Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including ...preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, amygdalae and insulae were selected from the volumetric analysis of structured magnetic resonance images (MRIs). Three-view patches (TVPs) from these regions were fed to the CNN for training. MRIs were classified with the SoftMax-normalized scores of individual model predictions on TVPs. The significance of each region of interest (ROI) for staging the AD spectrum was evaluated and reported. The results of the ensemble classifier are compared with state-of-the-art methods using the same evaluation metrics. Patch-based ROI ensembles provide comparable diagnostic performance for AD staging. In this work, TVP-based ROI analysis using a CNN provides informative landmarks in cerebral MRIs and may have significance in clinical studies and computer-aided diagnosis system design.
Gender differences in motor and non-motor symptoms in Parkinson disease (PD) are still controversial. This study aimed to investigate gender differences in clinical characteristics in patients with ...early PD.This study included 415 PD patients (201 men and 214 women) with modified Hoehn-Yahr stage 1 to 3 and a disease duration of ≤5 years. Demographic information was obtained by interviews, and motor and non-motor PD symptoms were evaluated with appropriate scales.Women with PD had a shorter duration of formal education than men with PD. No significant differences were found in other demographic variables. Women with PD had significantly lower scores in Unified Parkinson Disease Rating Scale part III and postural tremor compared to men with PD, which was significant after controlling for formal education. No significant gender-related differences were found in scores related to other motor symptoms. Concerning non-motor symptoms, men with PD had higher scores of sexual function on the Non-Motor Symptoms Scale, which means sexual dysfunction was more severe or occurred more frequently in men with PD. Women with PD had significantly higher scores of sleep disturbance in the Pittsburgh Sleep Quality Index, which was not significant after adjustment for multiple comparison.The present study suggests that women with PD had milder motor symptoms compared to men with PD, and gender differences in sexual function can be observed as non-motor symptoms.
Apathy is a common non-motor symptom of Parkinson disease (PD) that can affect the health-related quality of life (HRQoL) of patients and caregivers. This study aimed to investigate the clinical ...determinants of apathy and its impact on HRQoL in patients with early PD. We enrolled 324 patients with early PD with modified Hoehn-Yahr stages 1 to 3 and a disease duration ≤5 years. Demographic information was obtained, and motor and non-motor symptoms were evaluated with relevant scales. Apathy was present in 110 of 324 (33.9%) patients. Compared with patients with non-apathetic PD, those with apathetic PD had significantly higher modified Hoehn-Yahr stage, Unified Parkinson's Disease Rating Scale-II (UPDRS-II) score, Non-Motor Symptoms Scale (NMSS) total score, Beck Depression Inventory (BDI) score, and Parkinson's Disease Questionnaire-8 (PDQ-8) score. Clinical variables independently associated with the Apathy Evaluation Scale (AES) score were NMSS domain 3 score and BDI score. The univariate regression analysis revealed that the PDQ-8 score was significantly associated with age; disease duration; formal education duration; and UPDRS-III, UPDRS-II, NMSS total, Mini-Mental Status Examination, BDI, Beck Anxiety Inventory, and AES scores. Independent predictors of the PDQ-8 score in the multivariate regression analysis were UPDRS-III, UPDRS-II, NMSS total, NMSS domain 3, Beck Anxiety Inventory, and AES scores. In the present study, apathy was an independent predictor of HRQoL in patients with early PD. Therefore, identifying and managing apathy could help improve HRQoL in patients with early PD.
To characterize the course of Alzheimer's disease (AD) over a longer time interval, we aimed to construct a disease course model for the entire span of the disease using two separate cohorts ranging ...from preclinical AD to AD dementia. We modelled the progression course of 436 patients with AD continuum and investigated the effects of apolipoprotein E ε4 (APOE ε4) and sex on disease progression. To develop a model of progression from preclinical AD to AD dementia, we estimated Alzheimer's Disease Assessment Scale-Cognitive Subscale 13 (ADAS-cog 13) scores. When calculated as the median of ADAS-cog 13 scores for each cohort, the estimated time from preclinical AD to MCI due to AD was 7.8 years and preclinical AD to AD dementia was 15.2 years. ADAS-cog 13 scores deteriorated most rapidly in women APOE ε4 carriers and most slowly in men APOE ε4 non-carriers (p < 0.001). Our results suggest that disease progression modelling from preclinical AD to AD dementia may help clinicians to estimate where patients are in the disease course and provide information on variation in the disease course by sex and APOE ε4 status.
