Scholarlink

Background <p>Incisional hernia (IH) is a significant complication that occurs after midline&#xa0;laparotomy and is associated with high morbidity and economic impacts. A&#xa0;fundamental goal of preventing IH is to determine which patients are considered low- or&#xa0;high-risk, as modifications in prevention techniques have been justified in high-risk&#xa0;patients.</p> AIM <p>of this study was to externally validate the IHXGBoost-P model to&#xa0;assess its accuracy, generalizability, and clinical applicability in an independent cohort.</p> Methods: <p>A prospective cohort study was conducted in a tertiary hospital in Mexico&#xa0;(March 2021–December 2022) to externally validate the IHXGBoost-P model. Patients&#xa0;older than 18 years who underwent midline laparotomy and have a minimum follow-up&#xa0;of 24 months were included. The performance of the model was evaluated via area&#xa0;under the receiver operating characteristic curve (AUROC), accuracy, sensitivity,&#xa0;precision, specificity and calibration metrics.</p> Results <p>Of the 438 patients analyzed, 62 (14.1%) developed IH. The model&#xa0;demonstrated good discriminative capacity (Accuracy: 0.94 ± 0.015) and calibration&#xa0;(Brier score: 0.051). Key predictors included the risk of surgical site infection (odds&#xa0;ratio (OR): 3.01, 95% CI: 2.32–3.91), previous surgery, and body mass index (BMI).&#xa0;The specificity (0.97 ± 0.013) was determined to be high and useful for identifying lowrisk&#xa0;patients.</p> Conclusions <p>The IHXGBoost-P model is a reliable tool for predicting the risk of IH, with&#xa0;robust performance being observed in external validation. Its integration into clinical&#xa0;practice through a web application could optimize surgical decision-making to prevent&#xa0;IH.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

External validation of the IHXGboost-P model to predict incisional hernia after midline laparotomy

  • 期刊论文

  • 发表日期：

    2026年1月16日

查看全文
  • Edgard Efren Lozada Hernandez,
  • Tania A. Ramirez-delreal,
  • Dagoberto Armenta-Medina,
  • Sebastián Salazar-Colores

摘要

Background

Incisional hernia (IH) is a significant complication that occurs after midline laparotomy and is associated with high morbidity and economic impacts. A fundamental goal of preventing IH is to determine which patients are considered low- or high-risk, as modifications in prevention techniques have been justified in high-risk patients.

AIM

of this study was to externally validate the IHXGBoost-P model to assess its accuracy, generalizability, and clinical applicability in an independent cohort.

Methods:

A prospective cohort study was conducted in a tertiary hospital in Mexico (March 2021–December 2022) to externally validate the IHXGBoost-P model. Patients older than 18 years who underwent midline laparotomy and have a minimum follow-up of 24 months were included. The performance of the model was evaluated via area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, precision, specificity and calibration metrics.

Results

Of the 438 patients analyzed, 62 (14.1%) developed IH. The model demonstrated good discriminative capacity (Accuracy: 0.94 ± 0.015) and calibration (Brier score: 0.051). Key predictors included the risk of surgical site infection (odds ratio (OR): 3.01, 95% CI: 2.32–3.91), previous surgery, and body mass index (BMI). The specificity (0.97 ± 0.013) was determined to be high and useful for identifying lowrisk patients.

Conclusions

The IHXGBoost-P model is a reliable tool for predicting the risk of IH, with robust performance being observed in external validation. Its integration into clinical practice through a web application could optimize surgical decision-making to prevent IH.