Association Between Clonal Hematopoiesis of Indeterminate Potential and Brain ß-Amyloid Deposition in Korean Patients With Cognitive Impairment.

Few studies have focused on the association between clonal hematopoiesis of indeterminate potential (CHIP) and ß-amyloid (Aß) deposition in the brain, which causes Alzheimer's disease. We aimed to investigate the potential role of CHIP in brain Aß deposition in Korean patients. We enrolled 58 Korean patients over 50 yrs of age with cognitive impairment who underwent brain Aß positron emission tomography. We explored CHIP in their peripheral blood using deep-targeted next-generation sequencing. Irrespective of the presence or absence of brain Aß deposition, mutations in DNMT3A and the C:G>T:A single-nucleotide variants were identified as the primary characteristics, which reflect aged hematopoiesis in the study population. Multivariate logistic regression revealed that the presence of CHIP was not associated with brain Aß deposition. As both CHIP and brain Aß deposition are associated with aging, further research is required to elucidate their possible interplay.

Characteristics of discordance between amyloid positron emission tomography and plasma amyloid-ß 42/40 positivity.

Various plasma biomarkers for amyloid-ß (Aß) have shown high predictability of amyloid PET positivity. However, the characteristics of discordance between amyloid PET and plasma Aß42/40 positivity are poorly understood. Thorough interpretation of discordant cases is vital as Aß plasma biomarker is imminent to integrate into clinical guidelines. We aimed to determine the characteristics of discordant groups between amyloid PET and plasma Aß42/40 positivity, and inter-assays variability depending on plasma assays. We compared tau burden measured by PET, brain volume assessed by MRI, cross-sectional cognitive function, longitudinal cognitive decline and polygenic risk score (PRS) between PET/plasma groups (PET-/plasma-, PET-/plasma+, PET+/plasma-, PET+/plasma+) using Alzheimer's Disease Neuroimaging Initiative database. Additionally, we investigated inter-assays variability between immunoprecipitation followed by mass spectrometry method developed at Washington University (IP-MS-WashU) and Elecsys immunoassay from Roche (IA-Elc). PET+/plasma+ was significantly associated with higher tau burden assessed by PET in entorhinal, Braak III/IV, and Braak V/VI regions, and with decreased volume of hippocampal and precuneus regions compared to PET-/plasma-. PET+/plasma+ showed poor performances in global cognition, memory, executive and daily-life function, and rapid cognitive decline. PET+/plasma+ was related to high PRS. The PET-/plasma+ showed intermediate changes between PET-/plasma- and PET+/plasma+ in terms of tau burden, hippocampal and precuneus volume, cross-sectional and longitudinal cognition, and PRS. PET+/plasma- represented heterogeneous characteristics with most prominent variability depending on plasma assays. Moreover, IP-MS-WashU showed more linear association between amyloid PET standardized uptake value ratio and plasma Aß42/40 than IA-Elc. IA-Elc showed more plasma Aß42/40 positivity in the amyloid PET-negative stage than IP-MS-WashU. Characteristics of PET-/plasma+ support plasma biomarkers as early biomarker of amyloidopathy prior to amyloid PET. Various plasma biomarker assays might be applied distinctively to detect different target subjects or disease stages.

Subsequent correlated changes in complement component 3 and amyloid beta oligomers in the blood of patients with Alzheimer's disease.

INTRODUCTION: Alzheimer's disease (AD) involves the complement cascade, with complement component 3 (C3) playing a key role. However, the relationship between C3 and amyloid beta (Aß) in blood is limited. METHODS: Plasma C3 and Aß oligomerization tendency (AßOt) were measured in 35 AD patients and 62 healthy controls. Correlations with cerebrospinal fluid (CSF) biomarkers, cognitive impairment, and amyloid positron emission tomography (PET) were analyzed. Differences between biomarkers were compared in groups classified by concordances of biomarkers. RESULTS: Plasma C3 and AßOt were elevated in AD patients and in CSF or amyloid PET-positive groups. Weak positive correlation was found between C3 and AßOt, while both had strong negative correlations with CSF Aß42 and cognitive performance. Abnormalities were observed for AßOt and CSF Aß42 followed by C3 changes. DISCUSSION: Increased plasma C3 in AD are associated with amyloid pathology, possibly reflecting a defense response for Aß clearance. Further studies on Aß-binding proteins will enhance understanding of Aß mechanisms in blood.

