Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization

Yuan Luo, Chengsheng Mao, Yiben Yang, Fei Wang, Faraz S. Ahmad, Donna Arnett, Marguerite R. Irvin, Sanjiv J. Shah
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:102-118, 2018.

Abstract

Hypertension is a heterogeneous syndrome in need of improved subtyping using phenotypic and genetic measurements so that patients in different subtypes share similar pathophysiologic mechanisms and respond more uniformly to targeted treatments. Existing machine learning approaches often face challenges in integrating phenotype and genotype information and presenting to clinicians an interpretable model. We aim to provide informed patient stratification by introducing Hybrid Non-negative Matrix Factorization (HNMF) on phenotype and genotype matrices. HNMF simultaneously approximates the phenotypic and genetic matrices using different appropriate loss functions, and generates patient subtypes, phenotypic groups and genetic groups. Unlike previous methods, HNMF approximates phenotypic matrix under Frobenius loss, and genetic matrix under Kullback-Leibler (KL) loss. We propose an alternating projected gradient method to solve the approximation problem. Simulation shows HNMF converges fast and accurately to the true factor matrices. On real-world clinical dataset, we used the patient factor matrix as features to predict main cardiac mechanistic outcomes. We compared HNMF with six different models using phenotype or genotype features alone, with or without NMF, or using joint NMF with only one type of loss. HNMF significantly outperforms all comparison models. HNMF also reveals intuitive phenotype-genotype interactions that characterize cardiac abnormalities.

Cite this Paper

BibTeX
@InProceedings{pmlr-v85-luo18a, title = {Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization}, author = {Luo, Yuan and Mao, Chengsheng and Yang, Yiben and Wang, Fei and Ahmad, Faraz S. and Arnett, Donna and Irvin, Marguerite R. and Shah, Sanjiv J.}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {102--118}, year = {2018}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {85}, series = {Proceedings of Machine Learning Research}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/luo18a/luo18a.pdf}, url = {https://proceedings.mlr.press/v85/luo18a.html}, abstract = {Hypertension is a heterogeneous syndrome in need of improved subtyping using phenotypic and genetic measurements so that patients in different subtypes share similar pathophysiologic mechanisms and respond more uniformly to targeted treatments. Existing machine learning approaches often face challenges in integrating phenotype and genotype information and presenting to clinicians an interpretable model. We aim to provide informed patient stratification by introducing Hybrid Non-negative Matrix Factorization (HNMF) on phenotype and genotype matrices. HNMF simultaneously approximates the phenotypic and genetic matrices using different appropriate loss functions, and generates patient subtypes, phenotypic groups and genetic groups. Unlike previous methods, HNMF approximates phenotypic matrix under Frobenius loss, and genetic matrix under Kullback-Leibler (KL) loss. We propose an alternating projected gradient method to solve the approximation problem. Simulation shows HNMF converges fast and accurately to the true factor matrices. On real-world clinical dataset, we used the patient factor matrix as features to predict main cardiac mechanistic outcomes. We compared HNMF with six different models using phenotype or genotype features alone, with or without NMF, or using joint NMF with only one type of loss. HNMF significantly outperforms all comparison models. HNMF also reveals intuitive phenotype-genotype interactions that characterize cardiac abnormalities.} }
Endnote
%0 Conference Paper %T Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization %A Yuan Luo %A Chengsheng Mao %A Yiben Yang %A Fei Wang %A Faraz S. Ahmad %A Donna Arnett %A Marguerite R. Irvin %A Sanjiv J. Shah %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-luo18a %I PMLR %P 102--118 %U https://proceedings.mlr.press/v85/luo18a.html %V 85 %X Hypertension is a heterogeneous syndrome in need of improved subtyping using phenotypic and genetic measurements so that patients in different subtypes share similar pathophysiologic mechanisms and respond more uniformly to targeted treatments. Existing machine learning approaches often face challenges in integrating phenotype and genotype information and presenting to clinicians an interpretable model. We aim to provide informed patient stratification by introducing Hybrid Non-negative Matrix Factorization (HNMF) on phenotype and genotype matrices. HNMF simultaneously approximates the phenotypic and genetic matrices using different appropriate loss functions, and generates patient subtypes, phenotypic groups and genetic groups. Unlike previous methods, HNMF approximates phenotypic matrix under Frobenius loss, and genetic matrix under Kullback-Leibler (KL) loss. We propose an alternating projected gradient method to solve the approximation problem. Simulation shows HNMF converges fast and accurately to the true factor matrices. On real-world clinical dataset, we used the patient factor matrix as features to predict main cardiac mechanistic outcomes. We compared HNMF with six different models using phenotype or genotype features alone, with or without NMF, or using joint NMF with only one type of loss. HNMF significantly outperforms all comparison models. HNMF also reveals intuitive phenotype-genotype interactions that characterize cardiac abnormalities.
APA
Luo, Y., Mao, C., Yang, Y., Wang, F., Ahmad, F.S., Arnett, D., Irvin, M.R. & Shah, S.J.. (2018). Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization. Proceedings of the 3rd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 85:102-118 Available from https://proceedings.mlr.press/v85/luo18a.html.

Related Material