Safwan Wshah1, Beilei Xu2, John Steinharter3, Clifford Reilly3, Katelin Morrissette4. 1. University of Vermont, Innovation 417, Burlington, Vermont, United States. 2. FLX AI, Inc., New York, New York, United States. 3. University of Vermont, Larner College of Medicine, Burlington, Vermont, United States. 4. University of Vermont Medical Center, Department of Medicine, Division of Pulmonary and Critical Care Medicine, Burlington, Vermont, United States.
Abstract
Purpose: This is a foundational study in which multiorgan system point of care ultrasound (POCUS) and machine learning (ML) are used to mimic physician management decisions regarding the functional intravascular volume status (IVS) and need for diuretic therapy. We present this as an impactful use case of an application of ML in aided decision making for clinical practice. IVS represents complex physiologic interactions of the cardiac, renal, pulmonary, and other organ systems. In particular, we focus on vascular congestion and overload as an evolving concept in POCUS diagnosis and clinical relevance. It is critical for physicians to be able to evaluate IVS without disrupting workflow or exposing patients to unnecessary testing, radiation, or cost. This work utilized a small retrospective dataset as a feasibility test for ML binary classification of diuretic administration validated with clinical decision data. Future work will be directed toward artificial intelligence (AI) delivery at the bedside and assessment of the impact on patient-centered outcomes and physician workflow improvement. Approach: We retrospectively reviewed and processed 1039 POCUS video clips, including cardiac, thoracic, and inferior vena cava (IVC) views. Multiorgan POCUS clips were correlated with clinical data extracted from the electronic health record and deidentified for algorithm training and validation. We implemented a two-stream three-dimensional (3D) deep learning approach that fuses heart and IVC data to perform binary classification of the need for diuretic use. Results: Our proposed approach achieves high classification accuracy (84%) for the determination of diuretic use with 0.84 area under the receiver operating characteristic curve. Conclusions: Our two-stream 3D deep neural network is able to classify POCUS video clips that match physicians' classification for or against diuretic use with high accuracy. This serves as a foundational step in the progress toward AI-aided diagnosis and AI implementation in the field of IVS evaluation by POCUS.
Purpose: This is a foundational study in which multiorgan system point of care ultrasound (POCUS) and machine learning (ML) are used to mimic physician management decisions regarding the functional intravascular volume status (IVS) and need for diuretic therapy. We present this as an impactful use case of an application of ML in aided decision making for clinical practice. IVS represents complex physiologic interactions of the cardiac, renal, pulmonary, and other organ systems. In particular, we focus on vascular congestion and overload as an evolving concept in POCUS diagnosis and clinical relevance. It is critical for physicians to be able to evaluate IVS without disrupting workflow or exposing patients to unnecessary testing, radiation, or cost. This work utilized a small retrospective dataset as a feasibility test for ML binary classification of diuretic administration validated with clinical decision data. Future work will be directed toward artificial intelligence (AI) delivery at the bedside and assessment of the impact on patient-centered outcomes and physician workflow improvement. Approach: We retrospectively reviewed and processed 1039 POCUS video clips, including cardiac, thoracic, and inferior vena cava (IVC) views. Multiorgan POCUS clips were correlated with clinical data extracted from the electronic health record and deidentified for algorithm training and validation. We implemented a two-stream three-dimensional (3D) deep learning approach that fuses heart and IVC data to perform binary classification of the need for diuretic use. Results: Our proposed approach achieves high classification accuracy (84%) for the determination of diuretic use with 0.84 area under the receiver operating characteristic curve. Conclusions: Our two-stream 3D deep neural network is able to classify POCUS video clips that match physicians' classification for or against diuretic use with high accuracy. This serves as a foundational step in the progress toward AI-aided diagnosis and AI implementation in the field of IVS evaluation by POCUS.
Authors: Bernd Saugel; Stephan Ringmaier; Konstantin Holzapfel; Tibor Schuster; Veit Phillip; Roland M Schmid; Wolfgang Huber Journal: J Crit Care Date: 2011-01-26 Impact factor: 3.425
Authors: J Geoffrey Chase; Jean-Charles Preiser; Jennifer L Dickson; Antoine Pironet; Yeong Shiong Chiew; Christopher G Pretty; Geoffrey M Shaw; Balazs Benyo; Knut Moeller; Soroush Safaei; Merryn Tawhai; Peter Hunter; Thomas Desaive Journal: Biomed Eng Online Date: 2018-02-20 Impact factor: 2.819