摘要
目的基于FP-Growth算法构建新型模型预测前列腺特异性抗原(PSA)处于4~10 ng/mL之间的前列腺癌(Prostate cancer,PCa)。方法筛选2019年6月至2024年6月河北北方学院附属第一医院放疗科前列腺疾病患者800例,将其分为FP-Growth模型组和验证组。使用FP-Growth算法扫描模型组患者基线资料构建预测模型并评价其预测效能,计算基于基线资料和PCa因果关系的有效强关联规则。结果基于有效强关联规则预测PCa时,发生率最高达75%。预测模型内部验证C-index为0.801,模型具有良好的一致性,且能够提供临床净收益;外部验证显示,模型预测模型组和验证组PCa的AUC差异无统计学意义(P=0.125),ROC(Receiver operating characteristic)曲线拟合较为理想(χ^(2)=7.754,P=0.376)。结论新型FP-Growth模型预测PSA处于4~10 ng/mL之间的PCa效能较为理想,能够为临床决策提供一定的参考。
Objective To construct a new prediction model for prostate cancer(PCa) with prostate specific antigen (PSA) between 4-10 ng/mL based on the FP Growth algorithm.Methods Total of 800 patients with prostate diseases who were treated in the Radiotherapy Department of the First Affiliated Hospital of Hebei North University from June 2019 to June 2024 were enrolled in the study.The patients were divided into the FP Growth model group and the validation group.The baseline data of the patients in the model group was scanned by using the FP Growth algorithm.The prediction efficiency of the model was evaluated.The effective strong association rules were calculated based on the causal relationship between baseline data and PCa.Results The highest incidence rate of predicting PCa was 75%based on the effective strong association rules.The C-index was 0.801 in the prediction model internal validation.The model had good consistency and could provide clinical net benefit.In the external validation,the AUC of the PCa prediction model for the model group and validation group had no statistically significant difference(P=0.125),and the ROC curve fitting was relatively ideal(χ^(2)=7.754,P=0.376).Conclusion The new FP Growth model has ideal performance in predicting PCa with PSA between 4-10 ng/mL,which can provide a reference for clinical decision-making.
作者
杜丽娜
张遵浩
管梦娇
杨阳
田龙
Du Li'na;Zhang Zunhao;Guan Mengjiao;Yang Yang;Tian Long(Department of Radiotherapy,the First Afiliated Hospital of Hebei North University,Zhangjiakou 075000,Hebei,China;Department of Radiotherapy,the First Hospital of Hebei Medical University,Shijiazhuang 050000,Hebei,China)
出处
《中国男科学杂志》
2025年第2期45-51,共7页
Chinese Journal of Andrology
基金
张家口市重点研究计划项目(2322191D)。
