Search

T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended. [ABSTRACT FROM AUTHOR]

Oxidative stress, inflammation, and increased cholesterol levels are all mechanisms that have been associated with Alzheimer's disease (AD) pathology. Several epidemiologic studies have reported a decreased risk of AD with fish consumption. This pilot study was designed to evaluate the effects of supplementation with omega-3 fatty acids alone (ω-3) or omega-3 plus alpha lipoic acid (ω-3 + LA) compared to placebo on oxidative stress biomarkers in AD. The primary outcome measure was peripheral F2-isoprostane levels (oxidative stress measure). Secondary outcome measures included performance on: Mini-Mental State Examination (MMSE), Activities of Daily Living/Instrumental Activities of Daily Living (ADL/IADL), and Alzheimer Disease Assessment Scale-cognitive subscale (ADAS-cog). Thirty-nine AD subjects were randomized to one of three groups: 1) placebo, 2) ω-3, or 3) ω-3 + LA for a treatment duration of 12 months. Eighty seven percent (34/39) of the subjects completed the 12-month intervention. There was no difference between groups at 12 months in peripheral F2-isoprostane levels (p = 0.83). The ω-3 + LA and ω-3 were not significantly different than the placebo group in ADAS-cog (p = 0.98, p = 0.86) and in ADL (p = 0.15, p = 0.82). Compared to placebo, the ω-3 + LA showed less decline in MMSE (p < 0.01) and IADL (p = 0.01) and the ω-3 group showed less decline in IADL (p < 0.01). The combination of ω-3 + LA slowed cognitive and functional decline in AD over 12 months. Because the results were generated from a small sample size, further evaluation of the combination of omega-3 fatty acids plus alpha-lipoic acid as a potential treatment in AD is warranted. [ABSTRACT FROM AUTHOR]

T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended.