Reduced Impact of Obesity on Short-Term Surgical Outcomes, Patient-Reported Pain Scores, and 30-Day Readmission Rates After Complex Spinal Fusion (≥7 Levels) for Adult Deformity Correction

Elsamadicy, Aladine A.; Camara-Quintana, Joaquin; Kundishora, Adam J.; Lee, Megan; Freedman, Isaac G.; Long, Aaron S.; Qureshi, Tariq; Laurans, Maxwell; Tomak, Patrick; Karikari, Isaac O.

doi:10.1016/j.wneu.2019.02.165

Cited by 12 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of studying surgical video, studies describe adverse events using textual medical records, radiography, and laboratory results. Analysis of these extra-operative records and correlations with pre-operative risk factors and post-operative management can be useful 50 – 54 . However, this research omits a crucial determinant of the outcome of the surgical patient: the surgical event itself.…”

Section: Discussionmentioning

confidence: 99%

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

Pangal

Kugener

Zhu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

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, R2 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, R2 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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Pangal

Kugener

Zhu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Analysis of these extra-operative records and correlations with preoperative risk factors and post-operative management can be useful. [49][50][51][52][53] However, this research omits a crucial determinant of the outcome of the surgical patient: the surgical event itself. This omission limits root-cause analysis to only the extra-operative universe and prevents evaluation of the technical maneuvers and patient anatomic conditions that make adverse events more likely.…”

Section: Socalnet Performance Compared To Expertsmentioning

confidence: 99%

Expert Surgeons and Deep Learning Models Can Predict the Outcome of Surgical Hemorrhage from One Minute of Video

Pangal

Kugener

Zhu

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: 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. Methods: 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. Results: 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, R2 0.70) and fewer than half of expert predictions identified blood loss > 500mL (47.5%, 19/40). SOCALNet had superior performance (mean error -57 mL, RMSE 295mL, R2 0.74) and detected most episodes of blood loss > 500mL (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. Conclusion: 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.

show abstract

“…An additional Level III article by Savetti et al 40 reported no association between obesity and SSI in 387 spine surgery patients. The fourth article, a Level III article by Elsamadicy et al, 41 reviewed 112 ASD patients (BMI >30 kg/m 2 ) undergoing elective complex spinal fusion (>7 levels) for deformity correction and found no correlation with increased BMI and SSI.…”

Section: Multilevel Lumbar or Thoracolumbar Surgery: Studies Showing ...mentioning

confidence: 99%

Congress of Neurological Surgeons Systematic Review and Evidence-Based Guidelines for Perioperative Spine: Preoperative Surgical Risk Assessment

et al. 2021

View full text Add to dashboard Cite

BACKGROUND Patient factors (increased body mass index [BMI], smoking, and diabetes) may impact outcomes after spine surgery. There is a lack of consensus regarding which factors should be screened for and potentially modified preoperatively to optimize outcome. OBJECTIVE The purpose of this evidence-based clinical practice guideline is to determine if preoperative patient factors of diabetes, smoking, and increased BMI impact surgical outcomes. METHODS A systematic review of the literature for studies relevant to spine surgery was performed using the National Library of Medicine PubMed database and the Cochrane Library. Clinical studies evaluating the impact of diabetes or increased BMI with reoperation and/or surgical site infection (SSI) were selected for review. In addition, the impact of preoperative smoking on patients undergoing spinal fusion was reviewed. RESULTS A total of 699 articles met inclusion criteria and 64 were included in the systematic review. In patients with diabetes, a preoperative hemoglobin A1c (HbA1c) >7.5 mg/dL is associated with an increased risk of reoperation or infection after spine surgery. The review noted conflicting studies regarding the relationship between increased BMI and SSI or reoperation. Preoperative smoking is associated with increased risk of reoperation (Grade B). There is insufficient evidence that cessation of smoking before spine surgery decreases the risk of reoperation. CONCLUSION This evidence-based guideline provides a Grade B recommendation that diabetic individuals undergoing spine surgery should have a preoperative HbA1c test before surgery and should be counseled regarding the increased risk of reoperation or infection if the level is >7.5 mg/dL. There is conflicting evidence that BMI correlates with greater SSI rate or reoperation rate (Grade I). Smoking is associated with increased risk of reoperation (Grade B) in patients undergoing spinal fusion. The full guidelines can be accessed at https://www.cns.org/guidelines/browse-guidelines-detail/2-preoperative-surgical-risk-assessement

show abstract

Reduced Impact of Obesity on Short-Term Surgical Outcomes, Patient-Reported Pain Scores, and 30-Day Readmission Rates After Complex Spinal Fusion (≥7 Levels) for Adult Deformity Correction

Cited by 12 publications

References 28 publications

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

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

Expert Surgeons and Deep Learning Models Can Predict the Outcome of Surgical Hemorrhage from One Minute of Video

Congress of Neurological Surgeons Systematic Review and Evidence-Based Guidelines for Perioperative Spine: Preoperative Surgical Risk Assessment

Contact Info

Product

Resources

About