Time-to-event estimation by re-defining time

• Published in: Journal of biomedical informatics Vol. 100; p. 103326
• Main Authors: Cao, Xi Hang, Han, Chao, Glass, Lucas M., Kindman, Allen, Obradovic, Zoran
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2019
• Subjects: Concept embedding; Knowledge discovery; Regime identification; Representation learning; Survival analysis; Time-to-event estimation; Representation learning; Survival analysis; Concept embedding; Knowledge discovery; Regime identification; Time-to-event estimation
• ISSN: 1532-0464; 1532-0480
• DOI: 10.1016/j.jbi.2019.103326

[Display omitted] •Indirect inference of event occurrence times via time concept vectors.•Efficient joint learning of model parameters and time concept vectors.•Demonstrated the effectiveness, interpretability, and scalability of the proposed model. The primary goal of a time-to-event estimation model is to accurately infer the occurrence time of a target event. Most existing studies focus on developing new models to effectively utilize the information in the censored observations. In this paper, we propose a model to tackle the time-to-event estimation problem from a completely different perspective. Our model relaxes a fundamental constraint that the target variable, time, is a univariate number which satisfies a partial order. Instead, the proposed model interprets each event occurrence time as a time concept with a vector representation. We hypothesize that the model will be more accurate and interpretable by capturing (1) the relationships between features and time concept vectors and (2) the relationships among time concept vectors. We also propose a scalable framework to simultaneously learn the model parameters and time concept vectors. Rigorous experiments and analysis have been conducted in medical event prediction task on seven gene expression datasets. The results demonstrate the efficiency and effectiveness of the proposed model. Furthermore, similarity information among time concept vectors helped in identifying time regimes, thus leading to a potential knowledge discovery related to the human cancer considered in our experiments.