Expert surgeons and deep learning models can predict the outcome of surgical hemorrhage from 1 min of video.

Journal: Scientific reports
Published Date: May 17, 2022

Abstract

Major vascular injury resulting in uncontrolled bleeding is a catastrophic and often fatal complication of minimally invasive surgery. At the outset of these events, surgeons do not know how much blood will be lost or whether they will successfully control the hemorrhage (achieve hemostasis). We evaluate the ability of a deep learning neural network (DNN) to predict hemostasis control ability using the first minute of surgical video and compare model performance with human experts viewing the same video. The publicly available SOCAL dataset contains 147 videos of attending and resident surgeons managing hemorrhage in a validated, high-fidelity cadaveric simulator. Videos are labeled with outcome and blood loss (mL). The first minute of 20 videos was shown to four, blinded, fellowship trained skull-base neurosurgery instructors, and to SOCALNet (a DNN trained on SOCAL videos). SOCALNet architecture included a convolutional network (ResNet) identifying spatial features and a recurrent network identifying temporal features (LSTM). Experts independently assessed surgeon skill, predicted outcome and blood loss (mL). Outcome and blood loss predictions were compared with SOCALNet. Expert inter-rater reliability was 0.95. Experts correctly predicted 14/20 trials (Sensitivity: 82%, Specificity: 55%, Positive Predictive Value (PPV): 69%, Negative Predictive Value (NPV): 71%). SOCALNet correctly predicted 17/20 trials (Sensitivity 100%, Specificity 66%, PPV 79%, NPV 100%) and correctly identified all successful attempts. Expert predictions of the highest and lowest skill surgeons and expert predictions reported with maximum confidence were more accurate. Experts systematically underestimated blood loss (mean error - 131 mL, RMSE 350 mL, R 0.70) and fewer than half of expert predictions identified blood loss > 500 mL (47.5%, 19/40). SOCALNet had superior performance (mean error - 57 mL, RMSE 295 mL, R 0.74) and detected most episodes of blood loss > 500 mL (80%, 8/10). In validation experiments, SOCALNet evaluation of a critical on-screen surgical maneuver and high/low-skill composite videos were concordant with expert evaluation. Using only the first minute of video, experts and SOCALNet can predict outcome and blood loss during surgical hemorrhage. Experts systematically underestimated blood loss, and SOCALNet had no false negatives. DNNs can provide accurate, meaningful assessments of surgical video. We call for the creation of datasets of surgical adverse events for quality improvement research.

Authors

  • Dhiraj J Pangal
    Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, California, USA. Electronic address: pangal@usc.edu.
  • Guillaume Kugener
    Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
  • Yichao Zhu
    Department of Neurosurgery, Keck School of Medicine of the University of Southern California, Los Angeles, California, USA.
  • Aditya Sinha
    Department of Neurosurgery, Keck School of Medicine of the University of Southern California, Los Angeles, California, USA.
  • Vyom Unadkat
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • David J Cote
    Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
  • Ben Strickland
    Department of Neurosurgery, Keck School of Medicine of the University of Southern California, Los Angeles, CA, USA.
  • Martin Rutkowski
    Department of Neurosurgery, Medical College of Georgia, Augusta, GA, USA.
  • Andrew Hung
    USC Institute of Urology, University of Southern California, Los Angeles, CA, USA.
  • Animashree Anandkumar
    Department of Computing & Mathematical Sciences, Caltech, Pasadena, CA.
  • X Y Han
    Department of Operations Research and Information Engineering, Cornell University, Ithaca, NY, USA.
  • Vardan Papyan
    Department of Mathematics, University of Toronto, Toronto, ON, Canada.
  • Bozena Wrobel
    2USC Caruso Department of Otolaryngology, Keck School of Medicine of the University of Southern California, Los Angeles.
  • Gabriel Zada
    Department of Neurological Surgery, Keck School of Medicine, University of Southern California, Los Angeles, CA, United States of America.
  • Daniel A Donoho
    Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, California, USA; Division of Neurosurgery, Department of Surgery, Texas Children's Hospital, Baylor College of Medicine, Houston, Texas, USA.

Keywords

External Resources

Popular Topics
Recent Journals