指南与共识泌尿男性生殖肿瘤

开发用于尿路上皮癌和肾细胞癌的人工智能生成、可解释的治疗推荐系统以支持多学科肿瘤会议

Development of an artificial intelligence-generated, explainable treatment recommendation system for urothelial carcinoma and renal cell carcinoma to support multidisciplinary cancer conferences.
指南 / 共识 · Eur J Cancer · 2025-03-15

本研究将2015至2022年经组织学确诊的尿路上皮癌和肾细胞癌患者在多学科肿瘤会议中的推荐数据转化为机器可读形式,训练机器学习和深度学习模型以模拟治疗推荐,并用F1分数评估。系统生成的完全自动化治疗推荐在尿路上皮癌和肾细胞癌中均取得优异F1分数,并通过临床特征及其重要性评分提供可解释性,最终可视化于仪表板。作者结论认为这是首个用于尿路上皮癌和肾细胞癌的可解释人工智能治疗推荐系统,可作为多学科肿瘤会议高质量循证治疗推荐的潜在支持工具,但下一步必须进行前瞻性验证。

要点

  • 人工智能训练使用1617条尿路上皮癌和880条肾细胞癌多学科肿瘤会议推荐。
  • 尿路上皮癌F1分数:手术0.81、抗癌药物0.83、吉西他滨/顺铂0.88。
  • 肾细胞癌F1分数:抗癌药物0.92、纳武利尤单抗0.78、帕博利珠单抗/阿昔替尼0.89。

核心结论

  • 本研究首次展示用于尿路上皮癌和肾细胞癌的人工智能生成、可解释的治疗推荐,性能优异,可作为多学科肿瘤会议高质量循证治疗推荐的潜在支持工具。
  • 作者认为全面的技术和临床开发为未来临床肿瘤学多学科肿瘤会议推荐的人工智能发展设定了全球参考标准。
  • 作者结论指出下一步必须对结果进行前瞻性验证。

研究设计与样本

  • 研究纳入2015至2022年经组织学确诊的尿路上皮癌和肾细胞癌患者,这些患者接受了多学科肿瘤会议推荐。
  • 将综合数据转化为机器可读表示,开发两步流程训练分类器以模拟治疗推荐,随后识别治疗推荐的上位和详细类别。
  • 训练了机器学习(CatBoost、XGBoost、随机森林)和深度学习(TabPFN、TabNet、SoftOrdering CNN、FCN)技术。
  • 结果以F1分数衡量准确度权重。
  • 人工智能训练使用1617条尿路上皮癌和880条肾细胞癌多学科肿瘤会议推荐,分别对应77和76个患者输入参数。

主要发现

  • 人工智能系统生成完全自动化的治疗推荐,尿路上皮癌F1分数优异,例如手术0.81、抗癌药物0.83、吉西他滨/顺铂0.88。
  • 肾细胞癌F1分数优异,例如抗癌药物0.92、纳武利尤单抗0.78、帕博利珠单抗/阿昔替尼0.89。
  • 可解释性通过临床特征及其重要性评分提供。
  • 治疗推荐和可解释性最终可视化于仪表板。

临床怎么用

  • 作者结论认为该人工智能系统可作为多学科肿瘤会议高质量循证治疗推荐的潜在支持工具。
  • 作者结论指出下一步必须对结果进行前瞻性验证。

局限性

  • 作者结论指出下一步必须对结果进行前瞻性验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: 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). METHODS: 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. RESULTS: 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. CONCLUSION: 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.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Duwe G, Mercier D, Kauth V, et al. Development of an artificial intelligence-generated, explainable treatment recommendation system for urothelial carcinoma and renal cell carcinoma to support multidisciplinary cancer conferences. Eur J Cancer. 2025. PMID: 40107091. doi:10.1016/j.ejca.2025.115367

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。