Predicting positron emission tomography brain amyloid positivity using interpretable machine learning models with wearable sensor data and lifestyle factors.

BACKGROUND: Developing a screening method for identifying individuals at higher risk of elevated brain amyloid burden is important to reduce costs and burden to patients in clinical trials on Alzheimer's disease or the clinical setting. We developed machine learning models using objectively measured lifestyle factors to predict elevated brain amyloid burden on positron emission tomography. METHODS: Our prospective cohort study of non-demented, community-dwelling older adults aged ≥ 65 years was conducted from August 2015 to September 2019 in Usuki, Oita Prefecture, Japan. One hundred and twenty-two individuals with mild cognitive impairment or subjective memory complaints (54 men and 68 women, median age: 75.50 years) wore wearable sensors and completed self-reported questionnaires, cognitive test, and positron emission tomography imaging at baseline. Moreover, 99 individuals in the second year and 61 individuals in the third year were followed up. In total, 282 eligible records with valid wearable sensors, cognitive test results, and amyloid imaging and data on demographic characteristics, living environments, and health behaviors were used in the machine learning models. Amyloid positivity was defined as a standardized uptake value ratio of ≥ 1.4. Models were constructed using kernel support vector machine, Elastic Net, and logistic regression for predicting amyloid positivity. The mean score among 10 times fivefold cross-validation repeats was utilized for evaluation. RESULTS: In Elastic Net, the mean area under the receiver operating characteristic curve of the model using objectively measured lifestyle factors alone was 0.70, whereas that of the models using wearable sensors in combination with demographic characteristics and health and life environment questionnaires was 0.79. Moreover, 22 variables were common to all machine learning models. CONCLUSION: Our machine learning models are useful for predicting elevated brain amyloid burden using readily-available and noninvasive variables without the need to visit a hospital. TRIAL REGISTRATION: This prospective study was conducted in accordance with the Declaration of Helsinki and was approved by the local ethics committee of Oita University Hospital (UMIN000017442). A written informed consent was obtained from all participants. This research was performed based on the Strengthening the Reporting of Observational Studies in Epidemiology reporting guideline.

Comparison of Brain Amyloid Deposition and Cortical Glucose Metabolism Between Clinic- and Community-Based Cohort.

BACKGROUND: The differences in positron emission tomography (PET) imaging among older adults with mild cognitive impairment (MCI), according to the recruitment source, remain unclear. OBJECTIVE: To investigate the differences in brain amyloid deposition and cortical glucose metabolism according to recruitment source among older adults with MCI. METHODS: Participants in the clinic-based MCI cohort, who were referred to Oita University Hospital for cognitive decline, consisted of 90 adults with MCI. The community-based MCI cohort, which participated in a prospective cohort study, consisted of 118 adults with MCI. Participants underwent cognitive function evaluation, 11C-Pittsburgh compound B (PiB)-PET, and 18F-fluorodeoxyglucose (FDG)-PET. The prevalence of amyloid positivity and mean PiB and FDG uptake values were compared between the cohorts. Moreover, a voxel-by-voxel group study was performed to determine the areas with significant differences between the clinic- and community-based MCI cohorts. RESULTS: The prevalence of amyloid positivity and mean PiB uptake value in the clinic-based MCI cohort were significantly higher than those in the community-based MCI cohort (p < 0.001 and p < 0.001, respectively). The mean FDG uptake value in the clinic-based MCI cohort was significantly lower than that in the community-based MCI cohort (p < 0.001). SPM 8 analysis showed significantly increased PiB uptake in the precuneus and parietotemporal lobe and significantly decreased FDG uptake in the posterior cingulate in the clinic-based MCI cohort compared to the community-based MCI cohort. CONCLUSION: The prevalence and severity of amyloid pathology in older adults with MCI varied depending on the recruitment source.

A Case of Miller Fisher Syndrome with Cerebellar Hypoperfusion.

We report a case of a 76-year-old man with Miller Fisher syndrome presenting with acute ophthalmoplegia and ataxia. Cerebrospinal fluid analysis showed normocytosis with an increased protein level. Serum anti-GQ1b IgG and anti-GT1a IgG antibodies were positive. Based on these results, the patient was diagnosed with Miller Fisher syndrome. He was treated with two courses of intravenous immunoglobulin, which improved his neurological symptoms. Brain perfusion single-photon emission computed tomography showed that cerebellar blood flow was decreased in the acute stage of the disease and improved after treatment. Although the prevailing view is that ataxia in Miller Fisher syndrome patients is of a peripheral origin, this case suggests that cerebellar hypoperfusion contributes to the development of ataxia in Miller Fisher syndrome.

Relationship between Cerebrospinal Fluid Matrix Metalloproteinases Levels and Brain Amyloid Deposition in Mild Cognitive Impairment.

