Pôle Hospitalo-Universitaire de Psychiatrie d'Adultes et d'Addictologie du Grand Nancy, Centre Psychothérapique de Nancy, Laxou, France; INSERM U1254, IADI, Université de Lorraine, Nancy, France; Faculté de Médecine, Université de Lorraine, Vandœuvre-lès-Nancy, France.
Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France.
J Affect Disord. 2022 Jun 1;306:208-214. doi: 10.1016/j.jad.2022.03.025. Epub 2022 Mar 15.
Major depressive disorder (MDD) is a major public health problem. The retina is a relevant site to indirectly study brain functioning. Alterations in retinal processing were demonstrated in MDD with the pattern electroretinogram (PERG). Here, the relevance of signal processing and machine learning tools applied on PERG was studied.
PERG - whose stimulation is reversible checkerboards - was performed according to the International Society for Clinical Electrophysiology of Vision (ISCEV) standards in 24 MDD patients and 29 controls at the inclusion. PERG was recorded every 4 weeks for 3 months in patients. Amplitude and implicit time of P50 and N95 were evaluated. Then, time/frequency features were extracted from the PERG time series based on wavelet analysis. A statistical model has been learned in this feature space and a metric aiming at quantifying the state of the MDD patient has been derived, based on minimum covariance determinant (MCD) mahalanobis distance.
MDD patients showed significant increase in P50 and N95 implicit time (p = 0,006 and p = 0,0004, respectively, Mann-Whitney U test) at the inclusion. The proposed metric extracted from the raw PERG provided discrimination between patients and controls at the inclusion (p = 0,0001). At the end of the follow-up at week 12, the difference between the metrics extracted on controls and patients was not significant (p = 0,07), reflecting the efficacy of the treatment.
Signal processing and machine learning tools applied on PERG could help clinical decision in the diagnosis and the follow-up of MDD in measuring treatment response.
重度抑郁症（MDD）是一个重大的公共卫生问题。视网膜是一个可以间接研究大脑功能的相关部位。在 MDD 中，模式视网膜电图（PERG）显示了视网膜处理的改变。在此，研究了应用于 PERG 的信号处理和机器学习工具的相关性。
根据国际临床视觉电生理学协会（ISCEV）的标准，对 24 名 MDD 患者和 29 名对照者进行 PERG 检查，纳入时进行 PERG 检查。患者每 4 周记录一次，持续 3 个月。评估 P50 和 N95 的振幅和潜伏期。然后，基于小波分析从 PERG 时间序列中提取时间/频率特征。在这个特征空间中学习了一个统计模型，并基于最小协方差判别（MCD）马氏距离，得出了一个旨在量化 MDD 患者状态的度量标准。
MDD 患者在纳入时 P50 和 N95 潜伏期明显增加（p=0.006 和 p=0.0004，Mann-Whitney U 检验）。从原始 PERG 中提取的建议度量标准在纳入时可以区分患者和对照组（p=0.0001）。在第 12 周的随访结束时，从对照组和患者身上提取的度量标准之间的差异不显著（p=0.07），反映了治疗的效果。
应用于 PERG 的信号处理和机器学习工具可以帮助临床决策，在诊断和随访 MDD 时测量治疗反应。
