Multimodal data fusion using sparse canonical correlation analysis and cooperative learning: a COVID-19 cohort study.

Autor: Er AG; Stanford Center for Biomedical Informatics Research (BMIR), Department of Medicine, Stanford University, Stanford, CA, 94305, USA. ahmetgorkemer@gmail.com.; Department of Health Informatics, Graduate School of Informatics, Middle East Technical University, 06800, Ankara, Turkey. ahmetgorkemer@gmail.com.; Department of Infectious Diseases and Clinical Microbiology, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey. ahmetgorkemer@gmail.com., Ding DY; Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA., Er B; Department of Internal Medicine, Division of Intensive Care Medicine, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Uzun M; Department of Infectious Diseases and Clinical Microbiology, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Cakmak M; Department of Internal Medicine, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Sadee C; Stanford Center for Biomedical Informatics Research (BMIR), Department of Medicine, Stanford University, Stanford, CA, 94305, USA., Durhan G; Department of Radiology, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Ozmen MN; Department of Radiology, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Tanriover MD; Department of Internal Medicine, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Topeli A; Department of Internal Medicine, Division of Intensive Care Medicine, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Aydin Son Y; Department of Health Informatics, Graduate School of Informatics, Middle East Technical University, 06800, Ankara, Turkey., Tibshirani R; Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA.; Department of Statistics, Stanford University, Stanford, CA, 94305, USA., Unal S; Department of Infectious Diseases and Clinical Microbiology, Hacettepe University Faculty of Medicine, 06230, Ankara, Turkey., Gevaert O; Stanford Center for Biomedical Informatics Research (BMIR), Department of Medicine, Stanford University, Stanford, CA, 94305, USA. ogevaert@stanford.edu.; Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA. ogevaert@stanford.edu.
Jazyk: angličtina
Zdroj: NPJ digital medicine [NPJ Digit Med] 2024 May 07; Vol. 7 (1), pp. 117. Date of Electronic Publication: 2024 May 07.
DOI: 10.1038/s41746-024-01128-2
Abstrakt: Through technological innovations, patient cohorts can be examined from multiple views with high-dimensional, multiscale biomedical data to classify clinical phenotypes and predict outcomes. Here, we aim to present our approach for analyzing multimodal data using unsupervised and supervised sparse linear methods in a COVID-19 patient cohort. This prospective cohort study of 149 adult patients was conducted in a tertiary care academic center. First, we used sparse canonical correlation analysis (CCA) to identify and quantify relationships across different data modalities, including viral genome sequencing, imaging, clinical data, and laboratory results. Then, we used cooperative learning to predict the clinical outcome of COVID-19 patients: Intensive care unit admission. We show that serum biomarkers representing severe disease and acute phase response correlate with original and wavelet radiomics features in the LLL frequency channel (cor(Xu 1 , Zv 1 ) = 0.596, p value < 0.001). Among radiomics features, histogram-based first-order features reporting the skewness, kurtosis, and uniformity have the lowest negative, whereas entropy-related features have the highest positive coefficients. Moreover, unsupervised analysis of clinical data and laboratory results gives insights into distinct clinical phenotypes. Leveraging the availability of global viral genome databases, we demonstrate that the Word2Vec natural language processing model can be used for viral genome encoding. It not only separates major SARS-CoV-2 variants but also allows the preservation of phylogenetic relationships among them. Our quadruple model using Word2Vec encoding achieves better prediction results in the supervised task. The model yields area under the curve (AUC) and accuracy values of 0.87 and 0.77, respectively. Our study illustrates that sparse CCA analysis and cooperative learning are powerful techniques for handling high-dimensional, multimodal data to investigate multivariate associations in unsupervised and supervised tasks.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: