Piedimonte Sabrina, Erdman Lauren, So Delvin, Bernardini Marcus Q, Ferguson Sarah E, Laframboise Stephane, Bouchard Fortier Genevieve, Cybulska Paulina, May Taymaa, Hogen Liat
Gynecologic Oncology, University of Toronto, Toronto, Ontario, Canada.
Computer Science, The Hospital for Sick Children, Toronto, Ontario, Canada.
J Surg Oncol. 2023 Mar;127(3):465-472. doi: 10.1002/jso.27137. Epub 2022 Nov 9.
To develop a machine learning (ML) algorithm to predict outcome of primary cytoreductive surgery (PCS) in patients with advanced ovarian cancer (AOC) METHODS: This retrospective cohort study included patients with AOC undergoing PCS between January 2017 and February 2021. Using radiologic criteria, patient factors (age, CA-125, performance status, BRCA) and surgical complexity scores, we trained a random forest model to predict the dichotomous outcome of optimal cytoreduction (<1 cm) and no gross residual (RD = 0 mm) using JMP-Pro 15 (SAS). This model is available at https://ipm-ml.ccm.sickkids.ca.
One hundred and fifty-one patients underwent PCS and randomly assigned to train (n = 92), validate (n = 30), or test (n = 29) the model. The median age was 58 (27-83). Patients with suboptimal cytoreduction were more likely to have an Eastern Cooperative Oncology Group 3-4 (11% vs. 0.75%, p = 0.004), lower albumin (38 vs. 41, p = 0.02), and higher CA125 (1126 vs. 388, p = 0.012) than patients with optimal cytoreduction (n = 133). There were no significant differences in age, histology, stage, or BRCA status between groups. The bootstrap random forest model had AUCs of 99.8% (training), 89.6%(validation), and 89.0% (test). The top five contributors were CA125, albumin, diaphragmatic disease, age, and ascites. For RD = 0 mm, the AUCs were 94.4%, 52%, and 84%, respectively.
Our ML algorithm demonstrated high accuracy in predicting optimal cytoreduction in patients with AOC selected for PCS and may assist decision-making.
开发一种机器学习（ML）算法，以预测晚期卵巢癌（AOC）患者的初次肿瘤细胞减灭术（PCS）结果。方法：这项回顾性队列研究纳入了2017年1月至2021年2月期间接受PCS的AOC患者。利用放射学标准、患者因素（年龄、CA-125、体能状态、BRCA）和手术复杂程度评分，我们使用JMP-Pro 15（SAS）软件训练了一个随机森林模型，以预测最佳肿瘤细胞减灭术（<1厘米）和无肉眼残留（RD = 0毫米）的二分结果。该模型可在https://ipm-ml.ccm.sickkids.ca获取。
151例患者接受了PCS，并被随机分配用于训练（n = 92）、验证（n = 30）或测试（n = 29）该模型。中位年龄为58岁（27 - 83岁）。与实现最佳肿瘤细胞减灭术的患者（n = 133）相比，肿瘤细胞减灭术未达最佳的患者更有可能具有东部肿瘤协作组3 - 4级（11%对0.75%，p = 0.004）、白蛋白水平较低（38对41，p = 0.02）以及CA125水平较高（1126对388，p = 0.012）。两组在年龄、组织学、分期或BRCA状态方面无显著差异。自助随机森林模型在训练集、验证集和测试集上的曲线下面积（AUC）分别为99.8%、89.6%和89.0%。贡献最大的五个因素是CA125、白蛋白、膈肌疾病、年龄和腹水。对于RD = 0毫米，AUC分别为94.4%、52%和84%。
我们的ML算法在预测接受PCS的AOC患者的最佳肿瘤细胞减灭术方面显示出高准确性，并可能有助于决策。
