Continual Learning of Longitudinal Health Records
-
Jacob Armstrong, David A. Clifton
-
Institute of Biomedical Engineering, Oxford University
Continual learning denotes machine learning methods which can adapt to new environments while retaining and reusing knowledge gained from past experiences. Such methods address two issues encountered by models in non-stationary environments: ungeneralisability to new data, and the catastrophic forgetting of previous knowledge when retrained. This is a pervasive problem in clinical settings where patient data exhibits covariate shift not only between populations, but also continuously over time. However, while continual learning methods have seen nascent success in the imaging domain, they have been little applied to the multi-variate sequential data characteristic of critical care patient recordings. Here they evaluated a variety of continual learning methods on longitudinal ICU data in a series of representative healthcare scenarios.
Input variables : Health Records
Output Variables : 48 H mortality prediction
Metrics to Monitor
|
Statistical
|
:
|
Somers D |
Accuracy |
Precision and Recall |
Confusion Matrix |
F1 Score |
Roc and Auc |
Prevalence |
Detection Rate |
Balanced Accuracy |
Cohen's Kappa |
Concordance |
Gini Coefficent |
KS Statistic |
Youden's J Index
|
|
Business
|
:
|
Population at High Risk of Disease |
Risk by Geography |
Risk by Demographics |
Risk by Clinical Parameters |
Optimized Hospital Resource Utilization |
Decreased Cost of Care |
Decreased Patient Visits
|
|
Infrastructure
|
:
|
Log Bytes |
Logging/User/IAMPolicy |
Logging/User/VPN |
CPU Utilization |
Memory Usage |
Error Count |
Prediction Count |
Prediction Latencies |
Private Endpoint Prediction Latencies |
Private Endpoint Response Count
|
Visit Model :
aps.arxiv.org