Background: Machine learning (ML) is a promising technique for patient-specific prediction of mild cognitive impairment (MCI) and dementia development. Neuropsychiatric symptoms (NPS) might improve the accuracy of ML models but have barely been used for this purpose. Objectives: To investigate if baseline mild behavioral impairment (MBI) status used for NPS quantification along with brain morphology features are predictive of follow-up diagnosis, median 40 months later in patients with normal cognition (NC) or MCI. Method: Baseline neuroimaging, neuropsychiatric, and clinical data from 102 individuals with NC and 239 with MCI were extracted from the Alzheimer's Disease Neuroimaging Initiative database. Neuropsychiatric inventory questionnaire items were transformed to MBI domains using a published algorithm. Diagnosis at latest follow-up was used as the outcome variable and ground truth classification. A logistic model tree classifier combined with information gain feature selection was trained to predict follow-up diagnosis. Results: In the binary classification (NC versus MCI/AD), the optimal ML model required only two features from over 200, MBI total score and left hippocampal volume. These features correctly classified participants as remaining normal or developing cognitive impairment with 84.4% accuracy (area under the receiver operating characteristics curve [ROC-AUC] = 0.86). Seven features were selected for the three-class model (NC versus MCI versus dementia) achieving an accuracy of 58.8% (ROC-AUC=0.73).

Background: Agitation and aggression are common in dementia and pre-dementia. The dementia risk syndrome mild behavioral impairment (MBI) includes these symptoms in the impulse dyscontrol domain. However, the neural circuitry associated with impulse dyscontrol in neurodegenerative disease is not well understood. The aim of this work is to investigate if regional micro-and macro-structural brain properties are associated with impulse dyscontrol symptoms in older adults with normal cognition, mild cognitive impairment, and Alzheimer's disease.Methods: Clinical, neuropsychiatric, and T1-weighted and diffusion-tensor MRI (DTI) data from 80 individuals with and 123 individuals without impulse dyscontrol, were obtained from the Alzheimer's Disease Neuroimaging Initiative. Linear mixed effect (LME) models were used to assess if impulse dyscontrol was related to regional DTI and volumetric parameters.Results: Impulse dyscontrol was present in 17% of participants with NC, 43% with MCI, and 66% with AD. Impulse dyscontrol was associated with: 1) lower fractional anisotropy, and greater mean, axial, and radial diffusivity in the fornix; 2) lesser fractional anisotropy, and greater radial diffusivity in the superior fronto-occipital fasciculus; 3) greater axial diffusivity in the cingulum; 4) grey matter atrophy, speci cally, lower cortical thickness and greater surface area in the parahippocampal gyrus. Conclusion:Our ndings provide evidence that well-established atrophy patterns of AD are prominent in the presence of impulse dyscontrol, even when disease status is controlled for, and possibly in advance of dementia. Our ndings support the growing evidence base for impulse dyscontrol symptoms as an early manifestation of Alzheimer's disease. BackgroundAgitation, aggression, and impulsivity are common in dementia and are associated with caregiver stress and poorer outcomes (1, 2). These symptoms are clinically meaningful, often requiring intervention -both non-pharmacological and pharmacological (3). Agitation in individuals with neurocognitive disorders is associated with emotional distress and symptoms of excessive motor activity, verbal aggression, or physical aggression (4). In a recent systematic review, the prevalence of agitation/aggression in patients with Alzheimer's disease (AD) was estimated to be 40% (5). Agitation can also present in advance of dementia in those with mild cognitive impairment (MCI), subjective cognitive decline (SCD), or even normal cognition (6-9). In the population-based Mayo Clinic Study of Aging, which enrolled participants ≥ 70 years of age, prevalence of irritability was 7.6% in normal cognition (NC) and 19.4% in MCI, while prevalence of agitation was 2.8% in NC and 9.1% in MCI (5). Importantly, in a subsequent analysis, these same impulse dyscontrol symptoms when present at study baseline predicted incident MCI. Hazard ratio for incident MCI with baseline irritability was 1.84 and for agitation hazard was 3.06 relative to the absence of symptoms (10). Thus, neuropsychiatric symptoms in ol...

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

Magnetic resonance angiography (MRA) can capture the variation of cerebral arteries with high spatial resolution. These measurements include valuable information about the morphology, geometry, and density of brain arteries, which may be useful to identify risk factors for cerebrovascular and neurological diseases at an early time point. However, this requires knowledge about the distribution and morphology of vessels in healthy subjects. The statistical arterial brain atlas described in this work is a free and public neuroimaging resource that can be used to identify vascular morphological changes. The atlas was generated based on 544 freely available multi-center MRA and T1-weighted MRI datasets. The arteries were automatically segmented in each MRA dataset and used for vessel radius quantification. The binary segmentation and vessel size information were non-linearly registered to the MNI brain atlas using the T1-weighted MRI datasets to construct atlases of artery occurrence probability, mean artery radius, and artery radius standard deviation. This public neuroimaging resource improves the understanding of the distribution and size of arteries in the healthy human brain.

Cognitive impairments are prevalent in Parkinson’s disease (PD), but the underlying mechanisms of their development are unknown. In this study, we aimed to predict global cognition (GC) in PD with machine learning (ML) using structural neuroimaging, genetics and clinical and demographic characteristics. As a post-hoc analysis, we aimed to explore the connection between novel selected features and GC more precisely and to investigate whether this relationship is specific to GC or is driven by specific cognitive domains. 101 idiopathic PD patients had a cognitive assessment, structural MRI and blood draw. ML was performed on 102 input features including demographics, cortical thickness and subcortical measures, and several genetic variants (APOE, MAPT, SNCA, etc.). Using the combination of RRELIEFF and Support Vector Regression, 11 features were found to be predictive of GC including sex, rs894280, Edinburgh Handedness Inventory, UPDRS-III, education, five cortical thickness measures (R-parahippocampal, L-entorhinal, R-rostral anterior cingulate, L-middle temporal, and R-transverse temporal), and R-caudate volume. The rs894280 of SNCA gene was selected as the most novel finding of ML. Post-hoc analysis revealed a robust association between rs894280 and GC, attention, and visuospatial abilities. This variant indicates a potential role for the SNCA gene in cognitive impairments of idiopathic PD.