相关实验视频
Updated: Jul 24, 2025

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
将更新的ICD-10-CA与AIS-2005更新2008算法进行内部和外部验证
Bourke W Tillmann1, Matthew P Guttman, Jaimini Thakore
1From the Interdepartmental Division of Critical Care (B.W.T., D.C.S., B.H.), University of Toronto; Department of Critical Care Medicine (B.W.T., D.C.S., B.H.), Sunnybrook Health Sciences Centre; Institute of Health Policy, Management, and Evaluation (B.W.T., M.P.G., A.B.N., D.C.S., P.P., B.H.), Department of Surgery (M.P.G., A.B.N., B.H.), University of Toronto, Toronto, Ontario; Trauma Services (J.T., J.M.M., R.G.), Provincial Health Services Authority; Division of General Surgery, Department of Surgery, (D.C.E.), University of British Columbia, Vancouver, British Columbia; ICES (A.B.N., P.P., D.C.S., P.P., B.H.); Sunnybrook Research Institute (A.B.N., D.C.S., B.H.); Tory Trauma Program (A.P.), Sunnybrook Health Sciences Centre, Toronto, Ontario; Department of Surgery (N.L.Y.), University of Calgary, Calgary, Alberta; Department of Medicine (D.C.S.), University of Toronto; Toronto Health Economic and Technology Assessment Collaborative (P.P.); and The Hospital for Sick Children (P.P.), Toronto, Ontario, Canada.
这项研究验证了一种算法,用于从行政数据中的国际疾病分类 (ICD-10-CA) 代码计算缩写伤害量表 (AIS) 评分. 该算法可靠地估计伤害严重程度,使创伤研究的风险调整成为可能.
科学领域:
- 创伤研究和公共卫生监测.
- 开发和验证临床算法.
- 卫生信息学和行政数据利用.
背景情况:
- 行政数据对于人口层面的创伤研究至关重要.
- 现有的行政数据缺乏特定的创伤诊断和伤害严重程度代码.
- 这限制了创伤护理中的风险调整比较分析.
研究的目的:
- 为了验证一个算法来导出缩写伤害量表 (AIS-2005更新2008年) 的严重程度得分.
- 从行政数据中使用加拿大国际疾病分类 (ICD-10-CA) 诊断代码.
- 在基于人群的创伤研究中实现准确的风险调整.
主要方法:
- 使用安大略省创伤登记 (2009-2017) 进行内部验证的回顾性队列研究.
- 专家分配的AIS分数与使用Cohen的kappa和类内相关系数的算法衍生分数的比较.
- 使用行政数据 (2009-2017) 进行外部验证,以评估区分能力和通过后勤回归进行校准.
主要成果:
- 专家指派和算法衍生的AIS分数之间的高度一致性用于识别严重伤害 (kappa = 0.75).
- 该算法在检测严重伤害方面表现出强烈的灵敏度 (95.1%) 和特异性 (78.5%).
- 专家分配和衍生损伤严重性得分之间存在强烈的相关性 (ICC = 0.80);算法在外部验证中保持了歧视性属性.
结论:
- 开发的ICD-10-CA到AIS-2005算法从行政数据提供可靠的损伤严重程度估计.
- 该算法在应用于大型行政数据集时保留了其歧视性属性.
- 该工具有助于在基于人群的创伤研究中对受伤结果进行风险调整.
相关概念视频
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
Formulating and Validating Nursing Diagnosis II
Risk nursing diagnoses represent clinical judgments of an individual, family, or community more vulnerable to developing the health problem than others...
Diagnostic and Statistical Manual of Mental Disorders (DSM)
Formulating and Validating Nursing Diagnosis I
There are thirteen domains...
Nursing Clinical Information System
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
Standards of Care II