Harnessing the Power of Voice: A Deep Neural Network Model for Alzheimer's Disease Detection.

Background and Purpose: Voice, reflecting cerebral functions, holds potential for analyzing and understanding brain function, especially in the context of cognitive impairment (CI) and Alzheimer's disease (AD). This study used voice data to distinguish between normal cognition and CI or Alzheimer's disease dementia (ADD). Methods: This study enrolled 3 groups of subjects: 1) 52 subjects with subjective cognitive decline; 2) 110 subjects with mild CI; and 3) 59 subjects with ADD. Voice features were extracted using Mel-frequency cepstral coefficients and Chroma. Results: A deep neural network (DNN) model showed promising performance, with an accuracy of roughly 81% in 10 trials in predicting ADD, which increased to an average value of about 82.0%±1.6% when evaluated against unseen test dataset. Conclusions: Although results did not demonstrate the level of accuracy necessary for a definitive clinical tool, they provided a compelling proof-of-concept for the potential use of voice data in cognitive status assessment. DNN algorithms using voice offer a promising approach to early detection of AD. They could improve the accuracy and accessibility of diagnosis, ultimately leading to better outcomes for patients.

qEEG as Biomarker for Alzheimer's Disease: Investigating Relative PSD Difference and Coherence Analysis.

Purpose: Electroencephalography (EEG) is a non-intrusive technique that provides comprehensive insights into the electrical activities of the brain's cerebral cortex. The brain signals obtained from EEGs can be used as a neuropsychological biomarker to detect different stages of Alzheimer's disease (AD) through quantitative EEG (qEEG) analysis. This paper investigates the difference in the abnormalities of resting state EEG (rEEG) signals between eyes-open (EOR) and eyes-closed (ECR) in AD by analyzing 19-scalp electrode EEG signals and making a comparison with healthy controls (HC). Participants and Methods: The rEEG data from 534 subjects (ages 40-90) consisting of 269 HC and 265 AD subjects in South Korea were used in this study. The qEEG for EOR and ECR states were performed separately for HC and AD subjects to measure the relative power spectrum density (PSD) and coherence with functional connectivity to evaluate abnormalities. The rEEG data were preprocessed and analyzed using EEGlab and Brainstorm toolboxes in MATLAB R2021a software, and statistical analyses were carried out using ANOVA. Results: Based on the Welch method, the relative PSD of the EEG EOR and ECR states difference in the AD group showed a significant increase in the delta frequency band of 19 EEG channels, particularly in the frontal, parietal, and temporal, than the HC groups. The delta power band on the source level was increased for the AD group and decreased for the HC group. In contrast, the source activities of alpha, beta, and gamma frequency bands were significantly reduced in the AD group, with a high decrease in the beta frequency band in all brain areas. Furthermore, the coherence of rEEG among different EEG electrodes was analyzed in the beta frequency band. It showed that pair-wise coherence between different brain areas in the AD group is remarkably increased in the ECR state and decreased after subtracting out the EOR state. Conclusion: The findings suggest that examining PSD and functional connectivity through coherence analysis could serve as a promising and comprehensive approach to differentiate individuals with AD from normal, which may benefit our understanding of the disease.

Angiotensin-converting enzyme insertion/deletion gene polymorphism and the progression of cerebral microbleeds.

