The amplitude of low-frequency fluctuation predicts levodopa treatment response in patients with Parkinson's disease

Houston, We Have AI Problem! Quality Issues with Neuroimaging-Based Artificial Intelligence in Parkinson's Disease: A Systematic Review

In recent years, many neuroimaging studies have applied artificial intelligence (AI) to facilitate existing challenges in Parkinson's disease (PD) diagnosis, prognosis, and intervention. The aim of this systematic review was to provide an overview of neuroimaging-based AI studies and to assess their methodological quality. A PubMed search yielded 810 studies, of which 244 that investigated the utility of neuroimaging-based AI for PD diagnosis, prognosis, or intervention were included. We systematically categorized studies by outcomes and rated them with respect to five minimal quality criteria (MQC) pertaining to data splitting, data leakage, model complexity, performance reporting, and indication of biological plausibility. We found that the majority of studies aimed to distinguish PD patients from healthy controls (54%) or atypical parkinsonian syndromes (25%), whereas prognostic or interventional studies were sparse. Only 20% of evaluated studies passed all five MQC, with data leakage, non-minimal model complexity, and reporting of biological plausibility as the primary factors for quality loss. Data leakage was associated with a significant inflation of accuracies. Very few studies employed external test sets (8%), where accuracy was significantly lower, and 19% of studies did not account for data imbalance. Adherence to MQC was low across all observed years and journal impact factors. This review outlines that AI has been applied to a wide variety of research questions pertaining to PD; however, the number of studies failing to pass the MQC is alarming. Therefore, we provide recommendations to enhance the interpretability, generalizability, and clinical utility of future AI applications using neuroimaging in PD. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Consistent abnormal activity in the putamen by dopamine modulation in Parkinson's disease: A resting-state neuroimaging meta-analysis

OBJECTIVE

This study aimed to elucidate brain areas mediated by oral anti-parkinsonian medicine that consistently show abnormal resting-state activation in PD and to reveal their functional connectivity profiles using meta-analytic approaches.

METHODS

Searches of the PubMed, Web of Science databases identified 78 neuroimaging studies including PD OFF state (PD-OFF) versus (vs.) PD ON state (PD-ON) or PD-ON versus healthy controls (HCs) or PD-OFF versus HCs data. Coordinate-based meta-analysis and functional meta-analytic connectivity modeling (MACM) were performed using the activation likelihood estimation algorithm.

RESULTS

Brain activation in PD-OFF vs. PD-ON was significantly changed in the right putamen and left inferior parietal lobule (IPL). Contrast analysis indicated that PD-OFF vs. HCs had more consistent activation in the right paracentral lobule, right middle frontal gyrus, right thalamus, left superior parietal lobule and right putamen, whereas PD-ON vs. HCs elicited more consistent activation in the bilateral middle temporal gyrus, left occipital gyrus, right inferior frontal gyrus and right caudate. MACM revealed coactivation of the right putamen in the direct contrast of PD-OFF vs. PD-ON. Subtraction analysis of significant coactivation clusters for PD-OFF vs. PD-ON with the medium of HCs showed effects in the sensorimotor, top-down control, and visual networks. By overlapping the MACM maps of the two analytical strategies, we demonstrated that the coactivated brain region focused on the right putamen.

CONCLUSIONS

The convergence of local brain regions and co-activation neural networks are involved the putamen, suggesting its potential as a specific imaging biomarker to monitor treatment efficacy.

SYSTEMATIC REVIEW REGISTRATION

[https://www.crd.york.ac.uk/PROSPERO/], identifier [CRD CRD42022304150].

Spontaneous brain activity in the hippocampal regions could characterize cognitive impairment in patients with Parkinson's disease

OBJECTIVE

This study aimed to investigate whether spontaneous brain activity can be used as a prospective indicator to identify cognitive impairment in patients with Parkinson's disease (PD).

METHODS

Resting-state functional magnetic resonance imaging (RS-fMRI) was performed on PD patients. The cognitive level of patients was assessed by the Montreal Cognitive Assessment (MoCA) scale. The fractional amplitude of low-frequency fluctuation (fALFF) was applied to measure the strength of spontaneous brain activity. Correlation analysis and between-group comparisons of fMRI data were conducted using Rest 1.8. By overlaying cognitively characterized brain regions and defining regions of interest (ROIs) based on their spatial distribution for subsequent cognitive stratification studies.

RESULTS

A total of 58 PD patients were enrolled in this study. They were divided into three groups: normal cognition (NC) group (27 patients, average MoCA was 27.96), mild cognitive impairment (MCI) group (21 patients, average MoCA was 23.52), and severe cognitive impairment (SCI) group (10 patients, average MoCA was 17.3). It is noteworthy to mention that those within the SCI group exhibited the most advanced chronological age, with an average of 74.4 years, whereas the MCI group displayed a higher prevalence of male participants at 85.7%. It was found hippocampal regions were a stable representative brain region of cognition according to the correlation analysis between the fALFF of the whole brain and cognition, and the comparison of fALFF between different cognitive groups. The parahippocampal gyrus was the only region with statistically significant differences in fALFF among the three cognitive groups, and it was also the only brain region to identify MCI from NC, with an AUC of 0.673. The paracentral lobule, postcentral gyrus was the region that identified SCI from NC, with an AUC of 0.941. The midbrain, hippocampus, and parahippocampa gyrus was the region that identified SCI from MCI, with an AUC of 0.926.

CONCLUSION

The parahippocampal gyrus was the potential brain region for recognizing cognitive impairment in PD, specifically for identifying MCI. Thus, the fALFF of parahippocampal gyrus is expected to contribute to future study as a multimodal fingerprint for early warning.

Subthalamic functional connectivity associated with freezing of gait dopa-response

INTRODUCTION

Freezing of gait (FOG) is a prevalent and debilitating feature of Parkinson's Disease (PD). The subthalamic nucleus (STN) is a center for controlled locomotion and a common DBS target. The objective of this study was to identify STN circuitry associated with FOG response to dopaminergic medication. In this study, we compare BOLD functional connectivity of the subthalamic nucleus (STN) in participants with and without dopa-responsive FOG.

METHODS

55 PD participants either with FOG (n = 38) or without FOG (n = 17) were recruited. Among FOG participants 22 were dopa-responsive and 16 were dopa-unresponsive. STN whole-brain connectivity was performed using CONN toolbox. The relationship between the degree of self-reported FOG dopa-response and STN connectivity was evaluated using partial correlations corrected for age, disease duration, and levodopa equivalent daily dose.

RESULTS

Right STN connectivity with the cerebellar locomotor region and the temporal/occipital cortex was greater in the dopa-responsive FOG group (voxel threshold p < 0.01, FWE corrected p < 0.05). Left STN connectivity with the occipital cortex was greater in the dopa-responsive FOG group and connectivity with the postcentral gyrus was greater in the dopa-unresponsive FOG group. Strength of connectivity to these regions correlated with l-dopa induced improvement in UPDRS Item-14 (FOG), but not UPDRS Part-III (overall motor score).

DISCUSSION

We demonstrate that dopa-unresponsive FOG is associated with changes in BOLD functional connectivity between the STN and locomotor as well as sensory processing regions. This finding supports the conceptual framework that effective treatment for freezing of gait likely requires the engagement of both locomotor and sensory brain regions.

Artificial intelligence-based model for dose prediction of sertraline in adolescents: a real-world study

BACKGROUND

Variability exists in sertraline pharmacokinetic parameters in individuals, especially obvious in adolescents. We aimed to establish an individualized dosing model of sertraline for adolescents with depression based on artificial intelligence (AI) techniques.

METHODS

Data were collected from 258 adolescent patients treated at the First Hospital of Hebei Medical University between December 2019 to July 2022. Nine different algorithms were used for modeling to compare the prediction abilities on sertraline daily dose, including XGBoost, LGBM, CatBoost, GBDT, SVM, ANN, TabNet, KNN, and DT. Performance of four dose subgroups (50 mg, 100 mg, 150 mg, and 200 mg) were analyzed.

RESULTS

CatBoost was chosen to establish the individualized medication model with the best performance. Six important variables were found to be correlated with sertraline dose, including plasma concentration, PLT, MPV, GL, A/G, and LDH. The ROC curve and confusion matrix exhibited the good prediction performance of CatBoost model in four dose subgroups (the AUC of 50 mg, 100 mg, 150 mg, and 200 mg were 0.93, 0.81, 0.93, and 0.93, respectively).

