De Silva Tharindu, Vedula S Swaroop, Perdomo-Pantoja Alexander, Vijayan Rohan, Doerr Sophia A, Uneri Ali, Han Runze, Ketcha Michael D, Skolasky Richard L, Witham Timothy, Theodore Nicholas, Siewerdsen Jeffrey H
Johns Hopkins University, Department of Biomedical Engineering, Baltimore, Maryland, United States.
Johns Hopkins University, Malone Center for Engineering in Healthcare, Baltimore, Maryland, United States.
J Med Imaging (Bellingham). 2020 May;7(3):031502. doi: 10.1117/1.JMI.7.3.031502. Epub 2020 Feb 18.
Data-intensive modeling could provide insight on the broad variability in outcomes in spine surgery. Previous studies were limited to analysis of demographic and clinical characteristics. We report an analytic framework called "SpineCloud" that incorporates quantitative features extracted from perioperative images to predict spine surgery outcome. A retrospective study was conducted in which patient demographics, imaging, and outcome data were collected. Image features were automatically computed from perioperative CT. Postoperative 3- and 12-month functional and pain outcomes were analyzed in terms of improvement relative to the preoperative state. A boosted decision tree classifier was trained to predict outcome using demographic and image features as predictor variables. Predictions were computed based on SpineCloud and conventional demographic models, and features associated with poor outcome were identified from weighting terms evident in the boosted tree. Neither approach was predictive of 3- or 12-month outcomes based on preoperative data alone in the current, preliminary study. However, SpineCloud predictions incorporating image features obtained during and immediately following surgery (i.e., intraoperative and immediate postoperative images) exhibited significant improvement in area under the receiver operating characteristic (AUC): ( to 0.83) at 3 months and ( to 0.82) at 12 months. Predictive modeling of lumbar spine surgery outcomes was improved by incorporation of image-based features compared to analysis based on conventional demographic data. The SpineCloud framework could improve understanding of factors underlying outcome variability and warrants further investigation and validation in a larger patient cohort.
数据密集型建模可以为脊柱手术结果的广泛变异性提供见解。以往的研究仅限于对人口统计学和临床特征的分析。我们报告了一个名为“SpineCloud”的分析框架，该框架整合了从围手术期图像中提取的定量特征，以预测脊柱手术结果。我们进行了一项回顾性研究，收集了患者的人口统计学、影像学和结果数据。图像特征由围手术期CT自动计算得出。根据相对于术前状态的改善情况，分析了术后3个月和12个月的功能和疼痛结果。使用人口统计学和图像特征作为预测变量，训练了一个增强决策树分类器来预测结果。基于SpineCloud和传统人口统计学模型计算预测结果，并从增强树中明显的加权项中识别出与不良结果相关的特征。在当前的初步研究中，仅基于术前数据，这两种方法都无法预测3个月或12个月的结果。然而，纳入手术期间和手术后立即获得的图像特征（即术中及术后即刻图像）的SpineCloud预测在受试者操作特征曲线下面积（AUC）方面有显著改善：3个月时从（具体数值）提高到0.83，12个月时从（具体数值）提高到0.82。与基于传统人口统计学数据的分析相比，纳入基于图像的特征可改善腰椎手术结果的预测建模。SpineCloud框架可以增进对结果变异性潜在因素的理解，值得在更大的患者队列中进行进一步研究和验证。
