Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
Open Access
- 10 July 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Scientific Reports
- Vol. 10 (1), 1-10
- https://doi.org/10.1038/s41598-020-67952-0
Abstract
The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of predictive modeling. In particular, forecasting acute hypotensive episodes (AHE) in intensive care patients has been of interest to researchers in critical care medicine. Given an advance warning of an AHE, care providers may be prompted to search for evolving disease processes and help mitigate negative clinical outcomes. However, the conventionally adopted definition of an AHE does not account for inter-patient variability and is restrictive. To reflect the wider trend of global clinical and research efforts in precision medicine, we introduce a patient-specific definition of AHE in this study and propose deep learning based models to predict this novel definition of AHE in data from multiple independent institutions. We provide extensive evaluation of the models by studying their accuracies in detecting patient-specific AHEs with lead-times ranging from 10 min to 1 hour before the onset of the event. The resulting models achieve AUROC values ranging from 0.57–0.87 depending on the lead time of the prediction. We demonstrate the generalizability and robustness of our approach through the use of independent multi-institutional data.This publication has 34 references indexed in Scilit:
- Utilizing ECG-Based Heartbeat Classification for Hypertrophic Cardiomyopathy IdentificationIEEE Transactions on Nanobioscience, 2015
- Optimizing mean arterial pressure in septic shock: a critical reappraisal of the literatureCritical Care, 2015
- A data-driven approach to optimized medication dosing: a focus on heparinIntensive Care Medicine, 2014
- High versus Low Blood-Pressure Target in Patients with Septic ShockThe New England Journal of Medicine, 2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine TranslationPublished by Association for Computational Linguistics (ACL) ,2014
- Relationship between Intraoperative Mean Arterial Pressure and Clinical Outcomes after Noncardiac SurgeryAnesthesiology, 2013
- A Practical Guide to Training Restricted Boltzmann MachinesLecture Notes in Computer Science, 2012
- Acute Physiology and Chronic Health Evaluation (APACHE) IV: Hospital mortality assessment for today’s critically ill patients*Critical Care Medicine, 2006
- Long Short-Term MemoryNeural Computation, 1997
- Better Bootstrap Confidence IntervalsJournal of the American Statistical Association, 1987