文献速递骨质疏松与代谢性骨病

基于通用数据模型开发与验证的机器学习骨折预测模型

Development and validation of common data model-based fracture prediction model using machine learning algorithm.
PubMed 文献 · Osteoporos Int · 2023-05-17

该研究利用韩国医院队列的通用数据模型数据库,纳入2008至2011年间接受双能X线吸收法骨密度检查的50岁以上参与者,发现队列20107例、验证队列13353例,采用DeepHit与Cox比例风险模型构建骨质疏松性骨折评分系统并在独立队列中验证,模型包含骨折史、年龄、腰椎与全髋T值及心血管疾病等预测因子,发现队列主要骨质疏松性骨折与髋部骨折的Harrell C指数分别为0.789和0.860,验证队列分别为0.762和0.773。

要点

  • 主要骨质疏松性骨折评分模型纳入骨折史、年龄、腰椎T值、全髋T值及心血管疾病。
  • 髋部骨折评分模型纳入骨折史、年龄、全髋T值、脑血管疾病及糖尿病。
  • 发现队列主要骨质疏松性骨折与髋部骨折C指数为0.789和0.860,验证队列为0.762和0.773。

核心结论

  • 作者从医院队列开发了骨质疏松性骨折评分系统并在独立队列中验证,认为这些简易评分模型可能有助于真实世界实践中预测骨折风险。

研究设计与样本

  • 研究利用通用数据模型数据库,发现队列20107例、验证队列13353例,均为2008至2011年间有双能X线吸收法骨密度数据的50岁以上参与者。
  • 主要结局为主要骨质疏松性骨折与髋部骨折事件,采用DeepHit和Cox比例风险模型识别预测因子并构建评分系统。

主要发现

  • 平均年龄64.5岁,84.3%为女性,平均随访7.6年期间观察到1990例主要骨质疏松性骨折和309例髋部骨折事件。
  • 主要骨质疏松性骨折最终评分模型选择骨折史、年龄、腰椎T值、全髋T值及心血管疾病作为预测因子。
  • 髋部骨折评分模型选择骨折史、年龄、全髋T值、脑血管疾病及糖尿病作为预测因子。
  • 发现队列主要骨质疏松性骨折与髋部骨折的Harrell C指数分别为0.789和0.860,验证队列分别为0.762和0.773。
  • 主要骨质疏松性骨折与髋部骨折的估计10年风险在评分0分时分别为2.0%和0.2%,在各自最高分时分别为68.8%和18.8%。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

UNLABELLED: The need for an accurate country-specific real-world-based fracture prediction model is increasing. Thus, we developed scoring systems for osteoporotic fractures from hospital-based cohorts and validated them in an independent cohort in Korea. The model includes history of fracture, age, lumbar spine and total hip T-score, and cardiovascular disease. PURPOSE: Osteoporotic fractures are substantial health and economic burden. Therefore, the need for an accurate real-world-based fracture prediction model is increasing. We aimed to develop and validate an accurate and user-friendly model to predict major osteoporotic and hip fractures using a common data model database. METHODS: The study included 20,107 and 13,353 participants aged ≥ 50 years with data on bone mineral density using dual-energy X-ray absorptiometry from the CDM database between 2008 and 2011 from the discovery and validation cohort, respectively. The main outcomes were major osteoporotic and hip fracture events. DeepHit and Cox proportional hazard models were used to identify predictors of fractures and to build scoring systems, respectively. RESULTS: The mean age was 64.5 years, and 84.3% were women. During a mean of 7.6 years of follow-up, 1990 major osteoporotic and 309 hip fracture events were observed. In the final scoring model, history of fracture, age, lumbar spine T-score, total hip T-score, and cardiovascular disease were selected as predictors for major osteoporotic fractures. For hip fractures, history of fracture, age, total hip T-score, cerebrovascular disease, and diabetes mellitus were selected. Harrell's C-index for osteoporotic and hip fractures were 0.789 and 0.860 in the discovery cohort and 0.762 and 0.773 in the validation cohort, respectively. The estimated 10-year risks of major osteoporotic and hip fractures were 2.0%, 0.2% at score 0 and 68.8%, 18.8% at their maximum scores, respectively. CONCLUSION: We developed scoring systems for osteoporotic fractures from hospital-based cohorts and validated them in an independent cohort. These simple scoring models may help predict fracture risks in real-world practice.

来源:Osteoporos Int,查看原文。版权归原作者所有。

引用

  1. Kong SH, Kim S, Kim Y, et al. Development and validation of common data model-based fracture prediction model using machine learning algorithm. Osteoporos Int. 2023. PMID: 37195320. doi:10.1007/s00198-023-06787-7

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。