CONCLUSION

The AI-based dose prediction model of sertraline in adolescents with depression had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.

Neurovascular coupling dysfunction of visual network organization in Parkinson's disease

Parkinson's disease (PD) has been showed perfusion and neural activity alterations in specific regions, such as the motor and visual networks; however, the clinical significance of coupling changes is still unknown. To identify how neurovascular coupling changes during the pathophysiology of PD, patients and healthy controls underwent multiparametric magnetic resonance imaging to measure neural activity organization of segregation and integration using amplitude of low-frequency fluctuation (ALFF) and functional connectivity strength (FCS), and measure vascular responses using cerebral blood flow (CBF). Neurovascular coupling was calculated as the global CBF-ALFF and CBF-FCS coupling and the regional CBF/ALFF and CBF/FCS ratio. Correlations and dynamic causal modeling was then used to evaluate relationships with disease-alterations to clinical variables and information flow. Neurovascular coupling was impaired in PD with decreased global CBF-ALFF and CBF-FCS coupling, as well as decreased CBF/ALFF in the parieto-occipital cortex (dorsal visual stream) and CBF/FCS in the temporo-occipital cortex (ventral visual stream); these decouplings were associated with motor and non-motor impairments. The distinctive patterns of neurovascular coupling alterations within the dorsal and ventral visual streams of the visual system could potentially provide additional understanding into the pathophysiological mechanisms of PD.

Machine learning for detecting Wilson's disease by amplitude of low-frequency fluctuation

Wilson's disease (WD) is a genetic disorder with the A7P7B gene mutations. It is difficult to diagnose in clinic. The purpose of this study was to confirm whether amplitude of low-frequency fluctuations (ALFF) is one of the potential biomarkers for the diagnosis of WD. The study enrolled 30 healthy controls (HCs) and 37 WD patients (WDs) to obtain their resting-state functional magnetic resonance imaging (rs-fMRI) data. ALFF was obtained through preprocessing of the rs-fMRI data. To distinguish between patients with WDs and HCs, four clusters with abnormal ALFF-z values were identified through between-group comparisons. Based on these clusters, three machine learning models were developed, including Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR). Abnormal ALFF z-values were also combined with volume information, clinical variables, and imaging features to develop machine learning models. There were 4 clusters where the ALFF z-values of the WDs were significantly higher than that of the HCs. Cluster1 was in the cerebellar region, Cluster2 was in the left caudate nucleus, Cluster3 was in the bilateral thalamus, and Cluster4 was in the right caudate nucleus. In the training set and test set, the models trained with Cluster2, Cluster3, and Cluster4 achieved area of curve (AUC) greater than 0.80. In the Delong test, only the AUC values of models trained with Cluster4 exhibited statistical significance. The AUC values of the Logit model (P = 0.04) and RF model (P = 0.04) were significantly higher than those of the SVM model. In the test set, the LR model and RF model trained with Cluster3 had high specificity, sensitivity, and accuracy. By conducting the Delong test, we discovered that there was no statistically significant inter-group difference in AUC values between the model that integrates multi-modal information and the model before fusion. The LR models trained with multimodal information and Cluster 4, as well as the LR and RF models trained with multimodal information and Cluster 3, have demonstrated high accuracy, specificity, and sensitivity. Overall, these findings suggest that using ALFF based on the thalamus or caudate nucleus as markers can effectively differentiate between WDs and HCs. The fusion of multimodal information did not significantly improve the classification performance of the models before fusion.

The altered spontaneous neural activity in patients with Parkinson's disease and its predictive value for the motor improvement of deep brain stimulation

BACKGROUND

This study aims to investigate the altered spontaneous neural activity in patients with Parkinson's disease (PD) revealed by amplitudes of low-frequency fluctuations (ALFF) of resting-state fMRI, and the feasibility of using ALFF as neuroimaging predictors for motor improvement after bilateral subthalamic nucleus (STN) deep brain stimulation (DBS).

METHODS

Fourty-four patients and 44 healthy controls were included in this study. First, the ALFF of patients with PD was compared with that of controls; then significant clusters were correlated with motor improvement after DBS (unified Parkinson's disease rating scale (UPDRS-III)) and other clinical variables. Second, regression and classification of the machine learning models were conducted to predict motor improvement after DBS. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the classification model.

