Predicting Progression from Normal to MCI and from MCI to AD Using Clinical Variables in the National Alzheimer's Coordinating Center Uniform Data Set Version 3: Application of Machine Learning Models and a Probability Calculator

Clinical trials are increasingly focused on pre-manifest and early Alzheimer's disease (AD). Accurately predicting clinical progressions from normal to MCI or from MCI to dementia/AD versus non-progression is challenging. Accurate identification of symptomatic progressors is important to avoid unnecessary treatment and improve trial efficiency. Due to large inter-individual variability, biomarker positivity and comorbidity information are often insufficient to identify those destined to have symptomatic progressions. Using only clinical variables, we aimed to predict clinical progressions, estimating probabilities of progressions with a small set of variables selected by machine learning approaches. This work updates our previous work that was applied to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set Version 2 (V2), by using the most recent version (V3) with additional analyses. We generated a user-friendly conversion probability calculator which can be used for effectively pre-screening trial participants.

Relationship of amyloid beta and neurofibrillary tau deposition in Neurodegeneration in Aging Down Syndrome (NiAD) study at baseline

IMPORTANCE

Adults with Down syndrome (DS) are at high-risk of revealing Alzheimer's disease (AD) pathology, in part due to the triplication of chromosome 21 encoding the amyloid precursor protein. Adults with DS are uniformly affected by AD pathology by their 30's and have a 70% to 80% chance of clinical dementia by their 60's. Our previous studies have assessed longitudinal changes in amyloid beta (Aβ) accumulation in DS.

OBJECTIVE

The goal of the present study was to assess the presence of brain tau using [18F]AV-1451 positron emission tomography (PET) in DS and to assess the relationship of brain tau pathology to Aβ using Pittsburgh Compound B (PiB)-PET.

DESIGN

Cohort study.

SETTING

Multi-center study.

PARTICIPANTS

Participants consisted of a sample of individuals with DS and sibling controls recruited from the community; exclusion criteria included contraindications for magnetic resonance imaging (MRI) and/or a medical or psychiatric condition that impaired cognitive functioning.

EXPOSURES

PET brain scans to assess Aβ ([11C]PiB) and tau ([18F]AV-1451) burden.

MAIN OUTCOMES AND MEASURES

Multiple linear regression models (adjusted for chronological age, sex and performance site) were used to examine associations between regional [18F]AV-1451 standard uptake value ratio (SUVR) (based on regions associated with Braak stages 1-6) and global [11C]PiB SUVR (as both a continuous and dichotomous variable).

RESULTS

A cohort of 156 participants (mean age = 39.05, SD(8.4)) were examined. These results revealed a significant relationship between in vivo Aβ and tau pathology in DS. As a dichotomous variable, [18F]AV-1451 retention was higher in each Braak region in PiB(+) participants. We also found, based on our statistical models, starting with the Braak 3 region of interest (ROI), an acceleration of [18F]AV-1451 SUVR deposition with [11C]PiB SUVR increases.

Amyloid-β and Parkinson's disease

Parkinson's disease (PD) is the second commonest neurodegenerative disorder in the world with a rising prevalence. The pathophysiology is multifactorial but aggregation of misfolded α-synuclein is considered to be a key underpinning mechanism. Amyloid-β (Aβ) and tau deposition are also comorbid associations and especially Aβ deposition is associated with cognitive decline in PD. Some existing evidence suggests that low cerebrospinal fluid (CSF) Aβ₄₂ is predictive of future cognitive impairment in PD. Recent studies also show that CSF Aβ is associated with the postural instability and gait difficulties (PIGD) or the newly proposed cholinergic subtype of PD, a possible risk factor for cognitive decline in PD. The glial-lymphatic system, responsible for convective solute clearance driven by active fluid transport through aquaporin-4 water channels, may be implicated in brain amyloid deposition. A better understanding of the role of this system and more specifically the role of Aβ in PD symptomatology, could introduce new treatment and repurposing drug-based strategies. For instance, apomorphine infusion has been shown to promote the degradation of Aβ in rodent models. This is further supported in a post-mortem study in PD patients although clinical implications are unclear. In this review, we address the clinical implication of cerebral Aβ deposition in PD and elaborate on its metabolism, its role in cognition and motor function/gait, and finally assess the potential effect of apomorphine on Aβ deposition in PD.

The impact of transcranial magnetic stimulation on diagnostic confidence in patients with Alzheimer disease

Background

Cholinergic dysfunction is a key abnormality in Alzheimer disease (AD) that can be detected in vivo with transcranial magnetic stimulation (TMS) protocols. Although TMS has clearly demonstrated analytical validity, its clinical utility is still debated. In the present study, we evaluated the incremental diagnostic value, expressed in terms of diagnostic confidence of Alzheimer disease (DCAD; range 0–100), of TMS measures in addition to the routine clinical diagnostic assessment in patients evaluated for cognitive impairment as compared with validated biomarkers of amyloidosis.

Methods

One hundred twenty patients with dementia were included and scored in terms of DCAD in a three-step assessment based on (1) demographic, clinical, and neuropsychological evaluations (clinical work-up); (2) clinical work-up plus amyloid markers (cerebrospinal fluid or amyloid positron emission tomographic imaging); and (3) clinical work-up plus TMS intracortical connectivity measures. Two blinded neurologists were asked to review the diagnosis and diagnostic confidence at each step.

Results

TMS measures increased the discrimination of DCAD in two clusters (AD-like vs FTD-like) when added to the clinical and neuropsychological evaluations with levels comparable to established biomarkers of brain amyloidosis (cluster distance of 55.1 for clinical work-up alone, 76.0 for clinical work-up plus amyloid markers, 80.0 for clinical work-up plus TMS). Classification accuracy for the “gold standard” diagnosis (dichotomous - AD vs FTD - variable) evaluated in the three-step assessment, expressed as AUC, increased from 0.82 (clinical work-up alone) to 0.98 (clinical work-up plus TMS) and to 0.99 (clinical work-up plus amyloidosis markers).

Conclusions

TMS in addition to routine assessment in patients with dementia has a significant effect on diagnosis and diagnostic confidence that is comparable to well-established amyloidosis biomarkers.

Electronic supplementary material

The online version of this article (10.1186/s13195-018-0423-6) contains supplementary material, which is available to authorized users.

Weight loss in the healthy elderly might be a non-cognitive sign of preclinical Alzheimer's disease

Weight loss has been proposed as a sign of pre-clinical Alzheimer Disease (AD). To test this hypothesis, we have evaluated the association between longitudinal changes in weight trajectories, cognitive performance, AD biomarker profiles and brain structure in 363 healthy controls from the Alzheimer´s Disease Neuroimaging Initiative (mean follow-up 50.5±30.5 months). Subjects were classified according to body weight trajectory into a weight loss group (WLG; relative weight loss ≥ 5%) and a non-weight loss group (non-WLG; relative weight loss < 5%). Linear mixed effects models were used to estimate the effect of body weight changes on ADAS-Cognitive score across time. Baseline CSF tau/AΔ₄₂ ratio and AV45 PET uptake were compared between WLG and non-WLG by analysis of covariance. Atrophy maps were compared between groups at baseline and longitudinally at a 2-year follow-up using Freesurfer. WLG showed increased baseline levels of cerebrospinal fluid tau/AΔ₄₂ ratio, increased PET amyloid uptake and diminished cortical thickness at baseline. WLG also showed faster cognitive decline and faster longitudinal atrophy. Our data support weight loss as a non-cognitive manifestation of pre-clinical AD.