Division of Oncology, Department of Medicine, Stanford University School of Medicine, Stanford, CA.
Quantitative Sciences Unit, Department of Medicine, Stanford University School of Medicine, Stanford, CA.
JCO Precis Oncol. 2022 Oct;6:e2200220. doi: 10.1200/PO.22.00220.
Brain metastasis is common in lung cancer, and treatment of brain metastasis can lead to significant morbidity. Although early detection of brain metastasis may improve outcomes, there are no prediction models to identify high-risk patients for brain magnetic resonance imaging (MRI) surveillance. Our goal is to develop a machine learning-based clinicogenomic prediction model to estimate patient-level brain metastasis risk.
A penalized regression competing risk model was developed using 330 patients diagnosed with lung cancer between January 2014 and June 2019 and followed through June 2021 at Stanford HealthCare. The main outcome was time from the diagnosis of distant metastatic disease to the development of brain metastasis, death, or censoring.
Among the 330 patients, 84 (25%) developed brain metastasis over 627 person-years, with a 1-year cumulative brain metastasis incidence of 10.2% (95% CI, 6.8 to 13.6). Features selected for model inclusion were histology, cancer stage, age at diagnosis, primary site, and and alterations. The prediction model yielded high discrimination (area under the curve 0.75). When the cohort was stratified by risk using a 1-year risk threshold of > 14.2% (85th percentile), the high-risk group had increased 1-year cumulative incidence of brain metastasis versus the low-risk group (30.8% 6.1%, < .01). Of 48 high-risk patients, 24 developed brain metastasis, and of these, 12 patients had brain metastasis detected more than 7 months after last brain MRI. Patients who missed this 7-month window had larger brain metastases (58% 33% largest diameter > 10 mm; odds ratio, 2.80, CI, 0.51 to 13) versus those who had MRIs more frequently.
The proposed model can identify high-risk patients, who may benefit from more intensive brain MRI surveillance to reduce morbidity of subsequent treatment through early detection.
脑转移是肺癌的常见并发症，对脑转移的治疗可能会导致严重的发病率。尽管早期发现脑转移可能会改善预后，但目前还没有预测模型来识别需要进行脑磁共振成像（MRI）监测的高危患者。我们的目标是开发一种基于机器学习的临床基因组预测模型，以估计患者的脑转移风险。
使用 2014 年 1 月至 2019 年 6 月期间在斯坦福健康医疗中心诊断为肺癌并随访至 2021 年 6 月的 330 名患者，建立了一种惩罚回归竞争风险模型。主要结局是从远处转移性疾病诊断到发生脑转移、死亡或删失的时间。
在 330 名患者中，84 名（25%）在 627 人年中发生脑转移，1 年累积脑转移发生率为 10.2%（95%CI，6.8 至 13.6）。纳入模型的特征包括组织学、癌症分期、诊断时的年龄、原发部位和 和 改变。预测模型具有较高的区分度（曲线下面积 0.75）。当根据 1 年风险阈值>14.2%（第 85 百分位）将队列分层为高风险和低风险时，高风险组的 1 年累积脑转移发生率高于低风险组（30.8% 6.1%， <.01）。在 48 名高风险患者中，24 名发生了脑转移，其中 12 名患者在最后一次脑部 MRI 后超过 7 个月才发现脑转移。错过了这个 7 个月窗口期的患者脑转移瘤较大（58% 33%最大直径>10mm；优势比，2.80，CI，0.51 至 13），而那些更频繁进行 MRI 的患者脑转移瘤较小。
该模型可以识别高危患者，这些患者可能受益于更密集的脑部 MRI 监测，以通过早期发现来降低后续治疗的发病率。
