Key result
Medication-driven LSTM-Gaussian process predicts ICU mortality while handling missing and noisy data.
Why the study?
ICU patients are vulnerable to infusion medications, but standard recurrent neural networks struggle to model long-term time-sequence treatment data with missing values to monitor real-time drug responses.
A deep learning approach using LSTM and Gaussian Process can model heterogeneous medication events and handle missing data to predict mortality risk in ICU patients.
Does not support clinical adoption; leaves open external validation of LSTM-GP models for ICU mortality prediction.
ICU patients are vulnerable to medications, especially infusion medications, and the rate and dosage of infusion drugs may worsen the condition. The mortality prediction model can monitor the real-time response of patients to drug treatment, evaluate doctors’ treatment plans to avoid severe situations such as inverse Drug-Drug Interactions (DDI), and facilitate the timely intervention and adjustment of doctor’s treatment plan. The treatment process of patients usually has a time-sequence relation (which usually has the missing data problem) in patients’ treatment history. The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network (RNN). However, sometimes, patients’ treatment can last for a long period of time, which RNN may not fit for modelling long time sequence data. Therefore, we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient, and the Natural Language Processing and Gaussian Process (GP), which can handle noisy, incomplete, sparse, heterogeneous and unevenly sampled patients’ medication records. In our work, we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients, while also handling the missing value problem using kernel-based Gaussian process. We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’ treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.
No takes yet. Share an insight, caveat, or question.
Shi et al. (2021) studied ICU patients. Heterogeneous medication events driven LSTM with Gaussian Process vs. Phased-LSTM was evaluated on Mortality prediction. A heterogeneous medication events driven LSTM combined with a kernel-based Gaussian process was proposed to predict ICU patient mortality and handle missing, noisy, and unevenly sampled data.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: