Disrupted Resting-state Functional Connectivity of the Nucleus Basalis of Meynert in Parkinson’s Disease with Mild Cognitive Impairment

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

BACKGROUND

Parkinson's Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes.

METHODS

To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson's Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted.

RESULTS

Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson's Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson's Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy.

CONCLUSIONS

Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment assessment, providing clear and formidable potential for implementation of machine learning into clinical practice.

Interactions between functional networks in Parkinson's disease mild cognitive impairment

The study of mild cognitive impairment (MCI) is critical to understand the underlying processes of cognitive decline in Parkinson's disease (PD). Functional connectivity (FC) disruptions in PD-MCI patients have been observed in several networks. However, the functional and cognitive changes associated with the disruptions observed in these networks are still unclear. Using a data-driven methodology based on independent component analysis, we examined differences in FC RSNs among PD-MCI, PD cognitively normal patients (PD-CN) and healthy controls (HC) and studied their associations with cognitive and motor variables. A significant difference was found between PD-MCI vs PD-CN and HC in a FC-trait comprising sensorimotor (SMN), dorsal attention (DAN), ventral attention (VAN) and frontoparietal (FPN) networks. This FC-trait was associated with working memory, memory and the UPDRS motor scale. SMN involvement in verbal memory recall may be related with the FC-trait correlation with memory deficits. Meanwhile, working memory impairment may be reflected in the DAN, VAN and FPN interconnectivity disruptions with the SMN. Furthermore, interactions between the SMN and the DAN, VAN and FPN network reflect the intertwined decline of motor and cognitive abilities in PD-MCI. Our findings suggest that the memory impairments observed in PD-MCI are associated with reduced FC within the SMN and between SMN and attention networks.

Visualizing risky situations induces a stronger neural response in brain areas associated with mental imagery and emotions than visualizing non-risky situations

In an fMRI study, we tested the prediction that visualizing risky situations induces a stronger neural response in brain areas associated with mental imagery and emotions than visualizing non-risky and more positive situations. We assumed that processing mental images that allow for "trying-out" the future has greater adaptive importance for risky than non-risky situations, because the former can generate severe negative outcomes. We identified several brain regions that were activated when participants produced images of risky situations and these regions overlap with brain areas engaged in visual, speech, and movement imagery. We also found that producing images of risky situations, in contrast to non-risky situations, was associated with increased neural activation in the insular cortex and cerebellum-the regions involved, among other functions, in emotional processing. Finally, we observed an increased BOLD signal in the cingulate gyrus associated with reward-based decision making and monitoring of decision outcomes. In summary, risky situations increased neural activation in brain areas involved in mental imagery, emotional processing, and decision making. These findings imply that the evaluation of everyday risky situations may be driven by emotional responses that result from mental imagery.

Identification of chronic mild traumatic brain injury using resting state functional MRI and machine learning techniques

Mild traumatic brain injury (mTBI) is a major public health concern that can result in a broad spectrum of short-term and long-term symptoms. Recently, machine learning (ML) algorithms have been used in neuroscience research for diagnostics and prognostic assessment of brain disorders. The present study aimed to develop an automatic classifier to distinguish patients suffering from chronic mTBI from healthy controls (HCs) utilizing multilevel metrics of resting-state functional magnetic resonance imaging (rs-fMRI). Sixty mTBI patients and forty HCs were enrolled and allocated to training and testing datasets with a ratio of 80:20. Several rs-fMRI metrics including fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), degree centrality (DC), voxel-mirrored homotopic connectivity (VMHC), functional connectivity strength (FCS), and seed-based FC were generated from two main analytical categories: local measures and network measures. Statistical two-sample t-test was employed comparing between mTBI and HCs groups. Then, for each rs-fMRI metric the features were selected extracting the mean values from the clusters showing significant differences. Finally, the support vector machine (SVM) models based on separate and multilevel metrics were built and the performance of the classifiers were assessed using five-fold cross-validation and via the area under the receiver operating characteristic curve (AUC). Feature importance was estimated using Shapley additive explanation (SHAP) values. Among local measures, the range of AUC was 86.67-100% and the optimal SVM model was obtained based on combined multilevel rs-fMRI metrics and DC as a separate model with AUC of 100%. Among network measures, the range of AUC was 80.42-93.33% and the optimal SVM model was obtained based on the combined multilevel seed-based FC metrics. The SHAP analysis revealed the DC value in the left postcentral and seed-based FC value between the motor ventral network and right superior temporal as the most important local and network features with the greatest contribution to the classification models. Our findings demonstrated that different rs-fMRI metrics can provide complementary information for classifying patients suffering from chronic mTBI. Moreover, we showed that ML approach is a promising tool for detecting patients with mTBI and might serve as potential imaging biomarker to identify patients at individual level.

