文献速递小儿泌尿与泌尿修复

人工智能用于儿童尿流率曲线客观评估

Artificial Intelligence for Objective Assessment of Pediatric Uroflowmetry Curves.
PubMed 文献 · Urology · 2025-08-13

本研究评估人工智能与机器学习对儿童尿流率曲线客观分类的潜力,纳入586条5-17岁儿童尿流率曲线,由三名小儿泌尿外科专家依据ICCS定义分类,使用YOLOv5×6算法训练(85%数据)和验证(15%数据)。模型总体准确率85.8%,钟形曲线识别成功率96%,mAP@0.5约90%。

要点

  • AI模型对儿童尿流率曲线分类总体准确率达85.8%。
  • 钟形曲线识别成功率最高达96%,平台型精确率1.00。
  • AI分类可减少观察者间变异,有望集成设备实时分析。

核心结论

  • AI驱动的尿流率曲线分类具有高准确率并可减少观察者变异。

研究设计与样本

  • 横断面研究,分析586条5-17岁儿童尿流率曲线,排除排尿量低于预期膀胱容量50%的测试。

主要发现

  • 三位专家间一致性高,Fleiss kappa为0.948±0.007。
  • AI模型总体准确率85.8%,钟形曲线识别成功率96%。
  • 平台型曲线精确率最高为1.00,断续型最低为0.64。
  • mAP@0.5约90%,在50个epoch后趋于稳定。

临床怎么用

  • AI分类可作为辅助工具用于儿童尿流率曲线的客观判读,减少人工判读差异。

局限性

  • 未来需多中心数据集和标准化报告以提升临床实用性并集成到尿流率设备中。

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

OBJECTIVE: To evaluate the potential of artificial intelligence (AI) and machine learning (ML) to objectively classify uroflowmetry curves, aiming to reduce variability and enhance diagnostic accuracy. METHODS: This cross-sectional study analyzed 586 uroflowmetry curves from children aged 5-17 years, excluding tests with voided volumes below 50% of expected bladder capacity. Curves were standardized per ICS recommendations (1 mm = 1 s on x-axis, 1mL/s on y-axis) and classified by three pediatric urology specialists into bell, tower, plateau, staccato, or interrupted patterns per ICCS definitions. The YOLOv5×6 algorithm was trained on 85% of the dataset, with 15% for validation, using a high-performance system. Performance was assessed via accuracy, precision, recall, F1-score, and mean Average Precision (mAP). RESULTS: Inter-rater agreement was high (Fleiss' kappa: 0.948 ± 0.007). The AI model achieved 85.8% accuracy, with 96% success in identifying bell-shaped curves. Plateau curves showed the highest precision (1.00), while staccato had the lowest (0.64). mAP@0.5 reached ∼90%, stabilizing after 50 epochs. CONCLUSION: AI-driven classification of uroflowmetry curves offers high accuracy and reduces observer variability. Future work should focus on multicenter datasets and standardized reporting to enhance clinical utility and integration into uroflowmetry devices for real-time analysis.

来源:Urology,查看原文。版权归原作者所有。

引用

  1. Yücel ÖB, Tekin A, Tiryaki S, et al. Artificial Intelligence for Objective Assessment of Pediatric Uroflowmetry Curves. Urology. 2025. PMID: 40816601. doi:10.1016/j.urology.2025.08.022

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。