Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Electronic health records (EHR) enable machine learning methods like tensor factorization to extract computational phenotypes. Using Northwestern Medicine data (2000-2015), we analyzed breast, prostate, colorectal, and lung cancer cohorts to predict five-year mortality. Adding a supervised term, indication filtering, and social determinants of health (SDOH) covariates improved interpretability and performance. AUCs ranged from 0.623-0.694 (breast), 0.603-0.750 (prostate), 0.523-0.641 (colorectal), and 0.517-0.623 (lung). Constrained tensor factorization proves effective for deriving mortality-predictive phenotypes from sparse EHR data.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI250964 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Tensor decomposed distinguishable cluster. I. Triples decomposition.
J Chem Phys
August 2025
Max-Planck-Institute for Solid State Research, Heisenbergstraße 1, 70569 Stuttgart, Germany.
We present a cost-reduced approach for the distinguishable cluster approximation to coupled cluster with singles, doubles, and iterative triples (DC-CCSDT) based on a tensor decomposition of the triples amplitudes. The triples amplitudes and residuals are processed in the singular-value-decomposition (SVD) basis. Truncation of the SVD basis according to the values of the singular values together with the density fitting (or Cholesky) factorization of the electron repulsion integrals reduces the scaling of the method to N6, and the DC approximation removes the most expensive terms of the SVD triples residuals and at the same time improves the accuracy of the method.
View Article and Find Full Text PDFConstrained Tensor Factorization for Cancer Phenotyping and Mortality Prediction.
Stud Health Technol Inform
August 2025
Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
Electronic health records (EHR) enable machine learning methods like tensor factorization to extract computational phenotypes. Using Northwestern Medicine data (2000-2015), we analyzed breast, prostate, colorectal, and lung cancer cohorts to predict five-year mortality. Adding a supervised term, indication filtering, and social determinants of health (SDOH) covariates improved interpretability and performance.
View Article and Find Full Text PDFComputational and Statistical Guarantees for Tensor-on-Tensor Regression with Tensor Train Decomposition.
IEEE Trans Pattern Anal Mach Intell
July 2025
Recently, a tensor-on-tensor (ToT) regression model has been proposed to generalize tensor recovery, encompassing scenarios like scalar-on-tensor regression and tensor-on-vector regression. However, the exponential growth in tensor complexity poses challenges for storage and computation in ToT regression. To overcome this hurdle, tensor decompositions have been introduced, with the tensor train (TT)-based ToT model proving efficient in practice due to reduced memory requirements, enhanced computational efficiency, and decreased sampling complexity.
View Article and Find Full Text PDFBiomechanical Modeling, Muscle Synergy-Based Rehabilitation Assessment, and Real-Time Fatigue Monitoring for Piano-Integrated Upper Limb Therapy.
Biomimetics (Basel)
June 2025
School of Arts and Design, Yanshan University, Haigang District, Qinhuangdao 066000, China.
Piano-based occupational therapy has emerged as an engaging and effective rehabilitation strategy for improving upper limb motor functions. However, a lack of comprehensive biomechanical modeling, objective rehabilitation assessment, and real-time fatigue monitoring has limited its clinical optimization. This study developed a comprehensive "key-finger-exoskeleton" biomechanical model based on Hill-type muscle dynamics and rigid-body kinematics.
View Article and Find Full Text PDFUnraveling Complex Temporal Patterns in EHRs via Robust Irregular Tensor Factorization.
AMIA Jt Summits Transl Sci Proc
June 2025
Emory University, Atlanta, GA.
REPAR RE PAR
View Article and Find Full Text PDF