Boeri Carlo, Chiappa Corrado, Galli Federica, De Berardinis Valentina, Bardelli Laura, Carcano Giulio, Rovera Francesca
SSD Breast Unit - ASST-Settelaghi Varese, Senology Research Center, Department of Medicine, University of Insubria, Varese, Italy.
Cancer Med. 2020 May;9(9):3234-3243. doi: 10.1002/cam4.2811. Epub 2020 Mar 10.
More than 750 000 women in Italy are surviving a diagnosis of breast cancer. A large body of literature tells us which characteristics impact the most on their prognosis. However, the prediction of each disease course and then the establishment of a therapeutic plan and follow-up tailored to the patient is still very complicated. In order to address this issue, a multidisciplinary approach has become widely accepted, while the Multigene Signature Panels and the Nottingham Prognostic Index are still discussed options. The current technological resources permit to gather many data for each patient. Machine Learning (ML) allows us to draw on these data, to discover their mutual relations and to esteem the prognosis for the new instances. This study provides a primary evaluation of the application of ML to predict breast cancer prognosis. We analyzed 1021 patients who underwent surgery for breast cancer in our Institute and we included 610 of them. Three outcomes were chosen: cancer recurrence (both loco-regional and systemic) and death from the disease within 32 months. We developed two types of ML models for every outcome (Artificial Neural Network and Support Vector Machine). Each ML algorithm was tested in accuracy (=95.29%-96.86%), sensitivity (=0.35-0.64), specificity (=0.97-0.99), and AUC (=0.804-0.916). These models might become an additional resource to evaluate the prognosis of breast cancer patients in our daily clinical practice. Before that, we should increase their sensitivity, according to literature, by considering a wider population sample with a longer period of follow-up. However, specificity, accuracy, minimal additional costs, and reproducibility are already encouraging.
在意大利，超过75万名女性在被诊断出患有乳腺癌后存活了下来。大量文献告诉我们哪些特征对她们的预后影响最大。然而，预测每个疾病进程，进而制定适合患者的治疗方案和后续跟进仍然非常复杂。为了解决这个问题，多学科方法已被广泛接受，而多基因特征面板和诺丁汉预后指数仍是讨论中的选项。当前的技术资源允许为每个患者收集许多数据。机器学习（ML）使我们能够利用这些数据，发现它们之间的相互关系，并评估新病例的预后。本研究对应用ML预测乳腺癌预后进行了初步评估。我们分析了在我们研究所接受乳腺癌手术的1021名患者，其中纳入了610名。选择了三个结果：癌症复发（局部和全身）以及在32个月内死于该疾病。针对每个结果我们开发了两种类型的ML模型（人工神经网络和支持向量机）。每个ML算法在准确率（=95.29%-96.86%）、敏感性（=0.35-0.64）、特异性（=0.97-0.99）和AUC（=0.804-0.916）方面进行了测试。这些模型可能会成为我们日常临床实践中评估乳腺癌患者预后的额外资源。在此之前，根据文献，我们应该通过考虑更广泛的人群样本和更长的随访期来提高它们的敏感性。然而，特异性、准确性、最低额外成本和可重复性已经令人鼓舞。