Clinical trial registration

[clinicaltrials.gov], identifier [NCT03241732].

Topological patterns of motor networks in Parkinson’s disease with different sides of onset: A resting-state-informed structural connectome study

Parkinson’s disease (PD) has a characteristically unilateral pattern of symptoms at onset and in the early stages; this lateralization is considered a diagnostically important diagnosis feature. We aimed to compare the graph-theoretical properties of whole-brain networks generated by using resting-state functional MRI (rs-fMRI), diffusion tensor imaging (DTI), and the resting-state-informed structural connectome (rsSC) in patients with left-onset PD (LPD), right-onset PD (RPD), and healthy controls (HCs). We recruited 26 patients with PD (13 with LPD and 13 with RPD) as well as 13 age- and sex-matched HCs. Rs-fMRI and DTI were performed in all subjects. Graph-theoretical analysis was used to calculate the local and global efficiency of a whole-brain network generated by rs-fMRI, DTI, and rsSC. Two-sample t-tests and Pearson correlation analysis were conducted. Significantly decreased global and local efficiency were revealed specifically in LPD patients compared with HCs when the rsSC network was used; no significant intergroup difference was found by using rs-fMRI or DTI alone. For rsSC network analysis, multiple network metrics were found to be abnormal in LPD. The degree centrality of the left precuneus was significantly correlated with the Unified Parkinson’s Disease Rating Scale (UPDRS) score and disease duration (p = 0.030, r = 0.599; p = 0.037, r = 0.582). The topological properties of motor-related brain networks can differentiate LPD and RPD. Nodal metrics may serve as important structural features for PD diagnosis and monitoring of disease progression. Collectively, these findings may provide neurobiological insights into the lateralization of PD onset.

Imaging the Limbic System in Parkinson's Disease-A Review of Limbic Pathology and Clinical Symptoms

The limbic system describes a complex of brain structures central for memory, learning, as well as goal directed and emotional behavior. In addition to pathological studies, recent findings using in vivo structural and functional imaging of the brain pinpoint the vulnerability of limbic structures to neurodegeneration in Parkinson's disease (PD) throughout the disease course. Accordingly, dysfunction of the limbic system is critically related to the symptom complex which characterizes PD, including neuropsychiatric, vegetative, and motor symptoms, and their heterogeneity in patients with PD. The aim of this systematic review was to put the spotlight on neuroimaging of the limbic system in PD and to give an overview of the most important structures affected by the disease, their function, disease related alterations, and corresponding clinical manifestations. PubMed was searched in order to identify the most recent studies that investigate the limbic system in PD with the help of neuroimaging methods. First, PD related neuropathological changes and corresponding clinical symptoms of each limbic system region are reviewed, and, finally, a network integration of the limbic system within the complex of PD pathology is discussed.

Relationship between plasma clozapine/N-desmethylclozapine and changes in basal forebrain-dorsolateral prefrontal cortex coupling in treatment-resistant schizophrenia

Clozapine (CLZ) demonstrates a unique clinical efficacy relative to other antipsychotic drugs. Previous work has linked the plasma ratio of CLZ and its major metabolite, N-desmethylclozapine (NDMC), to an inverse relationship with cognition via putative action on the cholinergic system. However, neuroimaging correlates of CLZ/NDMC remain unknown. Here, we examined changes in basal forebrain functional connectivity with the dorsolateral prefrontal cortex, and secondly, cognition in relation to the CLZ/NDMC ratio. A cohort of nineteen chronically ill participants with treatment-resistant schizophrenia (TRS) undergoing 12 weeks of CLZ treatment were included. Measures of cognition and plasma CLZ/NDMC ratios were obtained in addition to resting-state functional neuroimaging scans, captured at baseline and after 12 weeks of CLZ treatment. We observed a significant correlation between basal forebrain-DLPFC connectivity and CLZ/NDMC ratios across CLZ treatment (p = 0.02). Consistent with previous findings, we also demonstrate a positive relationship between CLZ/NDMC ratio and working memory (p = 0.03). These findings may reflect the action of CLZ and NDMC on the muscarinic cholinergic system, highlighting a possible neural correlate of cognition across treatment.

