Dynamic time warping outperforms Pearson correlation in detecting atypical functional connectivity in autism spectrum disorders

Assessment of Flourishing Levels of Individuals by Using Resting State fNIRS with Different Functional Connectivity Measures

“…Our result supports the idea to combine the feature sets extracted from both connectivity measures for classification to obtain higher accuracy compared to using one type of connectivity measure (Meszlenyi, Buza, et al, 2017). Both measures have their own pros and cons and they should be used together to reveal the potential differences between groups due to focusing different aspects of functional networks (Linke et al, 2020). Further basic research is needed to reveal the reason that causes this difference.…”

“…Compared to CC, DTW is a novel measure in functional connectivity estimation and few studies were performed by utilizing DTW for EEG (Karamzadeh et al, 2013), fMRI (Jin et al, 2020; Linke et al, 2020; Meszlenyi, Hermann, et al, 2017; Mohanty et al, 2020) and fNIRS (Gokcay et al, 2019). In a recent study, it was shown that its efficiency outperformed conventional CC approach to detect atypical connectivity patterns in autism and it was reported that DTW was found sensitive to BOLD signal amplitude which is dependent on Hb concentration (Linke et al, 2020). In another study that uses DTW and CC to classify ADHD patients and gender groups, it was reported that DTW showed better performance for classification using SVM and Least Absolute Shrinkage and Selection Operator (LASSO) (Meszlényi et al, 2016).…”

“…For warping window length l , We chose warping window length l as 1 sec (10 samples). After estimating the DTW distance for functional connectivity, as it was previously stated in (Linke et al, 2020; Meszlenyi, Hermann, et al, 2017), we first normalized the distance by dividing it to length of the time series. Then, we multiplied the values to -1 and demeaned to a transform distance.…”

“…The other approach, DTW has previously been used in both fMRI (Linke et al, 2020; Meszlenyi, Hermann, et al, 2017), EEG (Karamzadeh et al, 2013) and fNIRS based connectivity studies (Gokcay et al, 2019). DTW is a template matching method used for similarity measurement of two time-varying time series (Sakoe & Chiba, 1978).…”

“…Also, while estimating the connectivity matrices we utilized the conventional Pearson’s correlation coefficient (CC) and Dynamic Time Warping (DTW) distance. DTW is an elastic matching algorithm that allows to capture the lags between two time series and has recently been used as a functional connectivity metric in several neuroimaging studies (Gokcay et al, 2019; Jin et al, 2020; Linke et al, 2020; Meszlényi et al, 2016; Meszlenyi, Buza, et al, 2017; Meszlenyi, Hermann, et al, 2017; Mohanty et al, 2020).…”