Nica, Alexandru

ABSTRACT Predicting delayed graft function (DGF) relies on donor, recipient, and perioperative factors. Despite the growing recognition that DGF duration strongly influences patient outcomes, no models currently address or predict its impact—highlighting an important gap in current research and clinical practice. This study aimed to develop an ensemble‐based machine learning model using perioperative data to predict DGF occurrence and duration. The gradient‐boosted decision trees model was trained and validated on 2725 patients, with k‐fold cross‐validation in an external cohort of 284 patients. Model performance was evaluated based on accuracy, ROC‐AUC, and other metrics using R and Python libraries. The binary DGF prediction model achieved a ROC‐AUC of 0.77, while the DGF duration classification model had an accuracy of 79.2%. DGF duration AUC values by time interval were 0.76 for 0–1 weeks, 0.81 for >1–2 weeks, 0.80 for >2–3 weeks, and 0.87 for >3 weeks; the overall macro‐averaged AUC was 0.81. The mean Brier score for multi‐class predictions was 0.14. External validation showed a 78% accuracy for DGF duration prediction. Acute kidney injury (AKI) and donor donation after circulatory death (DCD) status were key DGF predictors. The use of gradient‐boosted decision trees (GBDT) improves the prediction of both the likelihood and duration of DGF, addressing a current gap in kidney transplant patient care. By facilitating personalized transplant care, this model supports more effective perioperative planning and timely interventions, which may contribute to better patient outcomes.

BACKGROUND: Although most transplant centers preferentially offer minimally invasive approaches to donor nephrectomies, there remains less standardization specific to the kidney extraction site. This study aimed to evaluate incisional hernia occurrence in living kidney donors based on kidney extraction site location. STUDY DESIGN: This was a retrospective study of all donors who underwent minimally invasive living donor nephrectomies at the Mayo Clinic Arizona between 2011 and 2023 with a 2-year external validation cohort from Mayo Clinic Florida and Mayo Clinic Minnesota. The cohort was divided into 2 groups based on the kidney extraction site type: midline infraumbilical and Pfannenstiel. RESULTS: In the primary cohort, incisional hernia occurrence was observed in 1.2% of donors with an infraumbilical midline kidney extraction site compared with 0.1% with a Pfannenstiel extraction site (p = 0.04). Donors with an infraumbilical midline kidney extraction site were more likely to be men (50.8% vs 23.3%, p < 0.0001), have a higher BMI (mean 27.2 vs 26 kg/m2, p < 0.0001), and have current or former tobacco use (p = 0.002). There were no differences in incisional hernia occurrence when comparing minimally invasive surgical techniques (p = 0.52). In the external validation cohort, hernia occurrence was observed in 4.5% of donors with a midline incision compared with 0.0% with a Pfannenstiel incision (p = 0.09). Using combined data from the 3 sites, the use of a Pfannenstiel incision as the extraction site was associated with significantly lower odds of developing a hernia compared with the infraumbilical midline incision (odds ratio 0.06, 95% CI 0.008 to 0.456). CONCLUSIONS: Although the risk of hernia in living kidney donors is generally low, the use of a Pfannenstiel incision for kidney extraction appears to offer an additional incremental reduction in risk.