This study aimed to explore whether cerebrospinal fluid (CSF) levels of matrix metalloproteinases (MMPs), and their inhibitors (TIMPs) were associated with brain amyloid deposition, cortical glucose metabolism, and white matter lesions (WMLs) in individuals with amnestic mild cognitive impairment (MCI). A total of 33 individuals with amnestic MCI (mean age, 75.6 years) underwent 11C-Pittsburgh compound B positron emission tomography (PiB-PET), 18F-fluorodeoxyglucose positron emission tomography, magnetic resonance imaging or computed tomography, and CSF analysis. PET uptake of the frontal and temporoparietal lobes and posterior cingulate gyrus was assessed using the cerebellar cortex as the reference region. WMLs were assessed by the Fazekas scale. CSF levels of MMPs and TIMPs were measured with bead-based multiplex assays. After adjusting for covariates, multiple linear regression analysis showed that CSF levels of MMP-2 were negatively correlated with global PiB uptake (p = 0.035), especially in the parietotemporal lobe and posterior cingulate gyrus (p = 0.016 and p = 0.041, respectively). Moreover, CSF levels of MMP-7 were positively correlated with the severity of WMLs (p = 0.033). CSF levels of MMP-2 and MMP-7 are associated with brain amyloid deposition and severity of WMLs, respectively. These findings provide valuable insights into the role of MMPs in amyloid ß catabolism and blood-brain barrier integration at the MCI stage.

Association between objectively measured walking steps and sleep in community-dwelling older adults: A prospective cohort study.

Physical inactivity and sleep disturbances are major problems in an ageing society. There is increasing evidence that physical activity is associated with sleep quality. However, the association between daily walking steps and sleep remain unclear. This prospective study examined the relationship between objectively measured daily walking steps and sleep parameters in Japanese community-dwelling older adults. In total, 855 community-dwelling individuals aged 65 and above, with an uninterrupted follow-up from August 2015 to March 2016, were enrolled. The participants wore a wristband sensor for an average of 7.8 days every three months. Multiple linear regression analysis was performed to examine the relationship between daily walking steps and sleep parameters, including the total sleep time, sleep efficiency, time awake after sleep onset (WASO), awakening time count during the night, and naptime. The median (interquartile range, IQR) age of the participants was 73 (69-78) years, with 317 (37.1%) men and 538 (62.9%) women. The median (IQR) educational level was 12 (11-12) years, and the median (IQR) Mini-Mental State Examination score was 29 (27-30) points. The number of daily walking steps showed a positive correlation with sleep efficiency and an inverse correlation with WASO, awakening time count, and naptime, after adjusting for covariates and correcting for the false discovery rate (ß = 0.098, 95% confidence interval [CI]: 0.034 to 0.162, p = 0.003; ß = -0.107, 95% CI: -0.172 to -0.043, p = 0.001; ß = -0.105, 95% CI: -0.17 to -0.04, p = 0.002; and ß = -0.31, 95% CI: -0.371 to -0.249, p < 0.001, respectively). Our results can help promote walking as an intervention for preventing sleep disturbances in community-dwelling older adults.

Association of Modifiable Lifestyle Factors With Cortical Amyloid Burden and Cerebral Glucose Metabolism in Older Adults With Mild Cognitive Impairment.

Importance: Understanding the association of lifestyle factors with mild cognitive impairment enables the development of evidence-based interventions for delaying cognitive impairment. Objective: To explore whether objectively measured lifestyle factors, such as physical activity, conversation, and sleep, are associated with cortical amyloid burden and cerebral glucose metabolism in older adults with mild cognitive impairment. Design, Setting, and Participants: This cohort study included 855 community-dwelling adults in Usuki, Oita Prefecture, Japan, aged 65 years or older. Data were collected from August 2015 to December 2017. Participants were reviewed to examine risk and protective lifestyle factors for dementia. Data analysis was conducted in June 2019. Exposures: Wearable sensors, carbon-11 labeled Pittsburgh compound B positron emission tomography images, and fluorine-18 fluorodeoxyglucose positron emission tomography images. Main Outcomes and Measures: Wearable sensor data, such as walking steps, conversation time, and sleep, were collected from August 2015 to October 2017, and positron emission tomography images were collected from October 2015 to December 2017. A multiple regression model and change-point regression model were used to examine the association of lifestyle factors with mean amyloid or fluorodeoxyglucose uptake, assessed on the basis of a standardized uptake value ratio of the frontal lobes, temporoparietal lobes, and posterior cingulate gyrus with the cerebellar cortex as the reference region. The bootstrap method was used to obtain nonparametric 95% CIs on the associations of lifestyle factors with cognitive decline. Results: Of the 855 adults in the study, 118 (13.8%) were diagnosed with mild cognitive impairment, with a mean (SD) age of 75.7 (5.8) years and 66 (55.9%) women. Total sleep time was inversely associated with fluorodeoxyglucose uptake after adjusting for covariates (ß = -0.287; 95% CI, -0.452 to -0.121, P < .001). Change-point regression showed an inverse association between total sleep time and mean amyloid uptake when sleep duration was longer than 325 minutes (B = -0.0018; 95% CI, -0.0031 to -0.0007). Conclusions and Relevance: To our knowledge, this is the first study to demonstrate that total sleep time was associated with brain function in older adults with mild cognitive impairment. Sleep duration is a potentially modifiable risk factor for dementia at the mild cognitive impairment stage.

Relationship Between the Japanese Version of the Montreal Cognitive Assessment and PET Imaging in Subjects with Mild Cognitive Impairment.

