Calesella Federico, Colombo Federica, Bravi Beatrice, Fortaner-Uyà Lidia, Monopoli Camilla, Poletti Sara, Tassi Emma, Maggioni Eleonora, Brambilla Paolo, Colombo Cristina, Bollettini Irene, Benedetti Francesco, Vai Benedetta
Psychiatry and Clinical Psychobiology Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milano, Italy.
Vita-Salute San Raffaele University, Milano, Italy.
Neurosci Appl. 2023 Dec 22;3:103931. doi: 10.1016/j.nsa.2023.103931. eCollection 2024.
Due to the overlapping depressive symptomatology with major depressive disorder (MDD), 60% of patients with bipolar disorder (BD) are initially misdiagnosed, calling for the definition of reliable biomarkers that can support the diagnostic process. Here, we optimized a machine learning pipeline for the differentiation between depressed BD and MDD patients based on multimodal structural neuroimaging features. Diffusion tensor imaging (DTI) and T1-weighted magnetic resonance imaging (MRI) data were acquired for 282 depressed BD (n = 180) and MDD (n = 102) patients. Images were preprocessed to obtain axial (AD), radial (RD), mean (MD) diffusivity, fractional anisotropy (FA), and voxel-based morphometry (VBM) maps. Each feature was entered separately into a 5-fold nested cross-validated predictive pipeline differentiating between BD and MDD patients, comprising: confound regression for nuisance variables removal, feature standardization, principal component analysis for feature reduction, and an elastic-net penalized regression. The DTI-based models reached accuracies ranging from 75% to 78%, whereas the VBM model reached 61% of accuracy. All the models were significantly different from a null model distribution at a 5000-permutation test. A 5000 bootstrap procedure revealed that widespread differences drove the classification, with BD patients associated to overall higher values of AD and FA, and grey matter volumes. Our results suggest that structural neuroimaging, in particular white matter microstructure and grey matter volumes, may be able to differentiate between MDD and BD patients with good predictive accuracy, being significantly higher than chance-level.
由于双相情感障碍（BD）与重度抑郁症（MDD）存在重叠的抑郁症状，60%的双相情感障碍患者最初被误诊，因此需要定义可靠的生物标志物来支持诊断过程。在此，我们基于多模态结构神经影像学特征，优化了一种机器学习流程，用于区分抑郁的双相情感障碍患者和重度抑郁症患者。对282例抑郁的双相情感障碍患者（n = 180）和重度抑郁症患者（n = 102）采集了扩散张量成像（DTI）和T1加权磁共振成像（MRI）数据。对图像进行预处理，以获得轴向扩散率（AD）、径向扩散率（RD）、平均扩散率（MD）、分数各向异性（FA）和基于体素的形态计量学（VBM）图谱。将每个特征分别输入到一个5折嵌套交叉验证的预测流程中，以区分双相情感障碍患者和重度抑郁症患者，该流程包括：对干扰变量进行混杂回归去除、特征标准化、用于特征约简的主成分分析以及弹性网惩罚回归。基于DTI的模型准确率在75%至78%之间，而VBM模型的准确率为61%。在5000次置换检验中，所有模型均与零模型分布有显著差异。一个5000次的自助程序显示，广泛的差异推动了分类，双相情感障碍患者的AD、FA和灰质体积总体值较高。我们的结果表明，结构神经影像学，特别是白质微观结构和灰质体积，可能能够以良好的预测准确率区分重度抑郁症患者和双相情感障碍患者，显著高于随机水平。
