Random forest classifiers aid in the detection of incidental osteoblastic osseous metastases in DEXA studies
Random forest classifiers aid in the detection of incidental osteoblastic osseous metastases in DEXA studies
复制标题
DOI：
10.1007/s11548-019-01933-1
复制
发表时间：
2019-05-01
影响因子：
3
通讯作者：
Sebro, Ronnie
中科院分区：
文献类型：
--
作者：
Mehta, Samir D.;Sebro, Ronnie
目的双能X线骨密度仪（DEXA）用于筛查低骨密度（BMD）患者。乳腺癌和前列腺癌患者经常接受改变骨密度的药物治疗，导致骨密度降低。这些患者可能有偶然的脊柱成骨细胞转移，可以在筛选DEXA研究中检测到。本试验的目的是评估随机森林分类器或支持向量机是否可以从筛选DEXA研究中识别出脊柱偶发成骨细胞转移的患者，并评估哪种技术更好。（155例正常对照患者和45例L1至L4一个或多个腰椎椎体成骨细胞转移患者）。数据集分为训练（80%）和验证（20%）数据集。得到了最优的随机森林（RF）和支持向量机（SVM）分类器。结果在验证数据集中，最优RF分类器的灵敏度、特异度、准确度和曲线下面积（AUC）分别为77.8%、100.0%、98.0%和0.889。最优SVM分类器的灵敏度、特异度、准确度和AUC分别为33.3%、96.8%、82.5%和0.651。RF分类器显著优于SVM分类器（P=0.008）。只有7的45例成骨细胞转移（15.6%）的前瞻性确定的放射科医师解释study.ConclusionsRF分类器可以作为一个有用的辅助手段，以确定偶然的腰椎成骨细胞转移筛选DEXA研究。
PurposeDual-energy X-ray absorptiometry (DEXA) studies are used for screening patients for low bone mineral density (BMD). Patients with breast and prostate cancer are often treated with hormone-altering drugs that result in low BMD. These patients may have incidental osteoblastic metastases of the spine that may be detected on screening DEXA studies. The aim of this pilot study is to assess whether random forest classifiers or support vector machines can identify patients with incidental osteoblastic metastases of the spine from screening DEXA studies and to evaluate which technique is better.MethodsWe retrospectively reviewed the DEXA studies from 200 patients (155 normal control patients and 45 patients with osteoblastic metastases of one or more lumbar vertebral bodies from L1 to L4). The dataset was split into training (80%) and validation (20%) datasets. The optimal random forest (RF) and support vector machine (SVM) classifiers were obtained. Receiver-operator-characteristic curves were compared with DeLong's test.ResultsThe sensitivity, specificity, accuracy and area under the curve (AUC) of the optimal RF classifier were 77.8%, 100.0%, 98.0% and 0.889, respectively, in the validation dataset. The sensitivity, specificity, accuracy and AUC of the optimal SVM classifier were 33.3%, 96.8%, 82.5% and 0.651 in the validation dataset. The RF classifier was significantly better than the SVM classifier (P=0.008). Only 7 of the 45 patients with osteoblastic metastases (15.6%) were prospectively identified by the radiologist interpreting the study.ConclusionsRF classifiers can be used as a useful adjunct to identify incidental lumbar spine osteoblastic metastases in screening DEXA studies.