RESULTS

Compared with healthy controls, patients with PD showed increased ALFF in the bilateral motor area and decreased ALFF in the bilateral temporal cortex and cerebellum. The Hoehn-Yahr stages correlated with ALFF within the bilateral cerebellum (p = 0.021), and UPDRS-III improvement correlated with ALFF in the left (p < 0.001) and right (p = 0.005) motor areas. The regression model showed a significant correlation between the predicted and observed UPDRS-III changes (R = 0.65, p < 0.001). The ROC analysis revealed an area under the curve (AUC) of 0.94 which differentiated moderate and superior DBS responders.

CONCLUSION

The results revealed altered ALFF patterns in patients with PD and their correlations with clinical variables. Both binary and continuous ALFF can potentially serve as predictive biomarkers for DBS response.

Structural and functional abnormalities in Parkinson's disease based on voxel-based morphometry and resting-state functional magnetic resonance imaging

OBJECTIVE

To explore differences in gray matter volume (GMV) and white matter volume (WMV) between patients with Parkinson's disease (PD) and healthy controls, and to examine whether the structural abnormalities correlate with functional abnormalities.

METHODS

T1-weighted magnetic resonance imaging and resting-state functional magnetic resonance imaging (fMRI) were performed on 180 patients with PD and 58 age- and sex-matched healthy controls. We used voxel-based morphometry (VBM) to compare GMV and WMV between groups, and resting-state fMRI to compare amplitudes of low-frequency fluctuations (ALFF) in the structurally abnormal brain regions.

RESULTS

Structural neuroimaging showed smaller whole-brain GMV, but not WMV, in patients. Furthermore, VBM revealed smaller GMV in the right superior temporal gyrus (STG) and left frontotemporal space in patients, after correction for multiple comparisons. Patients also showed significantly higher ALFF in the right STG. GMV in the right STG and left frontotemporal space in patients correlated negatively with age and scores on Part III of the Movement Disorder Society Unified Parkinson's Disease Rating Scale, but not with PD duration.

CONCLUSIONS

Structural atrophy in the frontotemporal lobe may be a useful imaging biomarker in PD, such as for detecting disease progression. Furthermore, this structural atrophy appears to correlate with enhanced spontaneous brain activity. This study associates particular structural and functional abnormalities with PD neuropathology.

Whole-brain metabolic pattern analysis in patients with anti-LGI1 encephalitis

BACKGROUND AND PURPOSE

Faciobrachial dystonic seizures (FBDS) and hyponatraemia are the distinct clinical features of autoimmune encephalitis (AE) caused by antibodies against leucine-rich glioma-inactivated 1 (LGI1). The pathophysiological pattern and neural mechanisms underlying these symptoms remain largely unexplored.

METHODS

We included 30 patients with anti-LGI1 AE and 30 controls from a retrospective observational cohort. Whole-brain metabolic pattern analysis was performed to assess the pathological network of anti-LGI1 AE, as well as the symptomatic networks of FBDS. Logistic regression was applied to explore independent predictors of FBDS. Finally, we applied multiple regression model to investigate the hyponatraemia-associated brain network and its effect on serum sodium levels.

RESULTS

The pathological network of anti-LGI1 AE involved a hypermetabolism in cerebellum, subcortical structures, and Rolandic area, as well as a hypometabolism in the medial prefrontal cortex. The symptomatic network of FBDS shown a hypometabolism in cerebellum and Rolandic area (P_FDR < 0.05). Hypometabolism in the cerebellum was an independent predictor of FBDS (P < 0.001). Hyponatraemia-associated network highlighted a negative effect on caudate nucleus, frontal and temporal white matter. Serum sodium level had the negative trend with metabolism of hypothalamus (Pearson's R = -0.180, P = 0.342) but the mediation was not detected (path c' = -7.238, 95% CI = -30.947 to 16.472).

CONCLUSIONS

Our results provide insights into the whole-brain metabolic patterns of patients with anti-LGI1 AE, including the symptomatic network FBDS and the hyponatraemia-associated brain network, which is conducive to understanding the neural mechanisms and evaluating disease progress of anti-LGI1 AE.