Discriminating subclinical depression from major depression using multi-scale brain functional features: A radiomics analysis

BACKGROUND

The diagnosis of subclinical depression (SD) currently relies exclusively on subjective clinical scores and structured interviews, which shares great similarities with major depression (MD) and increases the risk of misdiagnosis of SD and MD. This study aimed to develop a method of disease classification for SD and MD by resting-state functional features using radiomics strategy.

METHODS

Twenty-six SD, 36 MD subjects and 33 well-matched healthy controls (HC) were recruited and underwent resting-state functional magnetic resonance imaging (rs-fMRI). A novel radiomics analysis was proposed to discriminate SD from MD. Multi-scale brain functional features were extracted to explore a comprehensive representation of functional characteristics. A two-level feature selection strategy and support vector machine (SVM) were employed for classification.

RESULTS

The overall classification accuracy among SD, MD and HC groups was 84.21%. Particularly, the model excellently distinguished SD from MD with 96.77% accuracy, 100% sensitivity, and 92.31% specificity. Moreover, features with high discriminative power to distinguish SD from MD showed a strong association with default mode network, frontoparietal network, affective network, and visual network regions.

LIMITATION

The sample size was relatively small, which may limit the application in clinical translation to some extent.

CONCLUSION

These findings demonstrated that a valid radiomics approach based on functional measures can discriminate SD from MD with a high classification performance, facilitating an objective and reliable diagnosis individually in clinical practice. Features with high discriminative power may provide insight into a profound understanding of the brain functional impairments and pathophysiology of SD and MD.

Distinct alterations of functional connectivity of the basal forebrain subregions in insomnia disorder

BACKGROUND

Cholinergic basal forebrain (BF) plays an important role in sleep-wake regulation and is implicated in cortical arousal and activation. However, less is known currently regarding the abnormal BF-related neuronal circuit in human patients with insomnia disorder (ID). In this study, we aimed to explore alterations of functional connectivity (FC) in subregions of the BF and the relationships between FC alterations and sleep and mood measures in ID.

MATERIALS AND METHODS

One hundred and two ID patients and ninety-six healthy controls (HC) were included in this study. Each subject underwent both resting-state fMRI and high-resolution anatomical scanning. All participants completed the sleep and mood questionnaires in ID patients. Voxel-based resting-state FC in each BF subregion (Ch_123 and Ch_4) were computed. For the voxel-wise FC differences between groups, a two-sample t-test was performed on the individual maps in a voxel-by-voxel manner. To examine linear relationships with sleep and mood measures, Pearson correlations were calculated between FC alterations and sleep and mood measures, respectively.

RESULTS

The ID group showed significantly decreased FC between the medial superior frontal gyrus and Ch_123 compared to HC. However, increased FC between the midbrain and Ch_4 was found in ID based on the voxel-wise analysis. The correlation analysis only revealed that the altered FC between the midbrain with Ch_4 was significantly negatively correlated with the self-rating anxiety scale.

CONCLUSION

Our findings of decreased FC between Ch_123 and medial superior frontal gyrus and increased FC between midbrain and Ch4 suggest distinct roles of subregions of BF underlying the neurobiology of ID.

Disrupted Functional Connectivity Within and Between Resting-State Networks in the Subacute Stage of Post-stroke Aphasia

Background: Post-stroke aphasia (PSA) results from brain network disorders caused by focal stroke lesions. However, it still remains largely unclear whether the impairment is present in intra- and internetwork functional connectivity (FC) within each resting-state network (RSN) and between RSNs in the subacute stage of PSA.

Objectives: This study aimed to investigate the resting-state FC within and between RSNs in patients with PSA and observe the relationships between FC alterations and Western Aphasia Battery (WAB) measures.

Methods: A total of 20 individuals with subacute PSA and 20 healthy controls (HCs) were recruited for functional MRI (fMRI) scanning, and only patients with PSA underwent WAB assessment. Independent component analysis was carried out to identify RSNs. Two-sample t-tests were used to calculate intra- and internetwork FC differences between patients with PSA and HCs. The results were corrected for multiple comparisons using the false discovery rate (FDR correction, p < 0.05). Partial correlation analysis was performed to observe the relationship between FC and WAB scores with age, gender, mean framewise displacement, and lesion volume as covariates (p < 0.05).