Background and purpose: The angiotensin-converting enzyme (ACE) insertion (I)/deletion (D) polymorphism has been studied as a genetic candidate for cerebral small vessel disease (CSVD). However, no previous study has evaluated the relationship between the ACE I/D polymorphism and cerebral microbleed (CMB), an important CSVD marker. We evaluated the association between ACE I/D polymorphisms and 2-year changes in CMBs. Methods: The CHALLENGE (Comparison Study of Cilostazol and Aspirin on Changes in Volume of Cerebral Small Vessel Disease White Matter Changes) database was analyzed. Of 256 subjects, 186 participants who underwent a 2-year follow-up brain scan and ACE genotyping were included. Our analysis was conducted by dividing the ACE genotype into two groups (DD vs. ID/II) under the assumption of the recessive effects of the D allele. A linear mixed-effect model was used to compare the 2-year changes in the number of CMBs between the DD and combined ID/II genotypes. Results: Among 186 patients included in this study, 24 (12.9%) had the DD genotype, 91 (48.9%) had the ID genotype, and 71 (38.2%) had the II genotype. Baseline clinical characteristics and cerebral small vessel disease markers were not different between the two groups (DD vs. ID/II) except for the prevalence of hypertension (DD 66.7% vs. ID/II 84.6%; p = 0.04). A multivariate linear mixed-effects model showed that the DD carriers had a greater increase in total CMB counts than the ID/II carriers after adjusting for the baseline number of CMBs, age, sex, and hypertension (estimated mean of difference [standard error (SE)] = 1.33 [0.61]; p = 0.03). When we performed an analysis of cases divided into deep and lobar CMBs, only lobar CMBs were significantly different between the two groups (estimated mean of difference [SE] = 0.94 [0.42]; p = 0.02). Conclusion: The progression of CMBs over 2 years was greater in the ACE DD carriers compared with the combined II/ID carriers. The results of our study indicate a possible association between the ACE I/D polymorphism and CMB. A study with a larger sample size is needed to confirm this association.

PET-validated EEG-machine learning algorithm predicts brain amyloid pathology in pre-dementia Alzheimer's disease.

Developing reliable biomarkers is important for screening Alzheimer's disease (AD) and monitoring its progression. Although EEG is non-invasive direct measurement of brain neural activity and has potentials for various neurologic disorders, vulnerability to noise, difficulty in clinical interpretation and quantification of signal information have limited its clinical application. There have been many research about machine learning (ML) adoption with EEG, but the accuracy of detecting AD is not so high or not validated with Aß PET scan. We developed EEG-ML algorithm to detect brain Aß pathology among subjective cognitive decline (SCD) or mild cognitive impairment (MCI) population, and validated it with Aß PET. 19-channel resting-state EEG and Aß PET were collected from 311 subjects: 196 SCD(36 Aß +, 160 Aß -), 115 MCI(54 Aß +, 61Aß -). 235 EEG data were used for training ML, and 76 for validation. EEG features were standardized for age and sex. Multiple important features sets were selected by 6 statistics analysis. Then, we trained 8 multiple machine learning for each important features set. Meanwhile, we conducted paired t-test to find statistically different features between amyloid positive and negative group. The best model showed 90.9% sensitivity, 76.7% specificity and 82.9% accuracy in MCI + SCD (33 Aß +, 43 Aß -). Limited to SCD, 92.3% sensitivity, 75.0% specificity, 81.1% accuracy (13 Aß +, 24 Aß -). 90% sensitivity, 78.9% specificity and 84.6% accuracy for MCI (20 Aß +, 19 Aß -). Similar trends of EEG power have been observed from the group comparison between Aß + and Aß -, and between MCI and SCD: enhancement of frontal/ frontotemporal theta; attenuation of mid-beta in centroparietal areas. The present findings suggest that accurate classification for beta-amyloid accumulation in the brain based on QEEG alone could be possible, which implies that QEEG is a promising biomarker for beta-amyloid. Since QEEG is more accessible, cost-effective, and safer than amyloid PET, QEEG-based biomarkers may play an important role in the diagnosis and treatment of AD. We expect specific patterns in QEEG could play an important role to predict future progression of cognitive impairment in the preclinical stage of AD. Further feature engineering and validation with larger dataset is recommended.

