Michael Blaivas1,2, Laura Blaivas3, Gary Philips4, Roland Merchant5, Mitchell Levy6, Adeel Abbasi6, Carsten Eickhoff7, Nathan Shapiro8, Keith Corl6. 1. Department of Medicine, University of South Carolina School of Medicine, Columbia, South Carolina, USA. 2. Department of Emergency Medicine, St Francis Hospital, Columbus, Georgia, USA. 3. Michigan State University, East Lansing, Michigan, USA. 4. Center for Biostatistics, Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, USA. 5. Department of Emergency Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA. 6. Department of Medicine, Division of Pulmonary Critical Care and Sleep, Warren Alert Medical School of Brown University, Providence, Rhode Island, USA. 7. Brown Center for Biomedical Informatics, Brown University, Providence, Rhode Island, USA. 8. Department of Emergency Medicine, Beth Israel Deaconess Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Abstract
OBJECTIVES: To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically ill patients. METHODS: We used a data set of IVC ultrasound (US) videos to train the LSTM network. The data set was created from IVC US videos of spontaneously breathing critically ill patients undergoing intravenous fluid resuscitation as part of 2 prior prospective studies. We randomly selected 90% of the IVC videos to train the LSTM network and 10% of the videos to test the LSTM network's ability to predict fluid responsiveness. Fluid responsiveness was defined as a greater than 10% increase in the cardiac index after a 500-mL fluid bolus, as measured by bioreactance. RESULTS: We analyzed 211 videos from 175 critically ill patients: 191 to train the LSTM network and 20 to test it. Using standard data augmentation techniques, we increased our sample size from 191 to 3820 videos. Of the 175 patients, 91 (52%) were fluid responders. The LSTM network was able to predict fluid responsiveness moderately well, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval [CI], 0.43-1.00), a positive likelihood ratio of infinity, and a negative likelihood ratio of 0.3 (95% CI, 0.12-0.77). In comparison, point-of-care US experts using video review offline and manual diameter measurement via software caliper tools achieved an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.83-0.99). CONCLUSIONS: We demonstrated that an LSTM network can be trained by using videos of IVC US to classify IVC collapse to predict fluid responsiveness. Our LSTM network performed moderately well given the small training cohort but worse than point-of-care US experts. Further training and testing of the LSTM network with a larger data sets is warranted.
OBJECTIVES: To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically illpatients. METHODS: We used a data set of IVC ultrasound (US) videos to train the LSTM network. The data set was created from IVC US videos of spontaneously breathing critically illpatients undergoing intravenous fluid resuscitation as part of 2 prior prospective studies. We randomly selected 90% of the IVC videos to train the LSTM network and 10% of the videos to test the LSTM network's ability to predict fluid responsiveness. Fluid responsiveness was defined as a greater than 10% increase in the cardiac index after a 500-mL fluid bolus, as measured by bioreactance. RESULTS: We analyzed 211 videos from 175 critically illpatients: 191 to train the LSTM network and 20 to test it. Using standard data augmentation techniques, we increased our sample size from 191 to 3820 videos. Of the 175 patients, 91 (52%) were fluid responders. The LSTM network was able to predict fluid responsiveness moderately well, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval [CI], 0.43-1.00), a positive likelihood ratio of infinity, and a negative likelihood ratio of 0.3 (95% CI, 0.12-0.77). In comparison, point-of-care US experts using video review offline and manual diameter measurement via software caliper tools achieved an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.83-0.99). CONCLUSIONS: We demonstrated that an LSTM network can be trained by using videos of IVC US to classify IVC collapse to predict fluid responsiveness. Our LSTM network performed moderately well given the small training cohort but worse than point-of-care US experts. Further training and testing of the LSTM network with a larger data sets is warranted.
Authors: Sangil Lee; Samuel H Lam; Thiago Augusto Hernandes Rocha; Ross J Fleischman; Catherine A Staton; Richard Taylor; Alexander T Limkakeng Journal: Cureus Date: 2021-09-01
Authors: Min Wu; Navchetan Awasthi; Nastaran Mohammadian Rad; Josien P W Pluim; Richard G P Lopata Journal: Sensors (Basel) Date: 2021-11-28 Impact factor: 3.576
Authors: Luca Mesin; Stefano Albani; Piero Policastro; Paolo Pasquero; Massimo Porta; Chiara Melchiorri; Gianluca Leonardi; Carlo Albera; Paolo Scacciatella; Pierpaolo Pellicori; Davide Stolfo; Andrea Grillo; Bruno Fabris; Roberto Bini; Alberto Giannoni; Antonio Pepe; Leonardo Ermini; Stefano Seddone; Gianfranco Sinagra; Francesco Antonini-Canterin; Silvestro Roatta Journal: Front Cardiovasc Med Date: 2022-01-21