Brain Dynamics Complexity as a Signature of Cognitive Decline in Parkinson's Disease

Abstract

BackgroundHiguchi's fractal dimension (FD) captures brain dynamics complexity and may be a promising method to analyze resting‐state functional magnetic resonance imaging (fMRI) data and detect the neuronal interaction complexity underlying Parkinson's disease (PD) cognitive decline.ObjectivesThe aim was to compare FD with a more established index of spontaneous neural activity, the fractional amplitude of low‐frequency fluctuations (fALFF), and identify through machine learning (ML) models which method could best distinguish across PD‐cognitive states, ranging from normal cognition (PD‐NC), mild cognitive impairment (PD‐MCI) to dementia (PDD). Finally, the aim was to explore correlations between fALFF and FD with clinical and cognitive PD features.MethodsAmong 118 PD patients age‐, sex‐, and education matched with 35 healthy controls, 52 were classified with PD‐NC, 46 with PD‐MCI, and 20 with PDD based on an extensive cognitive and clinical evaluation. fALFF and FD metrics were computed on rs‐fMRI data and used to train ML models.ResultsFD outperformed fALFF metrics in differentiating between PD‐cognitive states, reaching an overall accuracy of 78% (vs. 62%). PD showed increased neuronal dynamics complexity within the sensorimotor network, central executive network (CEN), and default mode network (DMN), paralleled by a reduction in spontaneous neuronal activity within the CEN and DMN, whose increased complexity was strongly linked to the presence of dementia. Further, we found that some DMN critical hubs correlated with worse cognitive performance and disease severity.ConclusionsOur study indicates that PD‐cognitive decline is characterized by an altered spontaneous neuronal activity and increased temporal complexity, involving the CEN and DMN, possibly reflecting an increased segregation of these networks. Therefore, we propose FD as a prognostic biomarker of PD‐cognitive decline. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson’s Disease: A systematic review

“…A number of study activities were utilised including diagnosis, (PD vs Healthy Controls (HC), PDD vs HC, PD-NC vs PD-MCI, PD-MCI vs PDD), differential diagnosis (PD-CI/PD-MCI/PDD vs AD vs DLB), identification of biomarkers for PD detection, and the prediction of future CI states. Most studies focused on diagnostic activities (n = 48) [ 21 – 26 , 28 , 30 , 31 , 84 , 113 , 114 , 116 – 119 , 121 , 122 , 124 – 126 , 128 , 130 , 133 – 136 , 138 , 142 , 144 – 146 , 148 – 151 , 153 – 155 , 157 – 161 , 164 , 166 , 171 , 172 ], followed by prediction (n = 12) [ 29 , 129 , 131 , 132 , 137 , 140 , 141 , 152 , 156 , 162 , 163 , 170 ], biomarker identification (n = 6) [ 27 , 120 , 123 , 143 , 147 , 169 ], and differential diagnosis (n = 4) [...…”

“…The most commonly used data modalities were imaging (n = 33) [ 24 , 27 – 31 , 113 , 114 , 117 , 119 , 122 , 129 , 130 , 133 , 137 , 139 – 143 , 147 – 152 , 155 , 156 , 159 – 161 , 163 , 164 ], clinical characteristics (n = 17) [ 84 , 118 , 131 , 132 , 137 , 140 , 152 , 153 , 155 , 156 , 159 , 160 , 162 – 164 , 169 , 170 ], EEG (n = 11) [ 25 , 26 , 120 , 125 – 128 , 135 , 136 , 146 , 151 ], and neuropsychological profile (n = 10) [ 115 , 118 , 132 , 134 , 142 , 157 , 158 …”

“…ML techniques used across all reviewed studies were categorised into 12 categories, some of which overlap: (1) tree based methods (n = 32) [ 22 , 23 , 26 , 27 , 31 , 114 , 116 , 119 , 122 , 125 , 126 , 128 – 130 , 132 , 134 , 137 , 139 , 141 , 145 , 153 , 155 , 157 – 159 , 162 , 164 , 166 , 167 , 170 – 172 ], (2) Support Vector Machines (n = 30) [ 21 , 23 – 25 , 27 , 28 , 30 , 113 , 115 , 117 , 118 , 122 – 124 , 133 , 134 , 138 , 139 , 141 , 142 , 148 – 151 , 153 , 156 – 159 , 161 , …”

“…44 of the 58 supervised learning studies focused on classification activities, 40 of which focused on classification vs NC/HC [ 22 – 26 , 28 , 30 , 31 , 84 , 113 , 114 , 116 , 117 , 119 , 122 , 124 – 126 , 128 , 130 , 133 , 134 , 138 , 142 , 145 , 146 , 148 – 151 , 153 – 155 , 158 , 159 , 161 , 164 , 166 , 171 , 172 ], and four classifying against memory disorders [ 115 , 127 , 139 , 167 ]. 11 studies focused on prediction [ 129 , 131 , 132 , 137 , 140 , 141 , 152 , 156 , 162 , 163 , 170 ], and the remaining three on biomarker identification [ 27 , 123 , 169 ].…”

“…11 studies focused on prediction [ 129 , 131 , 132 , 137 , 140 , 141 , 152 , 156 , 162 , 163 , 170 ], and the remaining three on biomarker identification [ 27 , 123 , 169 ]. Regarding modalities, 23 studies used a combination of modalities, with the remaining 35 using only one, with the most commonly used modalities being imaging (n = 29) [ 24 , 27 , 28 , 30 , 31 , 113 , 114 , 117 , 119 , 122 , 129 , 130 , 133 , 137 , 139 – 142 , 148 – 152 , 155 , 156 , 159 , 161 , 163 , 164 ], clinical characteristics (n = 15) [ 84 , 131 , 132 , 137 , 140 , 152 , 153 , 155 , 156 , 159 , 162 – 164 , 169 ,…”