Duwe Gregor, Mercier Dominique, Kauth Verena, Moench Kerstin, Rajashekar Vikas, Junker Markus, Dengel Andreas, Haferkamp Axel, Höfner Thomas
Department of Urology and Pediatric Urology, University Medical Center Johannes Gutenberg University, Langenbeckstrasse 1, Mainz 55131, Germany.
German Research Center for Artificial Intelligence, Research Unit Smart Data & Knowledge Services, Trippstadter Strasse 122, Kaiserslautern 67663, Germany.
Eur J Cancer. 2025 May 2;220:115367. doi: 10.1016/j.ejca.2025.115367. Epub 2025 Mar 15.
Decisions on the best available treatment in clinical oncology are based on expert opinions in multidisciplinary cancer conferences (MCC). Artificial intelligence (AI) could increase evidence-based treatment by generating additional treatment recommendations (TR). We aimed to develop such an AI system for urothelial carcinoma (UC) and renal cell carcinoma (RCC).
Comprehensive data of patients with histologically confirmed UC and RCC who received MCC recommendations in the years 2015 - 2022 were transformed into machine readable representations. Development of a two-step process to train a classifier to mimic TR was followed by identification of superordinate and detailed categories of TR. Machine learning (CatBoost, XGBoost, Random Forest) and deep learning (TabPFN, TabNet, SoftOrdering CNN, FCN) techniques were trained. Results were measured by F1-scores for accuracy weights.
AI training was performed with 1617 (UC) and 880 (RCC) MCC recommendations (77 and 76 patient input parameters). The AI system generated fully automated TR with excellent F1-scores for UC (e.g. 'Surgery' 0.81, 'Anti-cancer drug' 0.83, 'Gemcitabine/Cisplatin' 0.88) and RCC (e.g. 'Anti-cancer drug' 0.92 'Nivolumab' 0.78, 'Pembrolizumab/Axitinib' 0.89). Explainability is provided by clinical features and their importance score. Finally, TR and explainability were visualized on a dashboard.
This study demonstrates for the first time AI-generated, explainable TR in UC and RCC with excellent performance results as a potential support tool for high-quality, evidence-based TR in MCC. The comprehensive technical and clinical development sets global reference standards for future AI developments in MCC recommendations in clinical oncology. Next, prospective validation of the results is mandatory.
临床肿瘤学中关于最佳可用治疗方案的决策基于多学科癌症会议（MCC）中的专家意见。人工智能（AI）可以通过生成额外的治疗建议（TR）来增加基于证据的治疗。我们旨在为尿路上皮癌（UC）和肾细胞癌（RCC）开发这样一种AI系统。
将2015年至2022年期间接受MCC建议的组织学确诊的UC和RCC患者的综合数据转化为机器可读形式。采用两步法训练分类器以模仿TR，随后确定TR的上级和详细类别。对机器学习（CatBoost、XGBoost、随机森林）和深度学习（TabPFN、TabNet、SoftOrdering CNN、FCN）技术进行了训练。通过F1分数衡量结果的准确性权重。
使用1617条（UC）和880条（RCC）MCC建议（77个和76个患者输入参数）进行AI训练。该AI系统生成了全自动的TR，UC（例如“手术”0.81、“抗癌药物”0.83、“吉西他滨/顺铂”0.88）和RCC（例如“抗癌药物”0.92、“纳武单抗”0.78、“帕博利珠单抗/阿昔替尼”0.89）的F1分数优异。临床特征及其重要性得分提供了可解释性。最后，TR和可解释性在仪表板上可视化。
本研究首次证明了在UC和RCC中由AI生成的、可解释的TR，其性能结果优异，可作为MCC中高质量、基于证据的TR的潜在支持工具。全面的技术和临床开发为临床肿瘤学MCC建议中的未来AI发展设定了全球参考标准。接下来，对结果进行前瞻性验证是必不可少的。
