New York University School of Medicine, New York, New York, USA.
Department of Twin Research and Genetic Epidemiology, Kings College, London, UK.
J Magn Reson Imaging. 2019 Apr;49(4):1029-1038. doi: 10.1002/jmri.26280. Epub 2018 Sep 25.
A current challenge in osteoporosis is identifying patients at risk of bone fracture.
To identify the machine learning classifiers that predict best osteoporotic bone fractures and, from the data, to highlight the imaging features and the anatomical regions that contribute most to prediction performance.
Prospective (cross-sectional) case-control study.
Thirty-two women with prior fragility bone fractures, of mean age = 61.6 and body mass index (BMI) = 22.7 kg/m , and 60 women without fractures, of mean age = 62.3 and BMI = 21.4 kg/m . Field Strength/ Sequence: 3D FLASH at 3T.
Quantitative MRI outcomes by software algorithms. Mechanical and topological microstructural parameters of the trabecular bone were calculated for five femoral regions, and added to the vector of features together with bone mineral density measurement, fracture risk assessment tool (FRAX) score, and personal characteristics such as age, weight, and height. We fitted 15 classifiers using 200 randomized cross-validation datasets. Statistical Tests: Data: Kolmogorov-Smirnov test for normality. Model Performance: sensitivity, specificity, precision, accuracy, F1-test, receiver operating characteristic curve (ROC). Two-sided t-test, with P < 0.05 for statistical significance.
The top three performing classifiers are RUS-boosted trees (in particular, performing best with head data, F1 = 0.64 ± 0.03), the logistic regression and the linear discriminant (both best with trochanteric datasets, F1 = 0.65 ± 0.03 and F1 = 0.67 ± 0.03, respectively). A permutation of these classifiers comprised the best three performers for four out of five anatomical datasets. After averaging across all the anatomical datasets, the score for the best performer, the boosted trees, was F1 = 0.63 ± 0.03 for All-features dataset, F1 = 0.52 ± 0.05 for the no-MRI dataset, and F1 = 0.48 ± 0.06 for the no-FRAX dataset. Data Conclusion: Of many classifiers, the RUS-boosted trees, the logistic regression, and the linear discriminant are best for predicting osteoporotic fracture. Both MRI and FRAX independently add value in identifying osteoporotic fractures. The femoral head, greater trochanter, and inter-trochanter anatomical regions within the proximal femur yielded better F1-scores for the best three classifiers.
2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1029-1038.
骨质疏松症目前面临的一个挑战是识别有骨折风险的患者。
确定预测骨质疏松性骨折的最佳机器学习分类器，并从数据中突出对预测性能贡献最大的成像特征和解剖区域。
前瞻性（横断面）病例对照研究。
32 名有脆性骨折既往史的女性，平均年龄 61.6 岁，体重指数（BMI）为 22.7 kg/m2，60 名无骨折的女性，平均年龄 62.3 岁，BMI 为 21.4 kg/m2。场强/序列：3T 下的 3D FLASH。
通过软件算法进行定量 MRI 结果评估。计算了五个股骨区域的小梁骨的机械和拓扑微观结构参数，并将其与骨密度测量、骨折风险评估工具（FRAX）评分以及年龄、体重和身高等个人特征一起添加到特征向量中。我们使用 200 个随机交叉验证数据集拟合了 15 个分类器。
数据：Kolmogorov-Smirnov 检验用于正态性。模型性能：灵敏度、特异性、精度、准确性、F1 检验、接收者操作特征曲线（ROC）。双侧 t 检验，P < 0.05 为统计学意义。
表现最好的前三个分类器是 RUS 增强树（特别是头部数据的表现最佳，F1=0.64±0.03）、逻辑回归和线性判别（两者在转子间数据集的表现最佳，F1=0.65±0.03 和 F1=0.67±0.03）。这四个解剖数据集的最佳分类器中，有三个是由这些分类器的排列组成的。在平均了所有解剖数据集后，表现最好的分类器，即增强树，在所有特征数据集上的 F1 得分为 0.63±0.03，在无 MRI 数据集上的 F1 得分为 0.52±0.05，在无 FRAX 数据集上的 F1 得分为 0.48±0.06。
在众多分类器中，RUS 增强树、逻辑回归和线性判别最适合预测骨质疏松性骨折。MRI 和 FRAX 均可独立增加对骨质疏松性骨折的识别。在预测最佳三个分类器的性能时，股骨近端的股骨头、大转子和转子间区域产生了更好的 F1 评分。
2 技术功效：第 2 阶段 J. Magn. Reson. Imaging 2019;49:1029-1038.
