Deep Learning-Based Risk Model for Best Management of Closed Groin Incisions After Vascular Surgery.

Journal Article (Journal Article)

BACKGROUND: Reduced surgical site infection (SSI) rates have been reported with use of closed incision negative pressure therapy (ciNPT) in high-risk patients. METHODS: A deep learning-based, risk-based prediction model was developed from a large national database of 72,435 patients who received infrainguinal vascular surgeries involving upper thigh/groin incisions. Patient demographics, histories, laboratory values, and other variables were inputs to the multilayered, adaptive model. The model was then retrospectively applied to a prospectively tracked single hospital data set of 370 similar patients undergoing vascular surgery, with ciNPT or control dressings applied over the closed incision at the surgeon's discretion. Objective predictive risk scores were generated for each patient and used to categorize patients as "high" or "low" predicted risk for SSI. RESULTS: Actual institutional cohort SSI rates were 10/148 (6.8%) and 28/134 (20.9%) for high-risk ciNPT versus control, respectively (P < 0.001), and 3/31 (9.7%) and 5/57 (8.8%) for low-risk ciNPT versus control, respectively (P = 0.99). Application of the model to the institutional cohort suggested that 205/370 (55.4%) patients were matched with their appropriate intervention over closed surgical incision (high risk with ciNPT or low risk with control), and 165/370 (44.6%) were inappropriately matched. With the model applied to the cohort, the predicted SSI rate with perfect utilization would be 27/370 (7.3%), versus 12.4% actual rate, with estimated cost savings of $231-$458 per patient. CONCLUSIONS: Compared with a subjective practice strategy, an objective risk-based strategy using prediction software may be associated with superior results in optimizing SSI rates and costs after vascular surgery.

Full Text

Duke Authors

Cited Authors

  • Chang, B; Sun, Z; Peiris, P; Huang, ES; Benrashid, E; Dillavou, ED

Published Date

  • October 2020

Published In

Volume / Issue

  • 254 /

Start / End Page

  • 408 - 416

PubMed ID

  • 32197791

Electronic International Standard Serial Number (EISSN)

  • 1095-8673

Digital Object Identifier (DOI)

  • 10.1016/j.jss.2020.02.012


  • eng

Conference Location

  • United States