Increased oligomeric TDP-43 in the plasma of Korean frontotemporal dementia patients with semantic dementia.

INTRODUCTION: Semantic dementia (SD) is a progressive neurodegenerative disease associated with impaired vocabulary that progresses to memory impairment. Post-mortem immunohistochemical analysis is the current reliable method of differentiating TDP-43 deposits in cortical tissue; no means of antemortem diagnosis exists in biofluids, let alone in plasma. METHODS: Here the multimer detection system (MDS) was used to quantify the oligomeric TDP-43 (o-TDP-43) concentrations in plasma of Korean SD patients (n = 16, 6 male, 10 female, ages 59-87). The o-TDP-43 concentrations were compared with the total TDP-43 (t-TDP-43) concentrations quantified through conventional enzyme-linked immunosorbent assay (ELISA). RESULTS AND DISCUSSION: Only MDS showed a significant increase in o-TDP-43 concentrations in the plasma of patients with SD compared to other neurodegenerative disorders and normal controls (p < 0.05). Based on these results, o-TDP-43 concentrations through the application of MDS may be a useful plasma biomarker in SD-FTD (frontotemporal dementia) diagnosis.

Classification of Aß State From Brain Amyloid PET Images Using Machine Learning Algorithm.

Background and Purpose: Analyzing brain amyloid positron emission tomography (PET) images to access the occurrence of ß-amyloid (Aß) deposition in Alzheimer's patients requires much time and effort from physicians, while the variation of each interpreter may differ. For these reasons, a machine learning model was developed using a convolutional neural network (CNN) as an objective decision to classify the Aß positive and Aß negative status from brain amyloid PET images. Methods: A total of 7,344 PET images of 144 subjects were used in this study. The 18F-florbetaben PET was administered to all participants, and the criteria for differentiating Aß positive and Aß negative state was based on brain amyloid plaque load score (BAPL) that depended on the visual assessment of PET images by the physicians. We applied the CNN algorithm trained in batches of 51 PET images per subject directory from 2 classes: Aß positive and Aß negative states, based on the BAPL scores. Results: The binary classification of the model average performance matrices was evaluated after 40 epochs of three trials based on test datasets. The model accuracy for classifying Aß positivity and Aß negativity was (95.00±0.02) in the test dataset. The sensitivity and specificity were (96.00±0.02) and (94.00±0.02), respectively, with an area under the curve of (87.00±0.03). Conclusions: Based on this study, the designed CNN model has the potential to be used clinically to screen amyloid PET images.

CNN for a Regression Machine Learning Algorithm for Predicting Cognitive Impairment Using qEEG.

Purpose: Electroencephalogram (EEG) signals give detailed information on the electrical brain activities occurring in the cerebral cortex. They are used to study brain-related disorders such as mild cognitive impairment (MCI) and Alzheimer's disease (AD). Brain signals obtained using an EEG machine can be a neurophysiological biomarker for early diagnosis of dementia through quantitative EEG (qEEG) analysis. This paper proposes a machine learning methodology to detect MCI and AD from qEEG time-frequency (TF) images of the subjects in an eyes-closed resting state (ECR). Participants and Methods: The dataset consisted of 16,910 TF images from 890 subjects: 269 healthy controls (HC), 356 MCI, and 265 AD. First, EEG signals were transformed into TF images using a Fast Fourier Transform (FFT) containing different event-rated changes of frequency sub-bands preprocessed from the EEGlab toolbox in the MATLAB R2021a environment software. The preprocessed TF images were applied in a convolutional neural network (CNN) with adjusted parameters. For classification, the computed image features were concatenated with age data and went through the feed-forward neural network (FNN). Results: The trained models', HC vs MCI, HC vs AD, and HC vs CASE (MCI + AD), performance metrics were evaluated based on the test dataset of the subjects. The accuracy, sensitivity, and specificity were evaluated: HC vs MCI was 83%, 93%, and 73%, HC vs AD was 81%, 80%, and 83%, and HC vs CASE (MCI + AD) was 88%, 80%, and 90%, respectively. Conclusion: The proposed models trained with TF images and age can be used to assist clinicians as a biomarker in detecting cognitively impaired subjects at an early stage in clinical sectors.

Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: Algorithms and dataset.

For automatic EEG diagnosis, this paper presents a new EEG data set with well-organized clinical annotations called Chung-Ang University Hospital EEG (CAUEEG), which has event history, patient's age, and corresponding diagnosis labels. We also designed two reliable evaluation tasks for the low-cost, non-invasive diagnosis to detect brain disorders: i) CAUEEG-Dementia with normal, mci, and dementia diagnostic labels and ii) CAUEEG-Abnormal with normal and abnormal. Based on the CAUEEG dataset, this paper proposes a new fully end-to-end deep learning model, called the CAUEEG End-to-end Deep neural Network (CEEDNet). CEEDNet pursues to bring all the functional elements for the EEG analysis in a seamless learnable fashion while restraining non-essential human intervention. Extensive experiments showed that our CEEDNet significantly improves the accuracy compared with existing methods, such as machine learning methods and Ieracitano-CNN (Ieracitano et al., 2019), due to taking full advantage of end-to-end learning. The high ROC-AUC scores of 0.9 on CAUEEG-Dementia and 0.86 on CAUEEG-Abnormal recorded by our CEEDNet models demonstrate that our method can lead potential patients to early diagnosis through automatic screening.

A machine-learning algorithm for predicting brain age using Rey-Osterrieth complex figure tests of healthy participants.

OBJECTIVE: Neuropsychologists widely use the Rey-Osterrieth complex figure test (RCFT) as part of neuropsychological test batteries to evaluate cognitive function and assess constructional ability, with age being the most significant factor. Our study investigated a supervised machine learning (ML) algorithm to predict brain age gap using RCFT drawings from the healthy elderly community for early dementia detection. PARTICIPANTS AND METHODS: RCFT drawings from 1,970 healthy subjects (ages 45-90 years) were collected from the Korean elderly community. We recorded subject demographic information including: age, gender, and education level. We trained the ML model with RCFT copies, immediate recall, delayed recall, and education level of the healthy subjects using CNN regression algorithm from Keras (https://keras.io/) with the Tensorflow library. RESULTS: The performance was evaluated by the mean absolute error (MAE) and root mean squared error (RMSE) between the predicted age and the chronological age based on a test dataset of 300 healthy subjects. The CNN regression model achieved an MAE of 7.2 years in predicting the brain age gap of the subjects, with an RMSE of 8.9 years. CONCLUSION: The MAE and RMSE accuracies of the CNN regression model predicting the brain age gap showed the model could be a potential biomarker for individual brain aging and a cost-effective method for early dementia detection.

Alpha-synuclein: a pathological factor with Aß and tau and biomarker in Alzheimer's disease.

BACKGROUND: Alpha-synuclein (α-syn) is considered the main pathophysiological protein component of Lewy bodies in synucleinopathies. α-Syn is an intrinsically disordered protein (IDP), and several types of structural conformations have been reported, depending on environmental factors. Since IDPs may have distinctive functions depending on their structures, α-syn can play different roles and interact with several proteins, including amyloid-beta (Aß) and tau, in Alzheimer's disease (AD) and other neurodegenerative disorders. MAIN BODY: In previous studies, α-syn aggregates in AD brains suggested a close relationship between AD and α-syn. In addition, α-syn directly interacts with Aß and tau, promoting mutual aggregation and exacerbating the cognitive decline. The interaction of α-syn with Aß and tau presented different consequences depending on the structural forms of the proteins. In AD, α-syn and tau levels in CSF were both elevated and revealed a high positive correlation. Especially, the CSF α-syn concentration was significantly elevated in the early stages of AD. Therefore, it could be a diagnostic marker of AD and help distinguish AD from other neurodegenerative disorders by incorporating other biomarkers. CONCLUSION: The overall physiological and pathophysiological functions, structures, and genetics of α-syn in AD are reviewed and summarized. The numerous associations of α-syn with Aß and tau suggested the significance of α-syn, as a partner of the pathophysiological roles in AD. Understanding the involvements of α-syn in the pathology of Aß and tau could help address the unresolved issues of AD. In particular, the current status of the CSF α-syn in AD recommends it as an additional biomarker in the panel for AD diagnosis.