Alzheimer disease (AD) is a leading cause of dementia that has gained prominence in our aging society. Yet, the complexity of diagnosing AD and measuring its invasiveness poses an obstacle. To this ...end, blood-based biomarkers could mitigate the inconveniences that impede an accurate diagnosis. We developed models to diagnose AD and measure the severity of neurocognitive impairment using blood protein biomarkers. Multiple reaction monitoring-mass spectrometry, a highly selective and sensitive approach for quantifying targeted proteins in samples, was used to analyze blood samples from 4 AD groups: cognitive normal control, asymptomatic AD, prodromal AD), and AD dementia. Multimarker models were developed using 10 protein biomarkers and apolipoprotein E genotypes for amyloid beta and 10 biomarkers with Korean Mini-Mental Status Examination (K-MMSE) score for predicting Alzheimer disease progression. The accuracies for the AD classification model and AD progression monitoring model were 84.9% (95% CI 82.8 to 87.0) and 79.1% (95% CI 77.8 to 80.5), respectively. The models were more accurate in diagnosing AD, compared with single APOE genotypes and the K-MMSE score. Our study demonstrates the possibility of predicting AD with high accuracy by blood biomarker analysis as an alternative method of screening for AD.
Alzheimer's disease (AD) is a progressive neurodegenerative disorder that is mostly prevalent in people older than 65 years. The hippocampus is a widely studied region of interest (ROI) for a number ...of reasons, such as memory function analysis, stress development observation and neurological disorder investigation. Moreover, hippocampal volume atrophy is known to be linked with Alzheimer's disease. On the other hand, several biomarkers, such as amyloid beta (<inline-formula> <tex-math notation="LaTeX">\text{a}\beta _{42} </tex-math></inline-formula>) protein, tau, phosphorylated tau and hippocampal volume atrophy, are being used to diagnose AD. In this research work, we have proposed a method to diagnose AD based on slice-wise volumetric features extracted from the left and right hippocampi of structural magnetic resonance imaging (sMRI) data. The proposed method is an aggregation of a convolutional neural network (CNN) model with a deep neural network (DNN) model. The left and right hippocampi have been localized automatically using a two-stage ensemble Hough-CNN. The localized hippocampal positions are used to extract (<inline-formula> <tex-math notation="LaTeX">80\times 80\times </tex-math></inline-formula>80 voxels) 3-D patches. The 2-D slices are then separated from the 3-D patches along axial, sagittal, and coronal views. The pre-processed 2-D patches are used to extract volumetric features from each slice by using a discrete volume estimation convolutional neural network (DVE-CNN) model. The extracted volumetric features have been used to train and test the classification network. The proposed approach has achieved average weighted classification accuracies of 94.82% and 94.02% based on the extracted volumetric features attributed to the left and right hippocampi, respectively. In addition, it has achieved area under the curve (AUC) values of 92.54% and 90.62% for the left and right hippocampi, respectively. Our method has outperformed the other methods by a certain margin in the same dataset.
Alzheimer's disease (AD) is the most common form of dementia with irreversible neurodegeneration. Accumulation of amyloid beta (Aβ) in the brain is considered to be a major cause of neuronal cell ...death in AD, but the neurotoxic mechanism of Aβ is not yet fully understood. Here, we focused on the role of microRNAs (miRNAs) in Aβ-induced neuronal cell death. In microarray and RT-qPCR analysis of plasma miRNAs obtained from 5 familiar AD mutations (5xFAD) and wild-type (WT) mice of various ages, miR-16-5p showed a significant age-related change that was accompanied by neuronal cell death in the brain tissue of 5xFAD mice. In addition, increased miR-16-5p was prominent near Aβ plaque-deposition sites in 5xFAD mouse brains. Aβ treatment induced miR-16-5p upregulation and apoptosis in primary cultured mouse cortical neurons and the SH-SY5Y human neuroblastoma cell line. In silico analysis and reporter gene assays indicated that miR-16-5p directly targets the mRNA encoding the anti-apoptotic factor, B cell lymphoma-2 (BCL-2), in the neuronal cell line. Overexpression of miR-16-5p in SH-SY5Y cells downregulated BCL-2 expression and induced apoptosis. These results collectively suggest that the miR-16-5p/BCL-2 axis plays an important role for neuronal cell apoptosis in AD.
