Rubik: Knowledge Guided Tensor Factorization and Completion for Health Data Analytics

By Yichen Wang, Robert Chen, Joydeep Ghosh, Joshua Charles Denny, Abel N. Kho, You Chen, Bradley A. Malin, Jimeng Sun. 2015

179 citations recorded by the source corpus.

Computational phenotyping is the process of converting heterogeneous electronic health records (EHRs) into meaningful clinical concepts. Unsupervised phenotyping methods have the potential to leverage a vast amount of labeled EHR data for phenotype discovery. However, existing unsupervised phenotyping methods do not incorporate current medical knowledge and cannot directly handle missing, or noisy data. We propose Rubik, a constrained non-negative tensor factorization and completion method for phenotyping. Rubik incorporates 1) guidance constraints to align with existing medical knowledge, and 2) pairwise constraints for obtaining distinct, non-overlapping phenotypes. Rubik also has built-in tensor completion that can significantly alleviate the impact of noisy and missing data. We utilize the Alternating Direction Method of Multipliers (ADMM) framework to tensor factorization and completion, which can be easily scaled through parallel computing. We evaluate Rubik on two EHR datasets, one of which contains 647,118 records for 7,744 patients from an outpatient clinic, the other of which is a public dataset containing 1,018,614 CMS claims records for 472,645 patients. Our results show that Rubik can discover more meaningful and distinct phenotypes than the baselines. In particular, by using knowledge guidance constraints, Rubik can also discover sub-phenotypes for several major diseases. Rubik also runs around seven times faster than current state-of-the-art tensor methods. Finally, Rubik is scalable to large datasets containing millions of EHR records.

Subfields: Computational Mathematics, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mathematics

In Electrical and Electronic Engineering

Citations in the corpus

Federated Tensor Factorization for Computational Phenotyping (2017, methodology): “…mode n to comprise the phenotypes. is, r th phenotype consists of r th column of factor matrices [13]. objective function of the tensor factorization with regularization terms for pairwise distinct constraints [28] is formulated It is rewritten with respect to mode-n matricization min where 1 ) .”
Mining Electronic Health Records: A Survey (2017, background): “…Descritive Atemporal [Roque et al. 2011; Bauer-Mehren et al. 2013] Descritive Temporal [Gotz et al. 2014; Schulam et al. 2015; Lasko et al. 2013; Wang et al. 2015a] Cross-Sectional [Wang et al. 2013b; Peissig et al. 2012; Pathak et al. 2012; Nadkarni et al. 2014; Chen et al. 2015; Chen et al.…”
COPA: Constrained PARAFAC2 for Sparse & Large Datasets (2018, unknown): “temporal phenotyping via EHR data. arXiv:1803.04572v1 [cs.LG] 12 Mar 2018 Table 1: Comparison of PARAFAC2 models and constrained tensor factorization applied to phenotyping Property Marble [14] Rubik [25] PARAFAC2 [5] SPARTan [20] Helwig [11] COPA Smoothness - - - - ✓ ✓ Sparsity ✓ ✓ - - - ✓ Scalabil”
Tensor Factorization for Precision Medicine in Heart Failure with Preserved Ejection Fraction (2017, unknown): “In addition, specifically designed tensor factorizations can also integrate additional domain-specific prior knowledge to constrain the tensor structure [27, 28].”
Time-Sensitive Recommendation From Recurrent User Activities (2015, methodology): “We compare with the stateof-art method [3] which considers poisson regression as the loss function to fit the number of events in each discretized time slot and shows better performance compared to other alternatives with the squared loss [25, 13, 22, 21].”