대한신장학회

논문분류	춘계학술대회 초록집
제목	Prediction Model of Acute Kidney Injury in Patients With Acute Pesticide Poisoning: Prediction of Acute Kidney Injury in Pesticide Intoxication (PKIP) Scores in a Cohort Study
저자	Se-Jin Ahn
출판정보	2025; 2025(1):
키워드	Pesticides, Poisoning, Acute Kidney Injury, Mortality, Decision support techniques
초록	Acute pesticide poisoning frequently leads to acute kidney injury (AKI), significantly increasing mortality. However, predictive research in this area remains limited, and criteria for AKI detection in pesticide poisoning victims are not well-defined. This study aimed to evaluate the Kidney Disease Improving Global Outcomes (KDIGO) criteria and develop a model for early AKI prediction in pesticide poisoning patients. This retrospective study analyzed 877 patients admitted for acute pesticide poisoning between 2015 and 2020. AKI was defined using KDIGO criteria, considering serum creatinine, urine output, and renal replacement therapy initiation. AKI stages were also determined. Six machine learning models with four feature selection methods were compared using 5-fold cross-validation, stratified by pesticide categories. The final model, Prediction of acute Kidney Injury in Pesticide intoxication (PKIP), was established. KDIGO-defined AKI significantly impacted mortality, with AKI patients showing a 16.6% mortality rate compared to 4.7% in non-AKI patients. The PKIP model, incorporating 14 features selected via Least Absolute Shrinkage and Selection Operator, demonstrated superior performance [AUROC 0.720 (95% CI: 0.692-0.747), AUPRC 0.513 (95% CI: 0.464-0.563)]. Risk stratification based on PKIP probabilities showed significant differences between groups. The high-risk group demonstrated markedly higher rates of AKI occurrence, progression to higher AKI stages, and mortality compared to the low-risk group. PKIP exhibited superior risk stratification for both AKI and mortality prediction compared to the APACHE II score, demonstrating better discrimination in patients with acute pesticide poisoning. This study validates the use of KDIGO criteria for AKI detection in pesticide poisoning and introduces the PKIP model as an effective tool for early AKI prediction and risk stratification. The web-based PKIP tool offers a practical instrument for prognostic management and intervention in clinical practice for pesticide poisoning patients.
원문(PDF)	PDF 원문보기

간행물 검색

대한신장학회 회원관리 규정