English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The aim of this paper is to design a deep learning-based model to predictproximal femoral strength using multi-view information fusion. Method: Wedeveloped new models using multi-view variational autoencoder (MVAE) forfeature representation learning and a product of expert (PoE) model formulti-view information fusion. We applied the proposed models to an in-houseLouisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345African Americans and 586 Caucasians. With an analytical solution of theproduct of Gaussian distribution, we adopted variational inference to train thedesigned MVAE-PoE model to perform common latent feature extraction. Weperformed genome-wide association studies (GWAS) to select 256 genetic variantswith the lowest p-values for each proximal femoral strength and integratedwhole genome sequence (WGS) features and DXA-derived imaging features topredict proximal femoral strength. Results: The best prediction model for fallfracture load was acquired by integrating WGS features and DXA-derived imagingfeatures. The designed models achieved the mean absolute percentage error of18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads usinglinear models of fall loading, nonlinear models of fall loading, and nonlinearmodels of stance loading, respectively. Compared to existing multi-viewinformation fusion methods, the proposed MVAE-PoE achieved the bestperformance. Conclusion: The proposed models are capable of predicting proximalfemoral strength using WGS features and DXA-derived imaging features. Thoughthis tool is not a substitute for FEA using QCT images, it would make improvedassessment of hip fracture risk more widely available while avoiding theincreased radiation dosage and clinical costs from QCT.

Multi-view information fusion using multi-view variational autoencoders to predict proximal femoral strength