BACKGROUND: The Montreal Cognitive Assessment (MoCA) test has high sensitivity and specificity for detecting mild cognitive impairment or early dementia. How the MoCA score relates to findings of positron emission tomography imaging, however, remains unclear. OBJECTIVE: This prospective study examined the relationship between the Japanese version of the MoCA (MoCA-J) test and brain amyloid deposition or cerebral glucose metabolism among subjects with mild cognitive impairment. METHODS: A total of 125 subjects with mild cognitive impairment underwent the MoCA-J test, and amyloid- and 18F-fluorodeoxyglucose- positron emission tomography. Linear correlation analysis and multiple linear regression analysis were conducted to investigate the relationship between the MoCA-J score and demographic characteristics, amyloid deposition, and cerebral glucose metabolism. Moreover, Statistical Parametric Mapping 8 was used for a voxel-wise regression analysis of the MoCA-J score and cerebral glucose metabolism. RESULTS: The MoCA-J score significantly correlated with age, years of education, and the Mini-Mental State Examination score. After adjusting for age, sex, and education, the MoCA-J score significantly correlated negatively with amyloid retention (ß= -0.174, p= 0.031) and positively with cerebral glucose metabolism (ß= 0.183, p= 0.044). Statistical Parametric Mapping showed that Japanese version of MoCA score correlated with glucose metabolism in the bilateral frontal and parietal lobes, and the left precuneus. CONCLUSION: The total MoCA-J score correlated with amyloid deposition and frontal and parietal glucose metabolism in subjects with mild cognitive impairment. Our findings support the usefulness of the MoCA-J test for screening subjects at high risk for Alzheimer's disease.

Modifiable Lifestyle Factors and Cognitive Function in Older People: A Cross-Sectional Observational Study.

Background: The development of evidence-based interventions for delaying or preventing cognitive impairment is an important challenge. Most previous studies using self-report questionnaires face problems with reliability and consistency due to recall bias or misclassification among older people. Therefore, objective measurement of lifestyle components is needed to confirm the relationships between lifestyle factors and cognitive function. Aims: The current study examined the relationship between lifestyle factors collected with wearable sensors and cognitive function among community-dwelling older people using machine learning. Methods: In total, 855 participants (mean age: 73.8 years) wore a wristband sensor for 7.8 days on average every 3 months. Various lifestyle parameters were measured, including walking steps, conversation time, total sleep time (TST), sleep efficiency, time awake after sleep onset, awakening count, napping time, and heart rate. Random forest (RF) regression analysis was used to examine the relationships between total daily sensing data and Mini-Mental State Examination (MMSE) scores. Confounding factor analysis was conducted with models that were adjusted and unadjusted for demographic and vascular risk factors, and selected variables were assessed as risk and protective factors using partial dependence plots (PDPs). Results: Lifestyle data were collected for 31.3 ± 7.1 days per year using wristband sensors. RF regression analysis adjusted for age, gender, and education levels selected four variables, including number of walking steps, conversation time, TST, and heart rate. Moreover, walking steps, conversation time, and heart rate remained after RF regression analysis adjusted for demographic and vascular risk factors. Number of walking steps, conversation time, and heart rate were categorized as protective factors, whereas TST was categorized as a risk factor for cognitive function. Although PDPs of number of walking steps and heart rate revealed continuously increased MMSE scores, those of conversation time and TST and revealed that the tendency in the graph was reversed at the boundary of a particular threshold (321.1 min for conversation time, 434.1 min for TST). Conclusions: Lifestyle factors, such as physical activity, sleep, and social activity appear to be associated with cognitive function among older people. Physical activity and appropriate durations of sleep and conversation are important for cognitive function.

Reversal of methamphetamine-induced behavioral sensitization by repeated administration of a dopamine D1 receptor agonist.

Repeated intermittent administration of methamphetamine (MAP) produces an enduring hypersensitivity to the motor stimulant effect of MAP, termed behavioral sensitization. Dopamine plays a critical role in the development and expression of behavioral sensitization. Here, we investigated whether a dopamine D1 receptor agonist could reverse behavioral sensitization to MAP. Administration of MAP (1.0 mg/kg, i.p.) to rats once every 3 days for a total of 5 times (days 1-13) induced the enhancement of locomotor activity after MAP challenge (0.5 mg/kg, i.p.) on day 20, verifying the development of behavioral sensitization. The MAP-sensitized rats then received a dopamine D1 agonist, R-(+)-SKF38393 (3.0 mg/kg, i.p.), once a day for 7 consecutive days (days 21-27). Behavioral analysis on days 30 and 41 revealed that the enhanced locomotor activity was reversed by repeated R-(+)-SKF38393 administration. Moreover, repeated R-(+)-SKF38393 administration reversed the increased dopamine release in the striatum after MAP challenge on day 41. Thus, repeated administration of the dopamine D1 receptor agonist induces the reversal of established behavioral sensitization to MAP and of increased dopamine release in the striatum, lasting for at least 2 weeks. Dopamine D1 receptor agonists may be useful therapeutic agents for the treatment of psychostimulant addiction.