PAR2COX: Survival-Informed Tensor Decomposition for Phenotyping and Risk Prediction from Irregular Longitudinal Data
Abstract
Accurate risk prediction is crucial for clinical-decision making, intervention planning, treatment and transplant allocation. However, longitudinal clinical data are often irregular and subject to censoring. We propose PAR2COX, a joint framework that integrates PARAFAC2 decomposition with Cox proportional hazards model, using patient-specific latent factors as covariates in the likelihood. The proposed alternating optimization framework jointly estimates phenotypes and survival parameters, enabling survival-guided representation learning. PAR2COX accommodates both historical patients with observed outcomes and current patients whose outcomes remain unknown. Numerical experiments and a case study based on MIMIC-IV data demonstrate improved risk stratification compared with existing approaches, highlighting the value of survival-informed phenotype learning.
Related
- A Combinatorial Benders Decomposition Framework for Two-Dimensional Irregular Bin Packing Problems with Convex Polygons
- Weekly sales forecasting using time series decomposition with irregular seasonality: A case study of Sony TV sales in the United States
- Geometry-Aware Latent Representation Learning for Drag Coefficient Prediction of Irregular Particles
- Bayesian joint modeling of longitudinal patient-reported outcomes and survival: an application to chronic obstructive pulmonary disease
- The R package LSJM for fitting location-scale joint models for a longitudinal marker and complex survival data
BibTeX
@misc{patalano2026par2cox,
title = {{PAR2COX: Survival-Informed Tensor Decomposition for Phenotyping and Risk Prediction from Irregular Longitudinal Data}},
author = {Mariafrancesca Patalano and Elif Konyar and Kamran Paynabar},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23705},
eprint = {2609.23705},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23705},
}
RIS
TY - UNPB
TI - PAR2COX: Survival-Informed Tensor Decomposition for Phenotyping and Risk Prediction from Irregular Longitudinal Data
AU - Mariafrancesca Patalano
AU - Elif Konyar
AU - Kamran Paynabar
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23705
UR - https://arxiv.org/abs/2609.23705
AB - Accurate risk prediction is crucial for clinical-decision making, intervention planning, treatment and transplant allocation. However, longitudinal clinical data are often irregular and subject to censoring. We propose PAR2COX, a joint framework that integrates PARAFAC2 decomposition with Cox proportional hazards model, using patient-specific latent factors as covariates in the likelihood. The proposed alternating optimization framework jointly estimates phenotypes and survival parameters, enabling survival-guided representation learning. PAR2COX accommodates both historical patients with observed outcomes and current patients whose outcomes remain unknown. Numerical experiments and a case study based on MIMIC-IV data demonstrate improved risk stratification compared with existing approaches, highlighting the value of survival-informed phenotype learning.
ER -