相关实验视频

Updated: Jun 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

可解释的机器学习模型用于在接受重大手术的癌症住院患者手术前预测术后并发症

Matthew C Hernandez¹, Chen Chen², Andrew Nguyen³

¹Department of Surgery, University of New Mexico, Albuquerque, NM.

JCO clinical cancer informatics

|April 22, 2024

概括

一个可解释的机器学习模型准确地预测了接受重大手术的癌症患者的术后并发症 (CD 3+). 该工具利用电子健康记录来识别高风险个体,改善患者护理和手术结果.

科学领域:

在瘤学瘤学.
医疗信息学医疗信息学
外科手术的结果

背景情况:

在接受重大手术的癌症患者中预测术后并发症 (PC) 是复杂的.
现有的方法往往缺乏准确性和可解释性,对于异质的患者群体.

研究的目的:

开发和验证一种可解释的机器学习 (ML) 模型,用于预测癌症住院患者的30天术后并发症 (CD 3+).
使用沙普利增量解释 (SHAP) 方法识别关键预测特征.

主要方法:

对827名癌症住院患者进行的988次手术的回顾性审查 (2017年12月 - 2021年6月).
使用电子健康记录 (EHR) 数据开发和测试ML模型.
使用AUROC,AUPRC和校准图表进行性能评估;用于模型解释性的SHAP.

主要成果:

在预测CD 3+并发症方面,ML模型实现了AUROC为0.77 (训练) 和0.73 (保持) 和AUPRC为0.56 (训练) 和0.52 (保持).
并发症率为28.6% (训练) 和27.5% (坚持).
SHAP分析确定了关键的风险因素及其在个人和队列层面的贡献.

结论:

一个可解释的ML模型可以准确地预测癌症患者严重的术后并发症的风险.
该模型利用患者特定的EHR数据进行风险分层.
可解释性特征通过突出关键预测因素来提高临床实用性.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

相关概念视频

Cancer Survival Analysis

Cancer Survival Analysis

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...