Prediction of amyloid PET positivity via machine learning algorithms trained with EDTA-based blood amyloid-ß oligomerization data.

BACKGROUND: The tendency of amyloid-ß to form oligomers in the blood as measured with Multimer Detection System-Oligomeric Amyloid-ß (MDS-OAß) is a valuable biomarker for Alzheimer's disease and has been verified with heparin-based plasma. The objective of this study was to evaluate the performance of ethylenediaminetetraacetic acid (EDTA)-based MDS-OAß and to develop machine learning algorithms to predict amyloid positron emission tomography (PET) positivity. METHODS: The performance of EDTA-based MDS-OAß in predicting PET positivity was evaluated in 312 individuals with various machine learning models. The models with various combinations of features (i.e., MDS-OAß level, age, apolipoprotein E4 alleles, and Mini-Mental Status Examination [MMSE] score) were tested 50 times on each dataset. RESULTS: The random forest model best-predicted amyloid PET positivity based on MDS-OAß combined with other features with an accuracy of 77.14 ± 4.21% and an F1 of 85.44 ± 3.10%. The order of significance of predictive features was MDS-OAß, MMSE, Age, and APOE. The Support Vector Machine using the MDS-OAß value only showed an accuracy of 71.09 ± 3.27% and F-1 value of 80.18 ± 2.70%. CONCLUSIONS: The Random Forest model using EDTA-based MDS-OAß combined with the MMSE and apolipoprotein E status can be used to prescreen for amyloid PET positivity.

Prediction of East Asian Brain Age using Machine Learning Algorithms Trained With Community-based Healthy Brain MRI.

Background and Purpose: Magnetic resonance imaging (MRI) helps with brain development analysis and disease diagnosis. Brain volumes measured from different ages using MRI provides useful information in clinical evaluation and research. Therefore, we trained machine learning models that predict the brain age gap of healthy subjects in the East Asian population using T1 brain MRI volume images. Methods: In total, 154 T1-weighted MRIs of healthy subjects (55-83 years of age) were collected from an East Asian community. The information of age, gender, and education level was collected for each participant. The MRIs of the participants were preprocessed using FreeSurfer(https://surfer.nmr.mgh.harvard.edu/) to collect the brain volume data. We trained the models using different supervised machine learning regression algorithms from the scikit-learn (https://scikit-learn.org/) library. Results: The trained models comprised 19 features that had been reduced from 55 brain volume labels. The algorithm BayesianRidge (BR) achieved a mean absolute error (MAE) and r squared (R2) of 3 and 0.3 years, respectively, in predicting the age of the new subjects compared to other regression methods. The results of feature importance analysis showed that the right pallidum, white matter hypointensities on T1-MRI scans, and left hippocampus comprise some of the essential features in predicting brain age. Conclusions: The MAE and R2 accuracies of the BR model predicting brain age gap in the East Asian population showed that the model could reduce the dimensionality of neuroimaging data to provide a meaningful biomarker for individual brain aging.

Genetic Screening in Korean Patients with Frontotemporal Dementia Syndrome.

