Leveraging Artificial Intelligence and Synthetic Data Derivatives for Spine Surgery Research.
Leveraging Artificial Intelligence and Synthetic Data Derivatives for Spine Surgery Research.
复制标题
DOI：
10.1177/21925682221085535
复制
发表时间：
2023-10
影响因子：
2.4
通讯作者：
Ray, Wilson Z.
中科院分区：
文献类型：
--
作者：
Greenberg, Jacob K.;Landman, Joshua M.;Kelly, Michael P.;Pennicooke, Brenton H.;Molina, Camilo A.;Foraker, Randi E.;Ray, Wilson Z.
关键词：
回顾性队列研究。利用电子健康记录（EHR）进行脊柱手术研究受到患者隐私和数据所有权问题的阻碍。合成数据衍生物可能有助于克服这些限制。本研究的目的是验证脊柱外科研究中使用的合成数据。数据来自15家医院的EHR。纳入了接受颈椎前路或腰椎后路融合术的患者（2010-2020年）。从EHR获得真实的数据。生成合成数据以模拟真实的数据的属性，而不与真实的患者保持一一对应。在每个队列中，使用逻辑回归和极端梯度增强机（XGBoost）评估预测30天再入院和30天并发症的能力。我们确定了9，072名真实的和9，088名人工颈椎融合患者。2个数据集的描述性特征几乎相同。当预测再入院时，使用逻辑回归和XGBoost，使用真实的和合成数据构建的模型的c-统计量均为0.69 - 0.71。在12,111例真实的和12,126例人工腰椎融合患者中，大多数变量的描述性特征几乎相同。使用逻辑回归和XGBoost来预测再入院，辨别力与使用真实的和合成数据建立的模型相似（c-统计量0.66 - 0.69）。当预测并发症时，使用真实的和合成数据得出的模型在两个队列中显示出相似的区分。尽管存在一些差异，但最有影响力的预测因子在真实的和合成数据集中是相似的。合成数据复制了真实的数据的大多数描述性和预测性，因此可以扩展脊柱手术中的EHR研究。
Retrospective cohort study. Leveraging electronic health records (EHRs) for spine surgery research is impeded by concerns regarding patient privacy and data ownership. Synthetic data derivatives may help overcome these limitations. This study’s objective was to validate the use of synthetic data for spine surgery research. Data came from the EHR from 15 hospitals. Patients that underwent anterior cervical or posterior lumbar fusion (2010-2020) were included. Real data were obtained from the EHR. Synthetic data was generated to simulate the properties of the real data, without maintaining a one-to-one correspondence with real patients. Within each cohort, ability to predict 30-day readmissions and 30-day complications was evaluated using logistic regression and extreme gradient boosting machines (XGBoost). We identified 9,072 real and 9,088 synthetic cervical fusion patients. Descriptive characteristics were nearly identical between the 2 datasets. When predicting readmission, models built using real and synthetic data both had c-statistics of .69-.71 using logistic regression and XGBoost. Among 12,111 real and 12,126 synthetic lumbar fusion patients, descriptive characteristics were nearly the same for most variables. Using logistic regression and XGBoost to predict readmission, discrimination was similar with models built using real and synthetic data (c-statistics .66-.69). When predicting complications, models derived using real and synthetic data showed similar discrimination in both cohorts. Despite some differences, the most influential predictors were similar in the real and synthetic datasets. Synthetic data replicate most descriptive and predictive properties of real data, and therefore may expand EHR research in spine surgery.
登录
查看更多内容
影响因子：
3.2
作者：
Benaim, Anat Reiner;Almog, Ronit;Beyar, Rafael
通讯作者：
Beyar, Rafael
影响因子：
8.1
作者：
Dash, Sabyasachi;Shakyawar, Sushil Kumar;Kaushik, Sandeep
通讯作者：
Kaushik, Sandeep
影响因子：
5.8
作者：
Stekhoven, Daniel J.;Buehlmann, Peter
通讯作者：
Buehlmann, Peter
影响因子：
2.4
作者：
Greenberg JK;Otun A;Ghogawala Z;Yen PY;Molina CA;Limbrick DD Jr;Foraker RE;Kelly MP;Ray WZ
通讯作者：
Ray WZ
影响因子：
3
作者：
Asher, Anthony L.;Speroff, Ted;McGirt, Mathew J.
通讯作者：
McGirt, Mathew J.