Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression.
- 1 January 2023
- journal article
- Vol. 225, 403-427
Abstract
We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient's data. To solve this problem, we propose a supervised contrastive learning framework that learns an embedding representation for each time step of a patient time series. Our framework learns the embedding space to have the following properties: (1) nearby points in the embedding space have similar predicted class probabilities, (2) adjacent time steps of the same time series map to nearby points in the embedding space, and (3) time steps with very different raw feature vectors map to far apart regions of the embedding space. To achieve property (3), we employ a nearest neighbor pairing mechanism in the raw feature space. This mechanism also serves as an alternative to "data augmentation", a key ingredient of contrastive learning, which lacks a standard procedure that is adequately realistic for clinical tabular data, to our knowledge. We demonstrate that our approach outperforms state-of-the-art baselines in predicting mortality of septic patients (MIMIC-III dataset) and tracking progression of cognitive impairment (ADNI dataset). Our method also consistently recovers the correct synthetic dataset embedding structure across experiments, a feat not achieved by baselines. Our ablation experiments show the pivotal role of our nearest neighbor pairing.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis With Competing Risks Based on Longitudinal DataIEEE Transactions on Biomedical Engineering, 2020
- Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for SepsisJAMA, 2019
- Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World GraphsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive careNature Medicine, 2018
- The MIMIC Code Repository: enabling reproducibility in critical care researchJournal of the American Medical Informatics Association, 2017
- Rey's Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer's diseaseNeuroImage: Clinical, 2017
- Clinical review: The liver in sepsisCritical Care, 2012
- Alzheimer's Disease Neuroimaging Initiative (ADNI)Neurology, 2010
- Staging Dementia Using Clinical Dementia Rating Scale Sum of Boxes ScoresArchives of Neurology, 2008
- Long Short-Term MemoryNeural Computation, 1997