Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning
This work addresses the problem of inaccurate predictions in patient care for healthcare professionals, but it appears incremental as it builds on existing sequence prediction methods with a focus on personalization.
The paper tackles the challenge of patient-specific variability in clinical event sequence prediction by developing an adaptive framework that adjusts predictions for individual patients through online model updates, aiming to improve accuracy over population-based models.
Clinical event sequences consist of thousands of clinical events that represent records of patient care in time. Developing accurate prediction models for such sequences is of a great importance for defining representations of a patient state and for improving patient care. One important challenge of learning a good predictive model of clinical sequences is patient-specific variability. Based on underlying clinical complications, each patient's sequence may consist of different sets of clinical events. However, population-based models learned from such sequences may not accurately predict patient-specific dynamics of event sequences. To address the problem, we develop a new adaptive event sequence prediction framework that learns to adjust its prediction for individual patients through an online model update.