Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning

TL;DR

This paper introduces an adaptive framework for predicting clinical event sequences that personalizes predictions for individual patients by updating the model online, addressing patient-specific variability in clinical data.

Contribution

It proposes a novel online adaptive learning method that personalizes clinical event sequence predictions, improving accuracy over traditional population-based models.

Findings

Enhanced prediction accuracy for individual patient sequences

Effective online model updating mechanism

Addresses variability in clinical event data

Abstract

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.