摘要
由新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-泌尿系统疾病和状况的新研究-尿失禁是一篇报道的主题。据新华社长春消息报道，“机器人辅助腹腔镜前列腺根治性切除术(RARP)在减少术后并发症方面优于开放手术，但仍有6-20%的患者在术后出现尿失禁(UI)。因此，许多研究者建立了RARP术后UI发生的预测模型，但这些模型的预测性能是支架内的。”本研究旨在系统回顾和评价已发表的RAR P患者UI风险预测模型。我们在PubMed、Co Chrane Library、Web of Science和Embase数据库中进行了全面的文献检索。报道了RARP后UI发生的临床预测模型的开发和/或验证。我们确定了7个研究，其中8个模型符合纳入标准。大多数研究使用逻辑回归模型预测RARP后UI的发生。最常见的预测因素包括年龄、体重指数和神经保留程序。模型性能从差到好。研究中受试者操作特征曲线下面积在0.64～0.98之间，所有研究均具有较高的偏倚风险，尽管它们具有预测RA RP后UI的潜力，但临床预测模型的准确性有限，偏倚风险较高，有待进一步改进。应从更大的代表性样本中综合考虑潜在的预测因素，并建立高质量的风险预测模型。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Urologic Diseases and Conditions-Urinary Incontinence is the subject of a report. According to news originating from Changchun, People's Republic of China, by NewsRx correspondents , research stated, "Even though robotic-assisted laparoscopic radical prostatect omy (RARP) is superior to open surgery in reducing postoperative complications, 6-20% of patients still experience urinary incontinence (UI) after surgery. Therefore, many researchers have established predictive models for UI occurrence after RARP, but the predictive performance of these models is inconsi stent." Our news journalists obtained a quote from the research from the Department of R eproductive Medicine Center, "This study aims to systematically review and criti cally evaluate the published prediction models of UI risk for patients after RAR P. We conducted a comprehensive literature search in the databases of PubMed, Co chrane Library, Web of Science, and Embase. Literature published from inception to March 20, 2024, which reported the development and/or validation of clinical prediction models for the occurrence of UI after RARP. We identified seven studi es with eight models that met our inclusion criteria. Most of the studies used l ogistic regression models to predict the occurrence of UI after RARP. The most c ommon predictors included age, body mass index, and nerve sparing procedure. The model performance ranged from poor to good, with the area under the receiver op erating characteristic curves ranging from 0.64 to 0.98 in studies. All the stud ies have a high risk of bias. Despite their potential for predicting UI after RA RP, clinical prediction models are restricted by their limited accuracy and high risk of bias. In the future, the study design should be improved, the potential predictors should be considered from larger and representative samples comprehe nsively, and high-quality risk prediction models should be established."
NETL
NSTL