Results: Compared to HCs, patients with PSA showed a significant increase in intranetwork FC in the salience network (SN). For internetwork FC analysis, patients showed a significantly increased coupling between left frontoparietal network (lFPN) and SN and decreased coupling between lFPN and right frontoparietal network (rFPN) as well as between lFPN and posterior default mode network (pDMN) (FDR correction, p < 0.05). Finally, a significant positive correlation was found between the intergroup difference of FC (lFPN-rFPN) and auditory-verbal comprehension (p < 0.05).

Conclusion: Altered FC was revealed within and between multiple RSNs in patients with PSA at the subacute stage. Reduced FC between lFPN and rFPN was the key element participating in language destruction. These findings proved that PSA is a brain network disorder caused by focal lesions; besides, it may improve our understanding of the pathophysiological mechanisms of patients with PSA at the subacute stage.

Altered functional connectivity between the nucleus basalis of Meynert and anterior cingulate cortex is associated with declined attentional performance after total sleep deprivation

BACKGROUND

Sleep deprivation can markedly influence vigilant attention. The nucleus basalis of Meynert (NBM), the main source of cholinergic projections to the cortex, plays an important role in wakefulness maintenance and attention control. However, the involvement of NBM in attentional impairments after total sleep deprivation (TSD) has yet to be established. The purpose of this study is to investigate the alterations in NBM functional connectivity and its association with the attentional performance following TSD.

METHODS

Thirty healthy adult males were recruited in the study. Participants underwent two resting-state functional magnetic resonance imaging (rs-fMRI) scans, once in rested wakefulness (RW) and once after 36 h of TSD. Seed-based functional connectivity analysis was performed using rs-fMRI data for the left and right NBM. The vigilant attention was measured using a psychomotor vigilance test (PVT). Furthermore, Pearson correlation analysis was conducted to investigate the relationship between altered NBM functional connectivity and changed PVT performance after TSD.

RESULTS

Compared to RW, enhanced functional connectivity was observed between right NBM and bilateral thalamus and cingulate cortex, while reduced functional connectivity was observed between left NBM and right superior parietal lobule following TSD. Moreover, altered NBM functional connectivity with the left anterior cingulate cortex was negatively correlated with PVT performance after TSD.

CONCLUSION

Our results suggest that the disrupted NBM-related cholinergic circuit highlights an important role in attentional performance after TSD. The enhanced NBM functional connectivity with the anterior cingulate cortex may act as neural signatures for attentional deficits induced by sleep deprivation.

Association Between REM Sleep Behavior Disorder and Cognitive Dysfunctions in Parkinson's Disease: A Systematic Review and Meta-Analysis of Observational Studies

Background: Rapid eye movement sleep behavior disorder (RBD) is thought to be a prodromal symptom of Parkinson's disease (PD). RBD is also thought to be involved in cognitive decline and dementia in PD. In PD, although the relationship between RBD and cognitive dysfunctions was confirmed by considerable studies, whether RBD was associated with distinct types of cognitive defects is worth of study. Objectives: This systematic review summarizes the evidence relating to cognitive dysfunction in PD patients with RBD (PD-RBD) and those without and explores their specificity to cognitive domains. Methods: A meta-analysis using a random-effects model was performed for 16 different cognitive domains, including global cognitive function, memory (long-term verbal recall, long-term verbal recognition, long-term visual recall, short-term spatial recall, and short-term verbal recall), executive function (general, fluid reasoning, generativity, shifting, inhibition, and updating), language, processing speed/complex attention/working memory, visuospatial/constructional ability, and psychomotor ability. The cognitive difference between the groups of patients was measured as a standardized mean difference (SMD, Cohen's d). PD-RBD patients were classified into Confirmed-RBD (definite diagnosis with polysomnography, PSG) and Probable-RBD (without PSG re-confirmation). In some domains, RBD patients could not be analyzed separately due to the exiguity of primary studies; this analysis refers to such RBD patients as "Mixed-RBD." Results: Thirty-nine studies with 6,695 PD subjects were finally included. Confirmed-RBD patients showed worse performance than those without in global cognitive function, long-term verbal recall, long-term verbal recognition, generativity, inhibition, shifting, language, and visuospatial/constructional ability; Probable-RBD, in global cognitive function and shifting; and Mixed-RBD, in long-term visual recall, short-term spatial recall, general executive function, and processing speed/complex attention/working memory. Conclusion: This meta-analysis strongly suggests a relationship between RBD, Confirmed-RBD in particular, and cognitive dysfunctions in PD patients. Early and routine screening by sensitive and targeted cognitive tasks is necessary for all PD-RBD patients because it may offer the therapeutic time window before they evolve to irreversible dementia.