文献速递神经肿瘤脊柱脊髓外科

能否使用人工智能聚类分析识别术后不良事件风险最高的脊柱转移性乳腺癌患者

Can We Use Artificial Intelligence Cluster Analysis to Identify Patients with Metastatic Breast Cancer to the Spine at Highest Risk of Postoperative Adverse Events?
PubMed 文献 · World Neurosurg · 2023-02-18

回顾性分析2008至2020年两家三级转诊中心因乳腺癌脊柱转移行开放手术的患者,采用两步无监督聚类按功能状态、术前脊柱放疗、结构不稳定、硬膜外脊髓压迫、神经功能缺损及肿瘤位置/激素状态分层,识别出5个聚类,其90天不良事件率分别为25.0%、73.3%、24.0%、31.6%和60.0%(P=0.003)。

要点

  • 聚类分析识别出5个患者聚类,各聚类90天不良事件率不同(P=0.003)。
  • 低功能/放疗组不良事件率73.3%,低功能/神经缺损组为60.0%。
  • 高功能组、ER/PR阳性组、腰椎/无压迫组不良事件率分别为25.0%、24.0%、31.6%。

核心结论

  • 就诊时功能状态、肿瘤激素特征、放疗史和硬膜外压迫可区分术后结局轨迹,作者认为结果有助于期望管理和识别术后可能需更密切监测的高危患者。

研究设计与样本

  • 回顾性分析纳入2008至2020年两家三级转诊中心因乳腺癌脊柱转移行开放手术的患者。
  • 采用两步无监督聚类分析,依据就诊时功能、术前脊柱放疗、结构不稳定、硬膜外脊髓压迫(ESCC)、神经功能缺损及肿瘤位置/激素状态将患者分层。
  • 比较采用χ2检验和单因素方差分析,主要结局为90天不良事件。

主要发现

  • 高功能组有胸椎转移,东部肿瘤协作组(ECOG)评分为1.0±0.8。
  • 低功能/放疗组有术前放疗,Karnofsky评分最低(56.0±10.6)。
  • 雌激素受体或孕激素受体(ER/PR)阳性组ER/PR阳性率>90%,Karnofsky评分为74.0±11.5。
  • 腰椎/无压迫组ESCC 2级或3级硬膜外病变患者最少(42.1%,P<0.001)。
  • 低功能/神经缺损组有ESCC 2级或3级病变和神经功能缺损。

关键数值与推荐

  • 90天不良事件率:高功能组25.0%,低功能/放疗组73.3%,ER/PR阳性组24.0%,腰椎/无压迫组31.6%,低功能/神经缺损组60.0%(P=0.003)。

临床怎么用

  • 作者认为结果有助于期望管理,并识别术后可能需更密切监测的高危患者。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: Group patients who required open surgery for metastatic breast cancer to the spine by functional level and metastatic disease characteristics to identify factors that predispose to poor outcomes. METHODS: A retrospective analysis included patients managed at 2 tertiary referral centers from 2008 to 2020. The primary outcome was a 90-day adverse event. A 2-step unsupervised cluster analysis stratified patients into cohorts using function at presentation, preoperative spine radiation, structural instability, epidural spinal cord compression (ESCC), neural deficits, and tumor location/hormone status. Comparisons were performed using χ2 test and one-way analysis of variance. RESULTS: Five patient "clusters" were identified. High function (HIGH) had thoracic metastases and an Eastern Cooperative Oncology Group (ECOG) score of 1.0 ± 0.8. Low function/irradiated (LOW + RADS) had preoperative radiation and the lowest Karnofsky scores (56.0 ± 10.6). Estrogen receptor or progesterone receptor (ER/PR) positive patients had >90% estrogen/progesterone positivity and moderate Karnofsky scores (74.0 ± 11.5). Lumbar/noncompressive (NON-COMP) had the fewest patients with ESCC grade 2 or 3 epidural disease (42.1%, P < 0.001). Low function/neurologic deficits (LOW + NEURO) had ESCC grade 2 or 3 disease and neurologic deficits. Adverse event rates were 25.0% in the HIGH group, 73.3% in LOW + RADS, 24.0% in ER/PR, 31.6% in NON-COMP, and 60.0% in LOW + NEURO (P = 0.003). CONCLUSIONS: Function at presentation, tumor hormone signature, radiation history, and epidural compression delineated postoperative trajectory. We believe our results can aid in expectation management and the identification of at-risk patients who may merit closer surveillance following surgical intervention.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Fourman MS, Siraj L, Duvall J, et al. Can We Use Artificial Intelligence Cluster Analysis to Identify Patients with Metastatic Breast Cancer to the Spine at Highest Risk of Postoperative Adverse Events? World Neurosurg. 2023. PMID: 36805503. doi:10.1016/j.wneu.2023.02.064

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。