Benjamin Y Andrew1, Elias Y Andrew2, Anne D Cherry3, Jennifer N Hauck3, Alina Nicoara3, Carl F Pieper4, Mark Stafford-Smith5. 1. Department of Anesthesiology, Duke University Medical Center, Durham, NC; Clinical Research Training Program, Duke University School of Medicine, Durham, NC. 2. Department of Electrical and Computer Engineering, School of Engineering and Applied Sciences, The George Washington University, Washington, DC. 3. Department of Anesthesiology, Duke University Medical Center, Durham, NC. 4. Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC. 5. Department of Anesthesiology, Duke University Medical Center, Durham, NC. Electronic address: mark.staffordsmit@dm.duke.edu.
Abstract
OBJECTIVE: Intraoperative Doppler-determined renal resistive index (RRI) is a promising early acute kidney injury (AKI) biomarker. As RRI continues to be studied, its clinical usefulness and robustness in research settings will be linked to the ease, efficiency, and precision with which it can be interpreted. Therefore, the authors assessed the usefulness of computer vision technology as an approach to developing an automated RRI-estimating algorithm with equivalent reliability and reproducibility to human experts. DESIGN: Retrospective. SETTING: Single-center, university hospital. PARTICIPANTS: Adult cardiac surgery patients from 7/1/2013 to 7/10/2014 with intraoperative transesophageal echocardiography-determined renal blood flow measurements. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Renal Doppler waveforms were obtained retrospectively and assessed by blinded human expert raters. Images (430) were divided evenly into development and validation cohorts. An algorithm for automated RRI analysis was built using computer vision techniques and tuned for alignment with experts using bootstrap resampling in the development cohort. This algorithm then was applied to the validation cohort for an unbiased assessment of agreement with human experts. Waveform analysis time per image averaged 0.144 seconds. Agreement was excellent by intraclass correlation coefficient (0.939; 95% confidence interval [CI] 0.921 to 0.953) and in Bland-Altman analysis (mean difference [human-algorithm] -0.0015; 95% CI -0.0054 to 0.0024), without evidence of systematic bias. CONCLUSION: The authors confirmed the value of computer vision technology to develop an algorithm for RRI estimation from automatically processed intraoperative renal Doppler waveforms. This simple-to-use and efficient tool further adds to the clinical and research value of RRI, already the "earliest" among several early AKI biomarkers being assessed.
OBJECTIVE: Intraoperative Doppler-determined renal resistive index (RRI) is a promising early acute kidney injury (AKI) biomarker. As RRI continues to be studied, its clinical usefulness and robustness in research settings will be linked to the ease, efficiency, and precision with which it can be interpreted. Therefore, the authors assessed the usefulness of computer vision technology as an approach to developing an automated RRI-estimating algorithm with equivalent reliability and reproducibility to human experts. DESIGN: Retrospective. SETTING: Single-center, university hospital. PARTICIPANTS: Adult cardiac surgery patients from 7/1/2013 to 7/10/2014 with intraoperative transesophageal echocardiography-determined renal blood flow measurements. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Renal Doppler waveforms were obtained retrospectively and assessed by blinded human expert raters. Images (430) were divided evenly into development and validation cohorts. An algorithm for automated RRI analysis was built using computer vision techniques and tuned for alignment with experts using bootstrap resampling in the development cohort. This algorithm then was applied to the validation cohort for an unbiased assessment of agreement with human experts. Waveform analysis time per image averaged 0.144 seconds. Agreement was excellent by intraclass correlation coefficient (0.939; 95% confidence interval [CI] 0.921 to 0.953) and in Bland-Altman analysis (mean difference [human-algorithm] -0.0015; 95% CI -0.0054 to 0.0024), without evidence of systematic bias. CONCLUSION: The authors confirmed the value of computer vision technology to develop an algorithm for RRI estimation from automatically processed intraoperative renal Doppler waveforms. This simple-to-use and efficient tool further adds to the clinical and research value of RRI, already the "earliest" among several early AKI biomarkers being assessed.
Authors: Paaladinesh Thavendiranathan; Shizhen Liu; Saurabh Datta; Michael Walls; Adrien Nitinunu; Thomas Van Houten; Nicholas A Tomson; Laura Vidmar; Bogdan Georgescu; Yang Wang; Seshadri Srinivasan; Nathalie De Michelis; Subha V Raman; Thomas Ryan; Mani A Vannan Journal: J Am Soc Echocardiogr Date: 2011-11-21 Impact factor: 5.251
Authors: Jeremiah R Brown; William M Hisey; Emily J Marshall; Donald S Likosky; Elizabeth L Nichols; Allen D Everett; Sara K Pasquali; Marshall L Jacobs; Jeff P Jacobs; Chirag R Parikh Journal: Ann Thorac Surg Date: 2016-06-17 Impact factor: 4.330
Authors: Massoud Zolgharni; Niti M Dhutia; Graham D Cole; M Reza Bahmanyar; Siana Jones; S M Afzal Sohaib; Sarah B Tai; Keith Willson; Judith A Finegold; Darrel P Francis Journal: IEEE Trans Med Imaging Date: 2014-05 Impact factor: 10.048
Authors: Niti M Dhutia; Massoud Zolgharni; Michael Mielewczik; Madalina Negoita; Stefania Sacchi; Karikaran Manoharan; Darrel P Francis; Graham D Cole Journal: Int J Cardiovasc Imaging Date: 2017-02-20 Impact factor: 2.357
Authors: Anne D Cherry; Jennifer N Hauck; Benjamin Y Andrew; Yi-Ju Li; Jamie R Privratsky; Lakshmi D Kartha; Alina Nicoara; Annemarie Thompson; Joseph P Mathew; Mark Stafford-Smith Journal: J Clin Anesth Date: 2019-11-04 Impact factor: 9.452