对用机器学习预测晚期癌症患者短期生存的症状管理药物的评估
Hua-Shui Hsu1,2,3,4, Chia-Hung Kao5,6,7, Shih-Sheng Chang5,8
1Department of Family Medicine and Social Medicine, School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan.
药物使用,特别是便软化剂,抗emetics和镇静剂,可以预测晚期癌症患者的生存率. 这些信息有助于医生制定有效的息护理计划,以改善患者的治疗结果.
科学领域:
- 在瘤学瘤学.
- 抚慰性护理是一种缓解性护理.
- 医疗信息学 医疗信息学
背景情况:
- 预估晚期癌症患者的预后对于有效的息护理计划至关重要.
- 年轻的医生和医疗团队从预测患者存活率的工具中受益.
- 不同的症状和临床数据需要复杂的分析来准确预测.
研究的目的:
- 评估药物使用的预测价值,并发症,实验室结果,以及住院晚期癌症患者短期生存的生命体征.
- 开发和验证用于预测14天内死亡的机器学习模型.
主要方法:
- 对住院晚期癌症患者的回顾性分析,这些患者被接收到宿舍病房.
- 使用极端梯度提升 (XGBoost) 和随机森林-XGBoost (RF-XGBoost) 模型.
- 为了特征解释性,使用了夏普利添加式解释 (SHAP).
主要成果:
- XGBoost和RF-XGBoost模型实现了高预测精度 (AUC分别为0.82和0.81).
- 药物使用 (便软化剂,抗emetics,镇静剂) 和实验室测试是关键预测因素.
- 具体的药物,如便软化剂,抗emetics,和镇静剂显示强大的正相关性与生存超过14天.
结论:
- 药物类型,特别是便软化剂,抗emetics和镇静剂,是晚期癌症患者生存的重要预测因素.
- 这些发现可以帮助医疗保健提供者改进息治疗策略.
- 改进的预后工具提高了对患者及其家属在终身护理期间的支持.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Pleural Effusion II: Symptoms and Management
A pleural effusion is the abnormal collection of fluid between the parietal and visceral pleura layers of tissue that form the lining of the lungs and chest cavity. It can occur independently or due to surrounding parenchymal diseases, such as infection, malignancy, or inflammatory conditions.
Clinical Manifestations:
Cancer Survival Analysis
Three-Phase Short Circuit—Unloaded Synchronous Machine
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
Endocarditis III: Medical Management
Myocarditis III: Medical Management
Pericarditis III: Medical Management
