Analyzing breast cancer invasive disease event classification through explainable artificial intelligence.
Analyzing breast cancer invasive disease event classification through explainable artificial intelligence.
复制标题
DOI：
10.3389/fmed.2023.1116354
复制
发表时间：
2023
影响因子：
3.9
通讯作者：
Lorusso, Vito
中科院分区：
文献类型：
--
作者：
Massafra, Raffaella;Fanizzi, Annarita;Amoroso, Nicola;Bove, Samantha;Comes, Maria Colomba;Pomarico, Domenico;Didonna, Vittorio;Diotaiuti, Sergio;Galati, Luisa;Giotta, Francesco;La Forgia, Daniele;Latorre, Agnese;Lombardi, Angela;Nardone, Annalisa;Pastena, Maria Irene;Ressa, Cosmo Maurizio;Rinaldi, Lucia;Tamborra, Pasquale;Zito, Alfredo;Paradiso, Angelo Virgilio;Bellotti, Roberto;Lorusso, Vito
最近，精确的机器学习和深度学习方法一直致力于研究乳腺癌浸润性疾病事件（IDE），如复发，对侧和第二种癌症。然而，这种方法的解释性很差。因此，我们设计了一个可解释的人工智能（XAI）框架，以调查在意大利巴里的IRCCS Istituto Tumori“Giovanni Paolo II”招募的486名乳腺癌患者队列中的IDE。使用Shapley值，我们根据临床实践中经常采用的两个时期，即首次肿瘤诊断后5年和10年，确定IDE驱动特征。年龄、肿瘤直径、手术类型和多样性在5年内占主导地位，而治疗相关特征，包括激素、化疗方案和淋巴血管浸润，在10年IDE预测中占主导地位。雌激素受体（ER），增殖标记Ki67和转移淋巴结影响两个框架。因此，我们的框架旨在缩短人工智能和临床实践之间的距离
Recently, accurate machine learning and deep learning approaches have been dedicated to the investigation of breast cancer invasive disease events (IDEs), such as recurrence, contralateral and second cancers. However, such approaches are poorly interpretable. Thus, we designed an Explainable Artificial Intelligence (XAI) framework to investigate IDEs within a cohort of 486 breast cancer patients enrolled at IRCCS Istituto Tumori “Giovanni Paolo II” in Bari, Italy. Using Shapley values, we determined the IDE driving features according to two periods, often adopted in clinical practice, of 5 and 10 years from the first tumor diagnosis. Age, tumor diameter, surgery type, and multiplicity are predominant within the 5-year frame, while therapy-related features, including hormone, chemotherapy schemes and lymphovascular invasion, dominate the 10-year IDE prediction. Estrogen Receptor (ER), proliferation marker Ki67 and metastatic lymph nodes affect both frames. Thus, our framework aims at shortening the distance between AI and clinical practice
登录
查看更多内容
影响因子：
3.7
作者：
Li J;Zhou Z;Dong J;Fu Y;Li Y;Luan Z;Peng X
通讯作者：
Peng X
影响因子：
14.4
作者：
Miller, Tim
通讯作者：
Miller, Tim
影响因子：
51.1
作者：
Arnold, Melina;Rutherford, Mark J.;Bray, Freddie
通讯作者：
Bray, Freddie
影响因子：
8.8
作者：
Hickman SE;Baxter GC;Gilbert FJ
通讯作者：
Gilbert FJ
可解释的人工智能揭示了对与乳腺癌患者更好的预后相关的肿瘤微环境条件的新见解。
影响因子：
5.2
作者：
Chakraborty D;Ivan C;Amero P;Khan M;Rodriguez-Aguayo C;Başağaoğlu H;Lopez-Berestein G
通讯作者：
Lopez-Berestein G