文献速递功能神经外科神经重症

使用个性化机器学习模型预测颞叶切除术后30天非癫痫发作结局

Predicting 30-Day Non-Seizure Outcomes Following Temporal Lobectomy with Personalized Machine Learning Models.
PubMed 文献 · World Neurosurg · 2023-11-23

本研究基于美国外科医师学会国家手术质量改进计划数据库,纳入423例接受颞叶切除术的患者,构建6种机器学习算法预测延长住院时间、非家庭出院和30天再入院。随机森林模型表现最佳,三种结局的AUROC分别为0.868、0.804和0.742。作者认为所开发的可用预测模型推进了以患者为中心的数据驱动范式。

要点

  • 随机森林模型预测延长住院时间的AUROC为0.868。
  • 随机森林模型预测非家庭出院的AUROC为0.804。
  • 随机森林模型预测30天再入院的AUROC为0.742。

核心结论

  • 作者认为所开发的可用预测模型提升了颞叶切除术的预后预测,是向以患者为中心的数据驱动范式转变的重要进展。

研究设计与样本

  • 基于美国外科医师学会国家手术质量改进计划数据库识别接受颞叶切除术的患者,最终纳入423例进行分析。
  • 测试了TabPFN、XGBoost、LightGBM、支持向量机、随机森林和逻辑回归6种机器学习算法,并使用Optuna优化库进行超参数调优。
  • 聚焦3种结局:延长住院时间、非家庭出院和30天再入院;将AUROC最高的模型纳入网络应用。
  • 使用SHapley Additive exPlanations评估预测变量的重要性。

主要发现

  • 423例患者中,111例(26.2%)发生延长住院时间,33例(7.8%)为非家庭出院,29例(6.9%)发生30天再入院。
  • 随机森林算法在各结局中表现最佳,预测延长住院时间、非家庭出院和30天再入院的AUROC分别为0.868、0.804和0.742。

临床怎么用

  • 作者开发了可访问的预测模型,用于增强颞叶切除术后预后预测,但原文未据此给出具体临床推荐。

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

BACKGROUND: Temporal lobe epilepsy is the most common reason behind drug-resistant seizures and temporal lobectomy (TL) is performed after all other efforts have been taken for a Temporal lobe epilepsy. Our study aims to develop multiple machine learning (ML) models capable of predicting postoperative outcomes following TL surgery. METHODS: Data from the American College of Surgeons National Surgical Quality Improvement Program database identified patients who underwent TL surgery. We focused on 3 outcomes: prolonged length of stay (LOS), nonhome discharges, and 30-day readmissions. Six ML algorithms, TabPFN, XGBoost, LightGBM, Support Vector Machine, Random Forest, and Logistic Regression, coupled with the Optuna optimization library for hyperparameter tuning, were tested. Models with the highest area under the receiver operating characteristic (AUROC) values were included in the web application. SHapley Additive exPlanations was used to evaluate importance of predictor variables. RESULTS: Our analysis included 423 patients. Of these patients, 111 (26.2%) experienced prolonged LOS, 33 (7.8%) had nonhome discharges, and 29 (6.9%) encountered 30-day readmissions. The top-performing models for each outcome were those built with the Random Forest algorithm. The Random Forest models yielded AUROCs of 0.868, 0.804, and 0.742 in predicting prolonged LOS, nonhome discharges, and 30-day readmissions, respectively. CONCLUSIONS: Our study uses ML to forecast adverse postoperative outcomes following TL. We developed accessible predictive models that enhance prognosis prediction for TL surgery. Making ML models available for this purpose represents a significant advancement in shifting toward a more patient-centric, data-driven paradigm.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Karabacak M, Jagtiani P, Panov F, et al. Predicting 30-Day Non-Seizure Outcomes Following Temporal Lobectomy with Personalized Machine Learning Models. World Neurosurg. 2023. PMID: 38006940. doi:10.1016/j.wneu.2023.11.077

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。