文献速递前列腺增生与排尿功能障碍

机器学习模型预测前列腺增生内镜剜除术后尿失禁:EAU-Endourology研究

Machine learning models to predict postoperative incontinence after endoscopic enucleation of the prostate for benign prostatic hyperplasia: An EAU-Endourology study.
PubMed 文献 · Prostate Cancer Prostatic Dis · 2025-08-19

该研究基于两个BPH登记数据库共3828例患者,构建六种机器学习模型预测内镜剜除术后尿失禁,最佳模型为极端梯度提升(手动调参),准确率86.2%、敏感度96.8%、特异度23.7%、PPV 88.2%、NPV 55.9%,高敏感度和PPV有助于识别可能发生尿失禁的患者以加强随访。

要点

  • 基于3828例BPH患者构建六种机器学习模型预测术后尿失禁。
  • 极端梯度提升(手动调参)表现最佳,准确率86.2%、敏感度96.8%。
  • 高敏感度和PPV意味着预测阳性者大概率发生尿失禁,可指导随访。

核心结论

  • 机器学习模型可用于预测BPH内镜剜除术后尿失禁,最佳模型具有高敏感度和PPV。

研究设计与样本

  • 研究数据来自两个BPH登记数据库,共纳入3828例患者,分为训练集和验证集。
  • 预测变量包括年龄、前列腺体积、术前IPSS、QoL评分、Qmax、残余尿、术前留置导尿管、早期尖部松解(EAR)、剜除类型(两叶、三叶或整块)和激光能量类型。
  • 构建六种机器学习模型并在验证集中评估准确性。

主要发现

  • 患者中位年龄68岁,中位前列腺体积85.5 cc,5.4%术前留置导尿管。
  • 最常见剜除类型为两叶,最常见能量类型为铥光纤激光,34.0%患者行EAR。
  • 六种模型中极端梯度提升(手动调参)表现最佳,准确率86.2%、敏感度96.8%、特异度23.7%、PPV 88.2%、NPV 55.9%。

关键数值与推荐

  • 极端梯度提升(手动调参)模型准确率86.2%、敏感度96.8%、特异度23.7%、PPV 88.2%、NPV 55.9%。

临床怎么用

  • 模型预测为尿失禁的患者,临床可加强术后随访以尽早发现和管理尿失禁。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Machine learning (ML) and artificial intelligence (AI) have demonstrated powerful functionality in the healthcare setting thus far. We aimed to construct an AI model to predict postoperative incontinence after enucleation surgery for benign prostatic hyperplasia (BPH). METHODS: Data were taken from two BPH registries and split into training and validation datasets. The following characteristics were used as predictors of incontinence: age, prostate volume, preoperative IPSS, QoL score, Qmax and post-void residual; presence of preoperative indwelling catheter, early apical release (EAR), enucleation type (2-lobe, 3-lobe, or en-bloc), and laser energy type. Six types of ML models were constructed using the training dataset and applied to the validation dataset to assess their accuracy. RESULTS: 3828 patients from both databases were analyzed. Median age was 68, median prostate volume was 85.5 cc. 5.4% had a preoperative indwelling catheter. The commonest enucleation type was 2-lobe, the commonest energy type was Thulium fiber laser, and EAR was performed in 34.0%. Of the six ML models tested, extreme gradient boosting with manual fine tuning was the best-performing with an accuracy of 86.2%, sensitivity of 96.8%, specificity of 23.7%, PPV of 88.2%, and NPV of 55.9%. CONCLUSIONS: We hereby present an ML model for incontinence prediction post-surgery for BPH. Its main strengths are high sensitivity and PPV, meaning that if a patient is predicted to be incontinent using this model, this is likely to reflect the eventual outcome. This allows clinicians to pay closer attention on follow-up to detect and manage postoperative incontinence expediently.

来源:Prostate Cancer Prostatic Dis,查看原文。版权归原作者所有。

引用

  1. Fong KY, Gauhar V, Herrmann TRW, et al. Machine learning models to predict postoperative incontinence after endoscopic enucleation of the prostate for benign prostatic hyperplasia: An EAU-Endourology study. Prostate Cancer Prostatic Dis. 2025. PMID: 40830571. doi:10.1038/s41391-025-01015-1

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。