浙大二院2013年-2026年经导管主动脉瓣置换术患者基线和长期随访数据集

本数据集系浙江大学医学院附属第二医院心内科在2013年至2026年间，在经导管主动脉瓣置换术（TAVR）临床诊疗、围手术期管理及长期随访过程中形成的科研数据集。数据真实可靠，且持续实时更新。数据全面系统地记录TAVR患者术前评估、术中记录、出院前以及术后1个月、术后每年长期随访四大模块，共包含367项标准化参数。
本数据集可为TAVR领域的临床科研、医疗质量改进与产业创新提供了坚实的数据基础。可以用于支持手术效果评估、并发症风险预测、临床路径优化和医疗器械疗效验证，还可用于构建风险预测模型、开展真实世界研究、助力精准医疗发展。同时，数据集能够为医疗质量管理、医保政策制定提供实证依据，并在合规前提下，作为高质量数据要素服务于医学人工智能训练、保险精算、公共卫生研究等跨界领域，推动医疗健康生态的协同发展。

This dataset is a scientific research dataset developed by the Department of Cardiology of the Second Affiliated Hospital, School of Medicine, Zhejiang University, based on the clinical diagnosis and treatment, perioperative management and long-term follow-up of patients undergoing transcatheter aortic valve replacement (TAVR) from 2013 to 2026. The data is authentic, reliable and updated in real time on an ongoing basis. It comprehensively and systematically documents four modules of data for TAVR patients, including preoperative assessment, intraoperative documentation, pre-discharge management, and postoperative follow-up (covering 1-month post-surgery follow-up and annual long-term follow-up), with a total of 367 standardized parameters.

This dataset provides a solid data foundation for clinical research, medical quality improvement and industrial innovation in the TAVR field. It can support surgical outcome assessment, complication risk prediction, clinical pathway optimization and efficacy validation of medical devices, as well as construct risk prediction models, conduct real-world studies and facilitate the development of precision medicine. Meanwhile, the dataset can offer empirical evidence for medical quality management and health insurance policy formulation. Under the premise of compliance, it can serve as high-quality data elements for cross-disciplinary fields including medical artificial intelligence training, insurance actuarial science and public health research, promoting the collaborative development of the medical and health ecosystem.

搜集汇总

背景与挑战

背景概述

该数据集涵盖2013-2026年TAVR患者的367项标准化临床数据，包括术前至长期随访全流程记录，为临床研究、风险预测及医疗创新提供支持，并适用于AI训练等跨界应用。