Noninvasive Identification of Hypotension Using Convolutional-Deconvolutional Networks

High-frequency identification of a patient’s hypotensive state allows for early notification of adverse events and long-term trends. Risks of complications such as heart attack, acute kidney injury, and mortality increase with duration of hypotension during surgery, and a hypotensive state can affect the appropriate medication choices and dosages for congestive heart failure patients. Current methods for identifying hypotension are based on blood pressure cuff measurements, which are low-frequency and must be manually collected, or catheterized blood pressure sensors, which are invasive, painful, and not necessarily usable for the youngest and smallest neonatal patients.This paper explores the potential of replacing the high-frequency hypotensive state produced by the invasive arterial catheter with a high-frequency projection from a fusion of multiple noninvasive sensors. These noninvasive sensors are available for a large majority of hospital patients, and have a lower risk of adverse effects ranging from patient discomfort to site infection. In addition, using multiple sensor inputs and a robust model allows for higher-reliability identification than single-sensor architectures.Our results demonstrate that by using a single flexible convolutional-deconvolutional neural network architecture, a patient’s hypotensive state may be reconstructed from any combination of the input sensor channels, with fidelity increasing in the number of available inputs.

[1]  Nicholas Bambos,et al.  A Practical Approach to Machine Learning for Clinical Decision Support , 2017 .

[2]  T. Pittman,et al.  Early hypotension worsens neurological outcome in pediatric patients with moderately severe head trauma. , 1998, Journal of pediatric surgery.

[3]  Nicholas Bambos,et al.  Optimal Health Monitoring via Wireless Body Area Networks , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[4]  Karel G M Moons,et al.  Intraoperative Hypotension and 1-Year Mortality after Noncardiac Surgery , 2009, Anesthesiology.

[5]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[6]  L Irestedt,et al.  Prediction of hypotension during spinal anesthesia for Cesarean section and its relation to the effect of crystalloid or colloid preload. , 2007, International journal of obstetric anesthesia.

[7]  Peter W. Glynn,et al.  Improving predictions of pediatric surgical durations with supervised learning , 2017, International Journal of Data Science and Analytics.

[8]  Terri Voepel-Lewis,et al.  How do pediatric anesthesiologists define intraoperative hypotension? , 2009, Paediatric anaesthesia.

[9]  Peter W. Glynn,et al.  Detecting Inaccurate Predictions of Pediatric Surgical Durations , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[10]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[11]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  W. Beattie,et al.  Association of Intraoperative Hypotension with Acute Kidney Injury after Elective Noncardiac Surgery , 2015, Anesthesiology.

[13]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Zhengyuan Zhou,et al.  Optimal Sensing for Patient Health Monitoring , 2018, 2018 IEEE International Conference on Communications (ICC).

[15]  A. Jaffe.  Long short-term memory recurrent neural networks for classification of acute hypotensive episodes , 2017 .

[16]  Nicholas Bambos,et al.  Physiological Waveform Imputation of Missing Data using Convolutional Autoencoders , 2018, 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom).

[17]  Leif Sörnmo,et al.  Prediction of Intradialytic Hypotension Using Photoplethysmography , 2010, IEEE Transactions on Biomedical Engineering.

[18]  MA Mneimneh,et al.  A rule-based approach for the prediction of acute hypotensive episodes , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[19]  JH Henriques,et al.  Prediction of acute hypotensive episodes using neural network multi-models , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[20]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  R Mukkamala,et al.  Forecasting acute hypotensive episodes in intensive care patients based on a peripheral arterial blood pressure waveform , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[22]  J. Rinehart,et al.  Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis , 2018, Anesthesiology.

[23]  M. Lemay,et al.  Computers in Cardiology / Physionet Challenge 2009: Predicting acute hypotensive episodes , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[24]  Zhengyuan Zhou,et al.  Sensing-Constrained Power Control in Digital Health , 2018, 2018 Annual American Control Conference (ACC).

[25]  W. Marsden.  I and J , 2012 .

[26]  Nicholas Bambos,et al.  Automatic Sleep Arousal Identification From Physiological Waveforms Using Deep Learning , 2018, 2018 Computing in Cardiology Conference (CinC).

[27]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[28]  G. Moody,et al.  Predicting acute hypotensive episodes: The 10th annual PhysioNet/Computers in Cardiology Challenge , 2010, 2009 36th Annual Computers in Cardiology Conference (CinC).