•Loss of neuron occurred near Aβ plaques in the 5xFAD mouse brains.•miR-16-5p was upregulated by Aβ deposition in in vivo and in vitro AD models.•Upregulation of miR-16-5p caused neuronal cell apoptosis via targeting BCL-2.•Upregulation of miR-16-5p may be a risk factor for neuronal cell apoptosis in AD.
Clustering stroke patients with similar characteristics to predict subsequent vascular outcome events is critical. This study aimed to compare several clustering methods, particularly a deep neural ...network-based model, and identify the best clustering method with a maximally distinct 1-year outcome in patients with ischemic stroke. Prospective stroke registry data from a comprehensive stroke center from January 2011 to July 2018 were retrospectively analyzed. Patients with acute ischemic stroke within 7 days of onset were included. The primary outcomes were the composite of all strokes (either hemorrhagic or ischemic), myocardial infarction, and all-cause mortality within one year. Neural network-based clustering models (deep lifetime clustering) were compared with other clustering models (k-prototype and semi-supervised clustering, SSC) and a conventional risk score (Stroke Prognostic Instrument-II, SPI-II) to obtain a distinct distribution of 1-year vascular events. Ultimately, 7,650 patients were included, and the 1-year primary outcome event occurred in 13.1%. The DLC-Kuiper UB model had a significantly higher C-index (0.674), log-rank score (153.1), and Brier score (0.08) than the other cluster models (SSC and DLC-MMD) and the SPI-II score. There were significant differences in primary outcome events among the 3 clusters (41.7%, 13.4%, and 6.5% in clusters 0, 1, and 2, respectively) when the DLC-Kuiper UB model was used. A neural network-based clustering model, the DLC-Kuiper UB model, can improve the clustering of stroke patients with a maximally distinct distribution of 1-year vascular outcomes among each cluster. Further studies are warranted to validate this deep neural network-based clustering model in ischemic stroke.
L. is the largest genus within the Convolvulaceae and contains 600-700 species.
species (morning glories) are economically valuable as horticultural species and scientifically valuable as ecological ...model plants to investigate mating systems, molecular evolution, and both plant-herbivore and plant-parasite interactions. Furthermore, the dried seeds of
or
are used in Korean traditional herbal medicines. In this study, chloroplast (cp) genomes were sequenced from six
species, namely,
and
and, for the first time,
, and
var.
. The cp genomes were 161,354-161,750 bp in length and exhibited conserved quadripartite structures. In total, 112 genes were identified, including 78 protein-coding regions, 30 transfer RNA genes, and 4 ribosomal RNA genes. The gene order, content, and orientation of the six
cp genomes were highly conserved and were consistent with the general structure of angiosperm cp genomes. Comparison of the six
cp genomes revealed locally divergent regions, mainly within intergenic spacer regions (
, and
). In addition, the protein-coding genes
, and
exhibited high sequence variability and were under positive selection (Ka/Ks > 1), indicating adaptive evolution to the environment within the
genus. Phylogenetic analysis of the six
species revealed that these species clustered according to the APG IV system. In particular,
and
had monophyletic positions, with
as a sister.
and
in the section Batatas and
and
var.
in the section Quamoclit were supported in this study with strong bootstrap values and posterior probabilities. We uncovered high-resolution phylogenetic relationships between Ipomoeeae. Finally, indel markers (IPOTY and IPOYCF) were developed for the discrimination of the important herbal medicine species
and
. The cp genomes and analyses in this study provide useful information for taxonomic, phylogenetic, and evolutionary analysis of the
genome, and the indel markers will be useful for authentication of herbal medicines.