Suartz Caio Vinícius, Martinez Lucas Motta, Cordeiro Maurício Dener, Flores Hunter Ausley, Kodama Sarah, Cardili Leonardo, Mota José Maurício, Coelho Fernando Morbeck Almeida, de Bessa Junior José, Camargo Cristina Pires, Teoh Jeremy Yuen-Chun, Shariat Shahrokh F, Toren Paul, Nahas William Carlos, Ribeiro-Filho Leopoldo Alves
Division of Urology, Institute of Cancer of São Paulo, University of São Paulo, São Paulo, Brazil.
Department of Urology, University of Colorado, Aurora, CO, United States.
Can Urol Assoc J. 2024 Sep;18(9):E276-E284. doi: 10.5489/cuaj.8681.
Neoadjuvant cisplatin-based combination chemotherapy (NAC) followed by radical cystectomy is the standard of care for cisplatin-fit patients harboring muscle-invasive bladder cancer (MIBC). Prediction of response to NAC is essential for clinical decision-making regarding alternatives in case of non-response, and bladder-sparing in case of complete response. This research aimed to assess the performance of machine learning in predicting therapeutic response following NAC treatment in patients with MIBC.
A systematic review adhering to the PRISMA guidelines was conducted until July 2023. The study integrated articles relating to artificial intelligence and NAC response in MIBC from various databases. The quality of articles was evaluated using the Quality Assessment Tool for Diagnostic Accuracy Studies 2 (QUADAS-2). A meta-analysis was subsequently performed on selected studies to determine the sensitivity and specificity of machine learning algorithms in predicting NAC response.
Of 655 articles identified, 12 studies comprising 1523 patients were included, and four studies were eligible for meta-analysis. The sensitivity and specificity of the studies were 0.62 (95% confidence interval [CI] 0.50-0.72) and 0.82 (95% CI 0.72-0.89), respectively, with a heterogeneity score (I) of 38.5%. The machine learning algorithms used computed tomography, genetic, and anatomopathologic data as input and exhibited promising potential for predicting NAC response.
Machine-learning algorithms, especially those using computed tomography, genetic, and pathologic data, demonstrate significant potential for predicting NAC response in MIBC. Standardization of methodologic data analysis and response criteria are needed as validation studies.
对于适合顺铂治疗的肌层浸润性膀胱癌（MIBC）患者，基于顺铂的新辅助联合化疗（NAC）后行根治性膀胱切除术是标准治疗方案。预测NAC的反应对于临床决策至关重要，即对于无反应的情况选择替代方案，以及对于完全反应的情况选择保留膀胱。本研究旨在评估机器学习在预测MIBC患者NAC治疗后治疗反应方面的性能。
遵循PRISMA指南进行系统综述，直至2023年7月。该研究整合了来自各种数据库的与MIBC中人工智能和NAC反应相关的文章。使用诊断准确性研究质量评估工具2（QUADAS-2）评估文章质量。随后对选定的研究进行荟萃分析，以确定机器学习算法在预测NAC反应方面的敏感性和特异性。
在识别出的655篇文章中，纳入了12项研究，共1523例患者，4项研究符合荟萃分析的条件。这些研究的敏感性和特异性分别为(0.62)（95%置信区间[CI](0.50 - 0.72)）和(0.82)（95%CI(0.72 - 0.89)），异质性得分（I）为(38.5%)。所使用的机器学习算法将计算机断层扫描、基因和解剖病理学数据作为输入，在预测NAC反应方面显示出有前景的潜力。
机器学习算法，尤其是那些使用计算机断层扫描、基因和病理数据的算法，在预测MIBC患者的NAC反应方面显示出显著潜力。作为验证研究，需要对方法学数据分析和反应标准进行标准化。
