Multitask learning and benchmarking with clinical time series data
arXiv:1703.07771 · doi:10.1038/s41597-019-0103-9
The paper introduces four benchmark prediction tasks derived from the MIMIC-III intensive care database—mortality risk, length of stay, physiologic decline detection, and phenotype classification—and evaluates strong linear and neural baselines, including multitask learning and architectural modifications.
Abstract
Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absence of publicly available benchmark data sets. To address this problem, we propose four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database. These tasks cover a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification. We propose strong linear and neural baselines for all four tasks and evaluate the effect of deep supervision, multitask training and data-specific architectural modifications on the performance of neural models.
This version of the paper adds details about the generation of the benchmark tasks and describes improved neural baselines