An automatic urodynamic diagnostic system for the diagnosis of Lower Urinary Tract Symptoms

Objectives: To establish a machine learning based diagnostic system for automatic detection of lower urinary tract symptoms (LUTS) using pressure-flow studies’ data. Methods: The six most common diagnoses of LUTS were included in the present study. A number of 527 eligible patients with complete data, from the year of 2015 to 2020, were enrolled in this study. Totally, two global features (patient age and gender) and 13 urodynamic features were considered to be the input for machine learning algorithms.研究目标：构建基于机器学习的诊断系统，利用压力流研究数据自动检测下尿路症状（lower urinary tract symptoms, LUTS）。研究方法：本研究纳入六种最常见的下尿路症状诊断类型，纳入2015年至2020年间的527例符合入组标准且数据完整的患者。最终选取两项全局特征（患者年龄与性别）及13项尿动力学特征，作为机器学习算法的输入变量。