NLR预测青年肾穿刺活检术后出血的可解释机器学习研究OA

Objective To evaluate the predictive value of preoperative neutrophil-to-lymphocyte ratio(NLR)for bleeding after ultrasound-guided percutaneous renal biopsy in young adults(18-44 years),and to construct an individualized risk prediction model using interpretable machine learning.Methods This retrospective study included 527 young adults who underwent ultrasound-guided percutaneous renal biopsy at Hangzhou TCM Hospital of Zhejiang Chinese Medical University from January 2020 to October 2025.Five prediction models,including eXtreme gradient boosting(XGBoost),were constructed,and the optimal model was interpreted using the Shapley additive explanations(SHAP)method.The additional predictive value of NLR was assessed through incremental analysis,with sensitivity comparisons against the systemic immune-inflammation index(SII)and the platelet-to-lymphocyte ratio(PLR).Results Post-biopsy bleeding occurred in 116 patients,and NLR was significantly higher in bleeding group than in non-bleeding group(P<0.05).The area under the curve(AUC)of the five models ranged from 0.665 to 0.771;XGBoost showed the best overall performance and was naturally compatible with SHAP(test AUC=0.737).SHAP revealed a non-linear threshold effect:NLR<2.0 was protective,whereas NLR>3.0 was associated with a sharply increased risk.Adding NLR improved the AUC from 0.696 to 0.735(ΔAUC=0.040,P=0.441),while further combination with SII and PLR yielded only marginal improvement.Conclusion Preoperative NLR is an important predictive feature of post-biopsy bleeding in young adults,with a threshold effect at approximately 3.0 and a certain additive predictive value over traditional models.NLR can serve as a simple biomarker for preoperative bleeding risk assessment.