The role of AI and machine learning in the diagnosis of Parkinson's disease and atypical parkinsonisms.

Parkinson's disease is a neurodegenerative movement disorder associated with motor and non-motor symptoms causing severe disability as the disease progresses. The development of biomarkers for Parkinson's disease to diagnose patients earlier and predict disease progression is imperative. As artificial intelligence and machine learning techniques efficiently process data and can handle multiple data types, we reviewed the literature to determine the extent to which these techniques have been applied to biomarkers for Parkinson's disease and movement disorders. We determined that the most applicable machine learning techniques are support vector machines and neural networks, depending on the size and type of the data being analyzed. Additionally, more complex machine learning techniques showed increased accuracy when compared to less complex techniques, especially when multiple machine learning models were combined. We can conclude that artificial intelligence and machine learning techniques may have the capacity to significantly boost diagnostic capacity in movement disorders and Parkinson's disease.

Multiple system atrophy with amyloid-ß-predominant Alzheimer's disease neuropathologic change.

Multiple system atrophy is a neurodegenerative disease with α-synuclein pathology predominating in the striatonigral and olivopontocerebellar systems. Mixed pathologies are considered to be of low frequency and mostly comprise primary age-related tauopathy or low levels of Alzheimer's disease-related neuropathologic change. Therefore, the concomitant presence of different misfolded proteins in the same brain region is less likely in multiple system atrophy. During the neuropathological evaluation of 21 consecutive multiple system atrophy cases, we identified four cases exhibiting an unusual discrepancy between high Thal amyloid-ß phase and low transentorhinal Braak neurofibrillary tangle stage. We mapped α-synuclein pathology, measured the size and number of glial cytoplasmic inclusions and compared the amyloid-ß peptides between multiple system atrophy and Alzheimer's disease. In addition, we performed α-synuclein seeding assay from the affected putamen samples. We performed genetic testing for APOE, MAPT, PSEN1, PSEN2 and APP. We refer to the four multiple system atrophy cases with discrepancy between amyloid-ß and tau pathology as 'amyloid-ß-predominant Alzheimer's disease neuropathologic change-multiple system atrophy' to distinguish these from multiple system atrophy with primary age-related tauopathy or multiple system atrophy with typical Alzheimer's disease neuropathologic change. As most multiple system atrophy cases with mixed pathologies reported in the literature, these cases did not show a peculiar clinical or MRI profile. Three amyloid-ß-predominant Alzheimer's disease neuropathologic change-multiple system atrophy cases were available for genetic testing, and all carried the APOE ɛ4 allele. The extent and severity of neuronal loss and α-synuclein pathology were not different compared with typical multiple system atrophy cases. Analysis of amyloid-ß peptides revealed more premature amyloid-ß plaques in amyloid-ß-predominant Alzheimer's disease neuropathologic change-multiple system atrophy compared with Alzheimer's disease. α-Synuclein seeding amplification assay showed differences in the kinetics in two cases. This study highlights a rare mixed pathology variant of multiple system atrophy in which there is an anatomical meeting point of amyloid-ß and α-synuclein, i.e. the striatum or cerebellum. Since biomarkers are entering clinical practice, these cases will be recognized, and the clinicians have to be informed that the prognosis is not necessarily different than in pure multiple system atrophy cases but that the effect of potential α-synuclein-based therapies might be influenced by the co-presence of amyloid-ß in regions where α-synuclein also aggregates. We propose that mixed pathologies should be interpreted not only based on differences in the clinical phenotype but also on whether protein depositions regionally overlap, potentially leading to a different response to α-synuclein-targeted therapies.

Longitudinal cerebral perfusion in presymptomatic genetic frontotemporal dementia: GENFI results.

INTRODUCTION: Effective longitudinal biomarkers that track disease progression are needed to characterize the presymptomatic phase of genetic frontotemporal dementia (FTD). We investigate the utility of cerebral perfusion as one such biomarker in presymptomatic FTD mutation carriers. METHODS: We investigated longitudinal profiles of cerebral perfusion using arterial spin labeling magnetic resonance imaging in 42 C9orf72, 70 GRN, and 31 MAPT presymptomatic carriers and 158 non-carrier controls. Linear mixed effects models assessed perfusion up to 5 years after baseline assessment. RESULTS: Perfusion decline was evident in all three presymptomatic groups in global gray matter. Each group also featured its own regional pattern of hypoperfusion over time, with the left thalamus common to all groups. Frontal lobe regions featured lower perfusion in those who symptomatically converted versus asymptomatic carriers past their expected age of disease onset. DISCUSSION: Cerebral perfusion is a potential biomarker for assessing genetic FTD and its genetic subgroups prior to symptom onset. HIGHLIGHTS: Gray matter perfusion declines in at-risk genetic frontotemporal dementia (FTD). Regional perfusion decline differs between at-risk genetic FTD subgroups . Hypoperfusion in the left thalamus is common across all presymptomatic groups. Converters exhibit greater right frontal hypoperfusion than non-converters past their expected conversion date. Cerebral hypoperfusion is a potential early biomarker of genetic FTD.

A multi-site study on sex differences in cortical thickness in non-demented Parkinson's disease.

Clinical, cognitive, and atrophy characteristics depending on sex have been previously reported in Parkinson's disease (PD). However, though sex differences in cortical gray matter measures in early drug naïve patients have been described, little is known about differences in cortical thickness (CTh) as the disease advances. Our multi-site sample comprised 211 non-demented PD patients (64.45% males; mean age 65.58 ± 8.44 years old; mean disease duration 6.42 ± 5.11 years) and 86 healthy controls (50% males; mean age 65.49 ± 9.33 years old) with available T1-weighted 3 T MRI data from four international research centers. Sex differences in regional mean CTh estimations were analyzed using generalized linear models. The relation of CTh in regions showing sex differences with age, disease duration, and age of onset was examined through multiple linear regression. PD males showed thinner cortex than PD females in six frontal (bilateral caudal middle frontal, bilateral superior frontal, left precentral and right pars orbitalis), three parietal (bilateral inferior parietal and left supramarginal), and one limbic region (right posterior cingulate). In PD males, lower CTh values in nine out of ten regions were associated with longer disease duration and older age, whereas in PD females, lower CTh was associated with older age but with longer disease duration only in one region. Overall, male patients show a more widespread pattern of reduced CTh compared with female patients. Disease duration seems more relevant to explain reduced CTh in male patients, suggesting worse prognostic over time. Further studies should explore sex-specific cortical atrophy trajectories using large longitudinal multi-site data.