Background: Frontotemporal dementia (FTD) syndrome is a genetically heterogeneous group of diseases. Pathogenic variants in the chromosome 9 open reading frame 72 (C9orf72), microtubule-associated protein tau (MAPT), and progranulin (GRN) genes are mainly associated with genetic FTD in Caucasian populations. Objective: To understand the genetic background of Korean patients with FTD syndrome. Methods: We searched for pathogenic variants of 52 genes related to FTD, amyotrophic lateral sclerosis, familial Alzheimer's disease, and other dementias, and hexanucleotide repeats of the C9orf72 gene in 72 Korean patients with FTD using whole exome sequencing and the repeat-primed polymerase chain reaction, respectively. Results: One likely pathogenic variant, p.G706R of MAPT, in a patient with behavioral variant FTD (bvFTD) and 13 variants of uncertain significance (VUSs) in nine patients with FTD were identified. Of these VUSs, M232R of the PRNP gene, whose role in pathogenicity is controversial, was also found in two patients with bvFTD. Conclusions: These results indicate that known pathogenic variants of the three main FTD genes (MAPT, GRN, and C9orf72) in Western countries are rare in Korean FTD patients.

Relationship Between Calcium Channel Blockers Therapy and Cognitive Function Improvement in Cognitive Decline Patients with Cerebrovascular Disease.

INTRODUCTION: Amlodipine belongs to a class of calcium channel blockers that relax blood vessels to allow easier flow of blood. Higher blood pressure (BP) is associated with cerebrovascular disease and is an important contributor to cognitive decline and dementia. AIM: This study aimed to evaluate the effect of 24 weeks of S-amlodipine besylate therapy on cognitive function in patients with hypertension and cerebrovascular disease. METHODS: The data were obtained from a study of post-market surveillance of S-amlodipine besylate. RESULTS: A total of 545 subjects (mean age 67 ± 9.68 years) with hypertension and ischemic cerebrovascular disease were enrolled. Patients with a baseline Mini-Mental State Examination (MMSE) score above 26 were assigned to the cognitive normal (CN) (n = 294) group, and those with MMSE score less than 26 were in the cognitive decline (CD) (n = 251) group. After 24 weeks of treatment with S-amlodipine besylate 5 mg, MMSE and Global Deterioration Scale (GDS) were evaluated again. Changes in MMSE were compared in the target BP reached (TBPR) and non-reached (NTBPR) groups and for CN and CD groups. Treatment with 5 mg of S-amlodipine besylate for 24 weeks improved MMSE and GDS scores (p < 0.001). The CD group showed improvement in MMSE score regardless of whether target BP was obtained (TBPR: p < 0.001, NTBPR: p < 0.01). However, the CN classification was not significant for either TBPR or NTBPR groups. CONCLUSIONS: S-amlodipine besylate improved cognition of the CD group with hypertension and cerebrovascular disease regardless of obtaining target BP.

Predicting progression to dementia with "comprehensive visual rating scale" and machine learning algorithms.

Background and Objective: Identifying biomarkers for predicting progression to dementia in patients with mild cognitive impairment (MCI) is crucial. To this end, the comprehensive visual rating scale (CVRS), which is based on magnetic resonance imaging (MRI), was developed for the assessment of structural changes in the brains of patients with MCI. This study aimed to investigate the use of the CVRS score for predicting dementia in patients with MCI over a 2-year follow-up period using various machine learning (ML) algorithms. Methods: We included 197 patients with MCI who were followed up more than once. The data used for this study were obtained from the Japanese-Alzheimer's Disease Neuroimaging Initiative study. We assessed all the patients using their CVRS scores, cortical thickness data, and clinical data to determine their progression to dementia during a follow-up period of over 2 years. ML algorithms, such as logistic regression, random forest (RF), XGBoost, and LightGBM, were applied to the combination of the dataset. Further, feature importance that contributed to the progression from MCI to dementia was analyzed to confirm the risk predictors among the various variables evaluated. Results: Of the 197 patients, 108 (54.8%) showed progression from MCI to dementia. Tree-based classifiers, such as XGBoost, LightGBM, and RF, achieved relatively high performance. In addition, the prediction models showed better performance when clinical data and CVRS score (accuracy 0.701-0.711) were used than when clinical data and cortical thickness (accuracy 0.650-0.685) were used. The features related to CVRS helped predict progression to dementia using the tree-based models compared to logistic regression. Conclusions: Tree-based ML algorithms can predict progression from MCI to dementia using baseline CVRS scores combined with clinical data.

