生存分析评分系统

使用机器学习计算评分

Posted by     Jamesjin63 on Sunday, November 29, 2020

临床试验设计

院外心脏骤停患者神经功能不良预后的评分系统的开发与验证 doi:10.1093/eurheartj/ehaa570 本研究是针对院外心脏骤停(OOHCA)事件,进行早期预测患者结局有助于医师进行临床决策。虽然针对该类患者预后预测已有CAHP及TTM评分管理系统,但两种评分系统变量组成复杂,紧急状态下使用受限。 结论:MIRACLE2评分运用简单的入院临床指标,为院外心脏骤停的患者不良神经功能结局提供了早期准确预测,具有良好的临床使用价值。

  1. 收集373例患者,进行临床指标分析,其生存预后效果。建立MIRACLE2评分系统。
  2. 在外部队列,进行验证MIRACLE2评分系统。

核心

采用机器学习方法,建立预测模型,导入患者信息,shiny显示结果。摈弃繁杂的评分计算,考虑变量的非线性关系。

参考文献:

  • Zhang, XP; Gao, YZ; Chen, ZH; et al. An Eastern Hepatobiliary Surgery Hospital/Portal Vein Tumor Thrombus Scoring System as an Aid to Decision Making on Hepatectomy for Hepatocellular Carcinoma Patients With Portal Vein Tumor Thrombus: A Multicenter Study. Hepatology.2019,69(5):2076-2090
  • Nilesh Pareek, Peter Kordis, Nicholas Beckley-Hoelscher, Dominic Pimenta, Spela Tadel Kocjancic, Anja Jazbec, Joanne Nevett, Rachael Fothergill, Sundeep Kalra, Tim Lockie, Ajay M Shah, Jonathan Byrne, Marko Noc, Philip MacCarthy, A practical risk score for early prediction of neurological outcome after out-of-hospital cardiac arrest: MIRACLE2, European Heart Journal, , ehaa570, https://doi.org/10.1093/eurheartj/ehaa570
  • Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW, Vickers AJ, Ransohoff DF, Collins GS. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015 Jan 6;162(1):W1-73. doi: 10.7326/M14-0698. PMID: 25560730.
  • 基于Cox回归模型构建疾病风险评分工具
  • Zhang XP, Gao YZ, Chen ZH, Chen MS, Li LQ, Wen TF, Xu L, Wang K, Chai ZT, Guo WX, Shi J, Xie D, Wu MC, Yee Lau W, Cheng SQ. An Eastern Hepatobiliary Surgery Hospital/Portal Vein Tumor Thrombus Scoring System as an Aid to Decision Making on Hepatectomy for Hepatocellular Carcinoma Patients With Portal Vein Tumor Thrombus: A Multicenter Study. Hepatology. 2019 May;69(5):2076-2090. doi: 10.1002/hep.30490. Epub 2019 Mar 12. PMID: 30586158.

comments powered by Disqus