基于静息态功能磁共振图像的动态功能连接特征的智商预测

目的近年来越来越多的研究表明大脑不同脑区间的功能连接的动态波动具有生理意义,但关于智商(intelligence quotient,IQ)的相关研究较少。本文基于动态功能连接(dynamic functional connectivity,DFC)提取动态特征对智商进行评估,为智商预测探索新的特征参数和预测模型。方法基于97个儿童静息态功能磁共振图像(resting state functional magnetic resonance image,RS-fMRI),采用滑动窗相关计算方法构建DFC。基于DFC提取相应时域、频域特征,通过弹性网(elastic-net,E-Net)和最小角回归(least angle regression,LAR)算法建立智商回归模型进行个体智商预测,并通过置换检验验证其显著性。结果基于动态功能连接的特定频段(0.075~0.1 Hz)频域特征和波动均值特征,可以实现对智商的基本预测,且频域特征的表现优于时域特征。另外,基于LAR算法构建的预测模型的表现优于E-Net算法。结论个体脑功能连接随时间的动态波动足以预测个体智商,且特定频段的频域特征和LAR算法能够提高预测准确率,这可为个体智商评估研究和动态功能连接的应用提供新的思路。

Prediction of intelligence quotient based on the characteristics of dynamic functional connectivity in resting state fMRI

Objective In recent years,studies have shown that the dynamic fluctuations of functional connectivity can reflect physiological information,but few studies about intelligence quotient(IQ).This study evaluated IQ based on features extracted from dynamic functional connectivity(DFC),and new feature parameters and prediction models are explored for IQ prediction.MethodsIn the study resting state functional magnetic resonance imaging(RS-fMRI)data of 97 children subjects were selected,and the sliding window technique was used to constructed DFC.Based on DFC,the time domain and frequency domain characteristics were extracted,IQ regression models were established with the use of elastic net(E-Net)and least angle regression(LAR)algorithm,and its significance was verified by Permutation test.ResultsIndividuals’IQ could be predicted by frequency domain of 0.075-0.01 Hz and the mean strength of dynamic fluctuation,the performance of frequency domain was better than that of time domain characteristics.Besides,the performance of the model based on the LAR algorithm was better than that of the E-Net algorithm.ConclusionsIQ can be predicted by DFC characteristics,the frequency domain characteristics of specific frequency band and LAR algorithm can improve the prediction accuracy.This result provides new ideas for further research about IQ prediction and dynamic functional connectivity.