Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan.
Psychiatry Clin Neurosci. 2022 Jun;76(6):260-267. doi: 10.1111/pcn.13350. Epub 2022 Apr 14.
Recently, a machine-learning (ML) technique has been used to create generalizable classifiers for psychiatric disorders based on information of functional connections (FCs) between brain regions at resting state. These classifiers predict diagnostic labels by a weighted linear sum (WLS) of the correlation values of a small number of selected FCs. We aimed to develop a generalizable classifier for gambling disorder (GD) from the information of FCs using the ML technique and examine relationships between WLS and clinical data.
As a training dataset for ML, data from 71 GD patients and 90 healthy controls (HCs) were obtained from two magnetic resonance imaging sites. We used an ML algorithm consisting of a cascade of an L1-regularized sparse canonical correlation analysis and a sparse logistic regression to create the classifier. The generalizability of the classifier was verified using an external dataset. This external dataset consisted of six GD patients and 14 HCs, and was collected at a different site from the sites of the training dataset. Correlations between WLS and South Oaks Gambling Screen (SOGS) and duration of illness were examined.
The classifier distinguished between the GD patients and HCs with high accuracy in leave-one-out cross-validation (area under curve (AUC = 0.89)). This performance was confirmed in the external dataset (AUC = 0.81). There was no correlation between WLS, and SOGS and duration of illness in the GD patients.
We developed a generalizable classifier for GD based on information of functional connections between brain regions at resting state.
最近，一种机器学习（ML）技术被用于根据静息状态下脑区之间的功能连接（FC）信息，创建用于精神障碍的可推广分类器。这些分类器通过对少数选定 FC 的相关值的加权线性和（WLS）来预测诊断标签。我们旨在使用 ML 技术从 FC 信息中开发用于赌博障碍（GD）的可推广分类器，并研究 WLS 与临床数据之间的关系。
作为 ML 的训练数据集，我们从两个磁共振成像地点获得了 71 名 GD 患者和 90 名健康对照者（HCs）的数据。我们使用由 L1 正则化稀疏典型相关分析和稀疏逻辑回归组成的 ML 算法来创建分类器。使用来自不同地点的外部数据集验证分类器的通用性。该外部数据集由 6 名 GD 患者和 14 名 HCs 组成，与训练数据集的地点不同。还检查了 WLS 与 South Oaks Gambling Screen（SOGS）和疾病持续时间之间的相关性。
分类器在留一交叉验证中（曲线下面积（AUC = 0.89））以很高的准确度区分 GD 患者和 HCs。这一性能在外部数据集中得到了验证（AUC = 0.81）。在 GD 患者中，WLS 与 SOGS 和疾病持续时间之间没有相关性。
我们基于静息状态下脑区之间的功能连接信息，开发了用于 GD 的可推广分类器。
