在肺癌患者中与完全植入的静脉接入口相关的长期并发症的预测模型
Jian Jia1,2, Xutong Fan3, Wenhong Zhang2,4
1Department of General Practice, The First Affiliated Hospital with Nanjing Medical University, Nanjing, Jiangsu 210029, P.R. China.
Oncology letters
|May 29, 2024
概括
这项研究开发了一种机器学习模型,用于预测肺癌患者的完全植入静脉接入口 (TIVAP) 的长期并发症. 一类SVM模型显示了早期检测的前景,可能节省资源.
科学领域:
- 医疗信息学 医疗信息学
- 在瘤学瘤学.
- 血管外科 血管外科
背景情况:
- 完全植入的静脉接入口 (TIVAPs) 对于化疗和营养支持至关重要,提高患者的生活质量.
- 长期的并发症,包括迁移,血栓形成和感染,需要TIVAP去除,并产生大量的医疗保健费用.
- 对TIVAP并发症的预测模型对于瘤患者的积极管理有价值.
研究的目的:
- 开发和评估TIVAP植入肺癌患者后长期并发症的预测模型.
- 为了比较隔离森林,一类SVM和局部异常因子算法在预测TIVAP并发症方面的有效性.
- 确定影响TIVAP相关不良事件的潜在因素.
主要方法:
- 一项回顾性研究包括902名接受TIVAP植入的肺癌患者.
- 患者被分为训练 (70%) 和测试 (30%) 队列.
- 使用三种机器学习算法 (隔离森林,一类SVM,局部异常因素) 来构建长期并发症的预测模型.
主要成果:
- 长期TIVAP并发症的总发病率为3.1% (902名患者中有28名).
- 一级SVM模型实现了最高的性能,MCC为0.078,AUC为0.62,精度为66.0%.
- 开发的模型显示了对分类并发症风险的潜力.
结论:
- 基于机器学习的预测模型,特别是使用一类SVM,可以帮助在肺癌患者中早期检测TIVAP相关并发症.
- 早期检测可能会导致更好的患者结果,降低治疗成本,并节省医疗资源.
- 需要进一步的研究和验证来完善该模型的临床应用.
更多相关视频
相关概念视频
Peripheral Artery Disease V: Postoperative Nursing Management
During the postoperative period, it is crucial to focus on maintaining circulation, identifying and managing potential complications, and planning for discharge.Nursing AssessmentVital signs monitoring: Regularly monitor vital signs, including blood pressure, heart rate, respiratory rate, and temperature, to detect early signs of complications such as bleeding and infection.Circulation assessment: Monitor pulses, perform Doppler assessments, and check capillary refill, color, temperature, and...
Venous Thrombosis III: Interprofessional Care
Venous thrombosis requires effective prevention and treatment strategies to improve patient outcomes and reduce potential complications.Prevention StrategiesHealthcare providers must prioritize preventing venous thromboembolism (VTE) for all adult patients upon admission. Interventions depend on bleeding and thrombosis risk, medical history, current medications, diagnoses, planned procedures, and patient preferences. Patients on bed rest should change positions every two hours and, if not...


