViewLearn combines deep learning flexibility with the statistical benefits of data and knowledge-driven feature selection, giving interpretable results. Deep neural networks are used to learn view-independent low-dimensional embedding through an optimization problem that minimizes the difference between observed and reconstructed data, while imposing a regularization penalty on the reconstructed data. The normalized Laplacian of a graph is used to model bilateral relationships between variables in each view, therefore, encouraging selection of related variables. iDeepViewLearn is tested on simulated and two real-world data, including breast cancer-related gene expression and methylation data. iDeepViewLearn had competitive classification results and identified genes and CpG sites that differentiated between individuals who died from breast cancer and those who did not. The results of our real data application and simulations with small to moderate sample sizes suggest that iDeepViewLearn may be a useful method for small-sample-size problems compared to other deep learning methods for multiview learning.
(1) Background: The COVID-19 pandemic has raised concerns about the impact of underlying medical conditions on the health outcomes of people living with HIV (PLWH). This study aimed to assess how pre-existing chronic medical conditions affect the health outcomes of PLWH infected with COVID-19. (2) Methods: A retrospective study using data from the Minnesota Fairview network (January 1, 2020 - December 31, 2022) was conducted. Fisher’s Exact Test, Kruskal-Wallis rank sum test, and ordinal logistic regressions with Benjamini-Hochberg (BH) adjustment on p-values were used to assess the influence of chronic conditions on COVID-19 severity, adjusting for age and gender. (3) Results: Among 216 records, significant associations were found for stroke, chronic kidney disease, lung disease, and neurologic conditions (p<0.05). Type 1 diabetes was marginally significant (0.05<p<0.1). After adjusting for age and sex, stroke (p=0.0008, BH-adjusted p=0.0044) and chronic kidney disease (p=0.0003, BH-adjusted p=0.0033) significantly increased the risk of severe COVID-19 outcomes. (4) Conclusions: Pre-existing medical conditions should be considered in the clinical management and public health interventions for PLWH with COVID-19. Tailored strategies are essential to mitigate the higher risk of severe outcomes in PLWH with specific chronic comorbidities.
(1) Background: The Coronavirus Disease 2019 (COVID-19) pandemic has raised concerns about the impact of underlying medical conditions on the health outcomes of people living with HIV (PLWH). This study aimed to assess how pre-existing chronic medical conditions affect the health outcomes of PLWH infected with COVID-19. (2) Methods: A retrospective study using data from the Minnesota Fairview network (1 January 2020–31 December 2022) was conducted. Fisher’s exact test, the Kruskal–Wallis rank-sum test, and ordinal logistic regressions with a Benjamini–Hochberg (BH) adjustment on p-values were used to assess the influence of chronic conditions on COVID-19 severity, adjusting for age and gender. (3) Results: Among 216 records, significant associations were found for a stroke, chronic kidney disease, lung disease, and neurologic conditions (p < 0.05). Type 1 diabetes was marginally significant (0.05 < p < 0.1). After adjusting for age and sex, a stroke (p = 0.0008, BH-adjusted p = 0.0044) and chronic kidney disease (p = 0.0003, BH-adjusted p = 0.0033) significantly increased the risk of severe COVID-19 outcomes. (4) Conclusions: Pre-existing medical conditions should be considered in the clinical management and public health interventions for PLWH infected with COVID-19. Tailored strategies are essential to mitigate the higher risk of severe outcomes in PLWH with specific chronic comorbidities.
We develop scalable randomized kernel methods for jointly associating data from multiple sources and simultaneously predicting an outcome or classifying a unit into one of two or more classes. The proposed methods model nonlinear relationships in multiview data together with predicting a clinical outcome and are capable of identifying variables or groups of variables that best contribute to the relationships among the views. We use the idea that random Fourier bases can approximate shift-invariant kernel functions to construct nonlinear mappings of each view and we use these mappings and the outcome variable to learn view-independent low-dimensional representations. Through simulation studies, we show that the proposed methods outperform several other linear and nonlinear methods for multiview data integration. When the proposed methods were applied to gene expression, metabolomics, proteomics, and lipidomics data pertaining to COVID-19, we identified several molecular signatures forCOVID-19 status and severity. Results from our real data application and simulations with small sample sizes suggest that the proposed methods may be useful for small sample size problems. Availability: Our algorithms are implemented in Pytorch and interfaced in R and would be made available at: https://github.com/lasandrall/RandMVLearn.