Couvy-Duchesne Baptiste, Faouzi Johann, Martin Benoît, Thibeau-Sutre Elina, Wild Adam, Ansart Manon, Durrleman Stanley, Dormont Didier, Burgos Ninon, Colliot Olivier
Paris Brain Institute, ICM, Paris, France.
Inserm, U 1127, Paris, France.
Front Psychiatry. 2020 Dec 15;11:593336. doi: 10.3389/fpsyt.2020.593336. eCollection 2020.
We ranked third in the Predictive Analytics Competition (PAC) 2019 challenge by achieving a mean absolute error (MAE) of 3.33 years in predicting age from T1-weighted MRI brain images. Our approach combined seven algorithms that allow generating predictions when the number of features exceeds the number of observations, in particular, two versions of best linear unbiased predictor (BLUP), support vector machine (SVM), two shallow convolutional neural networks (CNNs), and the famous ResNet and Inception V1. Ensemble learning was derived from estimating weights via linear regression in a hold-out subset of the training sample. We further evaluated and identified factors that could influence prediction accuracy: choice of algorithm, ensemble learning, and features used as input/MRI image processing. Our prediction error was correlated with age, and absolute error was greater for older participants, suggesting to increase the training sample for this subgroup. Our results may be used to guide researchers to build age predictors on healthy individuals, which can be used in research and in the clinics as non-specific predictors of disease status.
在2019年预测分析竞赛（PAC）挑战赛中，我们通过从T1加权脑部MRI图像预测年龄时实现了3.33年的平均绝对误差（MAE），排名第三。我们的方法结合了七种算法，这些算法允许在特征数量超过观测数量时生成预测，特别是两种版本的最佳线性无偏预测器（BLUP）、支持向量机（SVM）、两种浅层卷积神经网络（CNN）以及著名的ResNet和Inception V1。集成学习是通过在训练样本的留出子集中进行线性回归来估计权重而得出的。我们进一步评估并确定了可能影响预测准确性的因素：算法选择、集成学习以及用作输入的特征/ MRI图像处理。我们的预测误差与年龄相关，老年参与者的绝对误差更大，这表明需要增加该亚组的训练样本。我们的结果可用于指导研究人员为健康个体构建年龄预测器，这些预测器可在研究和临床中用作疾病状态的非特异性预测指标。
