基于感兴趣区脑表面形态学参数的可解释机器学习算法在区分早发性精神分裂症与双相障碍中的贡献
本研究纳入144例青少年(早发性精神分裂症81例、早发性双相障碍63例),基于高分辨率T1加权成像提取皮层厚度、脑回化、脑回化指数、沟深、分形维数和脑体积等表面形态学参数,应用机器学习分类器进行鉴别。AdaBoost算法在Destrieux图谱全变量数据集上准确率最高(82.75%),KNN在Desikan-Killiany-Tourville图谱全数据集上准确率最高(79.31%),SHAP技术用于解释各特征的贡献。
要点
- 基于T1加权成像的表面形态学参数结合机器学习可用于区分早发性精神分裂症与早发性双相障碍。
- AdaBoost在Destrieux图谱全变量数据集上准确率最高,为82.75%。
- KNN在Desikan-Killiany-Tourville图谱全数据集上准确率最高,为79.31%。
核心结论
- 本研究证明机器学习可利用表面形态学测量参数对早发性精神分裂症与早发性双相障碍进行鉴别诊断,未来研究可聚焦多中心数据以验证这些结果。
研究设计与样本
- 研究纳入144例青少年(16.2 ± 1.4岁,女性占39%),其中早发性精神分裂症81例、早发性双相障碍63例,采集高分辨率T1加权图像,测量皮层厚度、脑回化、脑回化指数、沟深、分形维数和脑体积,经特征选择后对各特征集及其组合应用机器学习分类器,并采用SHAP技术解释各特征贡献。
诊断标准与关键数值
- 在包含Destrieux图谱所有变量的全数据集中,AdaBoost算法准确率最高,为82.75%。
- 在分形维数特征子集中表现最佳的算法为K近邻(KNN)。
- 在沟深特征子集中表现最佳的算法为支持向量机(SVM)。
- 在脑回化指数特征子集中表现最佳的算法为AdaBoost。
- 在包含Desikan-Killiany-Tourville图谱所有变量的全数据集中,KNN算法准确率最高,为79.31%。
局限性
- 未来研究可聚焦多中心数据以验证这些结果。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: To differentiate early-onset schizophrenia (EOS) from early-onset bipolar disorder (EBD) using surface-based morphometry measurements and brain volumes using machine learning (ML) algorithms.
METHOD: High-resolution T1-weighted images were obtained to measure cortical thickness (CT), gyrification, gyrification index (GI), sulcal depth (SD), fractal dimension (FD), and brain volumes. After the feature selection step, ML classifiers were applied for each feature set and the combination of them. The SHapley Additive exPlanations (SHAP) technique was implemented to interpret the contribution of each feature.
FINDINGS: 144 adolescents (16.2 ± 1.4 years, female=39%) with EOS (n = 81) and EBD (n = 63) were included. The Adaptive Boosting (AdaBoost) algorithm had the highest accuracy (82.75%) in the whole dataset that includes all variables from Destrieux atlas. The best-performing algorithms were K-nearest neighbors (KNN) for FD subset, support vector machine (SVM) for SD subset, and AdaBoost for GI subset. The KNN algorithm had the highest accuracy (accuracy=79.31%) in the whole dataset from the Desikan-Killiany-Tourville atlas.
CONCLUSION: This study demonstrates the use of ML in the differential diagnosis of EOS and EBD using surface-based morphometry measurements. Future studies could focus on multicenter data for the validation of these results.
引用
- Saglam Y, Ermis C, Takir S, et al. The Contribution of Explainable Machine Learning Algorithms Using ROI-based Brain Surface Morphology Parameters in Distinguishing Early-onset Schizophrenia From Bipolar Disorder. Acad Radiol. 2024. PMID: 38704285. doi:10.1016/j.acra.2024.04.013
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。