Learning to Predict in-hospital mortality risk in intensive care unit with attention-based Temporal convolution network

Abstract

Background: Dynamic prediction of patients’ mortality risk in ICU with time series data is limited due to the high dimensionality, uncertainty with sampling intervals, and other issues. New deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset. Methods: 21139 records of ICU stays were analyzed and in total 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performances of attention-based TCN with traditional artificial intelligence (AI) method. Results: Area Under Receiver Operating Characteristic (AUCROC) and Area Under Precision-Recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48h after ICU admission were 0.837(0.824 -0.850) and 0.454. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, compared to the traditional AI method yield low sensitivity (<50%). Conclusions: Attention-based TCN model achieved better performance in prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. Attention-based TCN mortality risk model has the potential for helping decision-making in critical patients.

Early recognition of risk of critical adverse events based on deep neural decision gradient boosting

“…Recently, artificial intelligence technology has been widely applied in the medical field (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25). Statistical machine-learning methods based on sample data-driven models have also had widespread application in prediction models for critically ill patients (24,(26)(27)(28).…”

“…Recently, artificial intelligence technology has been widely applied in the medical field (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25). Statistical machine-learning methods based on sample data-driven models have also had widespread application in prediction models for critically ill patients (24,(26)(27)(28). It is a method that mines patient sample data through statistical learning methods to make a disease analysis based on the physical signs data after the processing and transformation of the data, so as to predict critical illness.…”