Mortality prediction is the task of predicting the mortality of patients. It is important in medical decision support systems in order to prioritise the patients who have a high risk of mortality.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Health care is one of the most exciting frontiers in data mining and machine learning.
Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications.
However, flexible tools such as artificial neural networks (ANNs) suffer from a lack of interpretability limiting their acceptability to clinicians.
In order to predict the risk, quantitative features have been computed based on the heart rate signals of ICU patients.
SOTA for Mortality Prediction on MIMIC-III
Nevertheless, a main impediment for the adoption of Deep Learning in healthcare is its reduced interpretability, for in this field it is crucial to gain insight on the why of predictions, to assure that models are actually learning relevant features instead of spurious correlations.
We answer this question by deep reinforcement learning (RL) that jointly minimizes the measurement cost and maximizes predictive gain, by scheduling strategically-timed measurements.
When training clinical prediction models from electronic health records (EHRs), a key concern should be a model's ability to sustain performance over time when deployed, even as care practices, database systems, and population demographics evolve.
Laboratory test results are an important and generally high dimensional component of a patient's Electronic Health Record (EHR).