Automated brain volumetric program measuring regional brain atrophy in diagnosis of mild cognitive impairment and Alzheimer's disease dementia.

A quantitative analysis of brain volume can assist in the diagnosis of Alzheimer's disease (AD) which is ususally accompanied by brain atrophy. With an automated analysis program Quick Brain Volumetry (QBraVo) developed for volumetric measurements, we measured regional volumes and ratios to evaluate their performance in discriminating AD dementia (ADD) and mild cognitive impairment (MCI) patients from normal controls (NC). Validation of QBraVo was based on intra-rater and inter-rater reliability with a manual measurement. The regional volumes and ratios to total intracranial volume (TIV) and to total brain volume (TBV) or total cerebrospinal fluid volume (TCV) were compared among subjects. The regional volume to total cerebellar volume ratio named Standardized Atrophy Volume Ratio (SAVR) was calculated to compare brain atrophy. Diagnostic performances to distinguish among NC, MCI, and ADD were compared between MMSE, SAVR, and the predictive model. In total, 56 NCs, 44 MCI, and 45 ADD patients were enrolled. The average run time of QBraVo was 5 min 36 seconds. Intra-rater reliability was 0.999. Inter-rater reliability was high for TBV, TCV, and TIV (R = 0.97, 0.89 and 0.93, respectively). The medial temporal SAVR showed the highest performance for discriminating ADD from NC (AUC = 0.808, diagnostic accuracy = 80.2%). The predictive model using both MMSE and medial temporal SAVR improved the diagnostic performance for MCI in NC (AUC = 0.844, diagnostic accuracy = 79%). Our results demonstrated QBraVo is a fast and accurate method to measure brain volume. The regional volume calculated as SAVR could help to diagnose ADD and MCI and increase diagnostic accuracy for MCI.

Neuropsychological test using machine learning for cognitive impairment screening.

OBJECTIVES: Neuropsychological tests (NPTs) are widely used tools to evaluate cognitive functioning. The interpretation of these tests can be time-consuming and requires a specialized clinician. For this reason, we trained machine learning models that detect normal controls (NC), cognitive impairment (CI), and dementia among subjects. PATIENTS AND METHODS: A total number of 14,927 subject datasets were collected from the formal neuropsychological assessments Seoul Neuropsychological Screening Battery (SNSB) by well-qualified neuropsychologists. The dataset included 44 NPTs of SNSB, age, education level, and diagnosis of each participant. The dataset was preprocessed and classified according to three different classes NC, CI, and dementia. We trained machine-learning with a supervised machine learning classifier algorithm support vector machine (SVM) 30 times with classification from scikit-learn (https://scikit-learn.org/stable/) to distinguish the prediction accuracy, sensitivity, and specificity of the models; NC vs. CI, NC vs. dementia, and NC vs. CI vs. dementia. Confusion matrixes were plotted using the testing dataset for each model. RESULTS: The trained model's 30 times mean accuracies for predicting cognitive states were as follows; NC vs. CI model was 88.61 ± 1.44%, NC vs. dementia model was 97.74 ± 5.78%, and NC vs. CI vs. dementia model was 83.85 ± 4.33%. NC vs. dementia showed the highest accuracy, sensitivity, and specificity of 97.74 ± 5.78, 97.99 ± 5.78, and 96.08 ± 4.33% in predicting dementia among subjects, respectively. CONCLUSION: Based on the results, the SVM algorithm is more appropriate in training models on an imbalanced dataset for a good prediction accuracy compared to natural network and logistic regression algorithms. The NC vs. dementia machine-learning trained model with SVM based on NPTs SNSB dataset could assist neuropsychologists in classifying the cognitive function of subjects.