利用人工智能预测自发的石头通道:开发和测试基于机器学习的计算器
Kavita Gupta1, Anna Ricapito1, Dara Lundon1
1Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
Journal of endourology
|June 2, 2025
概括
人工智能 (AI) 开发的计算器可以预测尿道结石患者的自发性石头通行 (SSP). 与现有方法相比,这些人工智能工具的准确性更高,有助于治疗决策.
科学领域:
- 泌尿器科 泌尿器科 泌尿器科 泌尿器科
- 人工智能的人工智能
- 医疗信息学 医疗信息学
背景情况:
- 尿道结石是一种常见的疾病,需要有效的管理策略.
- 预测自发性石头通道 (SSP) 对于指导治疗决策和患者护理至关重要.
- 目前的预测工具可能缺乏足够的准确性来实现最佳的临床效用.
研究的目的:
- 开发和验证基于人工智能 (AI) 的计算器,用于预测尿路结石患者的SSP.
- 将AI衍生模型的性能与现有的预测工具进行比较.
主要方法:
- 预期在CT上招募患有单独尿路结石 (≤10毫米) 的患者.
- 在训练队伍 (70%的患者) 上使用机器学习 (ML) 开发AI计算器.
- 在一个单独的测试队列 (30%的患者) 上对AI计算器的外部验证,与MIMIC工具进行比较.
主要成果:
- 51%的训练患者实现了SSP;较小和较远的石头与通道有关.
- 监督机器学习 (SML) 计算器实现了0.737.7的曲线下的面积 (AUC).
- 无监督机器学习 (USML) 计算器实现了0.706的AUC,这两个都超过了MIMIC工具 (AUC0.588).
结论:
- 人工智能驱动的计算器可以有效地开发用于预测尿管石中的SSP.
- 与现有工具相比,开发的AI模型显示出优异的预测性能.
- 这些人工智能计算器可以增强治疗尿道结石的临床决策.
相关概念视频
01:28Urinary Tract Calculi I: Introduction
56
Renal calculi, or kidney stones, are solid deposits of minerals and salts formed inside the kidneys. In medical terminology, "calculus" refers to the stone itself, while "lithiasis" describes the process of stone formation. Depending on their location within the urinary system, these stones may be classified as either urolithiasis, when situated within the urinary tract, or nephrolithiasis, when located within the kidneys. Each term signifies the specific impact of the stone.Predisposition...
56
01:30Urinary Tract Calculi III: Medical Management
32
The diagnosis of renal calculi involves several imaging techniques, including non-contrast CT scans and ultrasound. These methods help visualize kidney stones, assess their size and location, and detect possible obstructions. Additionally, Measuring urine pH is useful for diagnosing specific stone types, such as struvite (alkaline pH) and uric acid stones (acidic pH). Cystine stones are primarily linked to cystinuria, a genetic condition. A urinalysis helps detect blood in the urine (hematuria)...
32