Predicting Risk of Alzheimer's Diseases and Related Dementias with AI Foundation Model on Electronic Health Records.

Early identification of Alzheimer's disease (AD) and AD-related dementias (ADRD) has high clinical significance, both because of the potential to slow decline through initiating FDA-approved therapies and managing modifiable risk factors, and to help persons living with dementia and their families to plan before cognitive loss makes doing so challenging. However, substantial racial and ethnic disparities in early diagnosis currently lead to additional inequities in care, urging accurate and inclusive risk assessment programs. In this study, we trained an artificial intelligence foundation model to represent the electronic health records (EHR) data with a vast cohort of 1.2 million patients within a large health system. Building upon this foundation EHR model, we developed a predictive Transformer model, named TRADE, capable of identifying risks for AD/ADRD and mild cognitive impairment (MCI), by analyzing the past sequential visit records. Amongst individuals 65 and older, our model was able to generate risk predictions for various future timeframes. On the held-out validation set, our model achieved an area under the receiver operating characteristic (AUROC) of 0.772 (95% CI: 0.770, 0.773) for identifying the AD/ADRD/MCI risks in 1 year, and AUROC of 0.735 (95% CI: 0.734, 0.736) in 5 years. The positive predictive values (PPV) in 5 years among individuals with top 1% and 5% highest estimated risks were 39.2% and 27.8%, respectively. These results demonstrate significant improvements upon the current EHR-based AD/ADRD/MCI risk assessment models, paving the way for better prognosis and management of AD/ADRD/MCI at scale.

Minimax Powerful Functional Analysis of Covariance Tests: with Application to Longitudinal Genome-Wide Association Studies.

We model the Alzheimer's Disease-related phenotype response variables observed on irregular time points in longitudinal Genome-Wide Association Studies as sparse functional data and propose nonparametric test procedures to detect functional genotype effects while controlling the confounding effects of environmental covariates. Our new functional analysis of covariance tests are based on a seemingly unrelated kernel smoother, which takes into account the within-subject temporal correlations, and thus enjoy improved power over existing functional tests. We show that the proposed test combined with a uniformly consistent nonparametric covariance function estimator enjoys the Wilks phenomenon and is minimax most powerful. Data used in the preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, where an application of the proposed test lead to the discovery of new genes that may be related to Alzheimer's Disease.

Generalizable deep learning model for early Alzheimer's disease detection from structural MRIs.

Early diagnosis of Alzheimer's disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer's disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer's dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer's disease dementia by the model were faster to progress to dementia over time. An analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.

Associations of Resistance Exercise with Cardiovascular Disease Morbidity and Mortality.

PURPOSE: Resistance exercise (RE) can improve many cardiovascular disease (CVD) risk factors, but specific data on the effects on CVD events and mortality are lacking. We investigated the associations of RE with CVD and all-cause mortality and further examined the mediation effect of body mass index (BMI) between RE and CVD outcomes. METHODS: We included 12,591 participants (mean age, 47 yr) who received at least two clinical examinations 1987-2006. RE was assessed by a self-reported medical history questionnaire. RESULTS: During a mean follow-up of 5.4 and 10.5 yr, 205 total CVD events (morbidity and mortality combined) and 276 all-cause deaths occurred, respectively. Compared with no RE, weekly RE frequencies of one, two, three times or total amount of 1-59 min were associated with approximately 40%-70% decreased risk of total CVD events, independent of aerobic exercise (AE) (all P values <0.05). However, there was no significant risk reduction for higher weekly RE of more than four times or ≥60 min. Similar results were observed for CVD morbidity and all-cause mortality. In the stratified analyses by AE, weekly RE of one time or 1-59 min was associated with lower risks of total CVD events and CVD morbidity regardless of meeting the AE guidelines. Our mediation analysis showed that RE was associated with the risk of total CVD events in two ways: RE had a direct U-shaped association with CVD risk (P value for quadratic trend <0.001) and RE indirectly lowered CVD risk by decreasing BMI. CONCLUSION: Even one time or less than 1 h·wk of RE, independent of AE, is associated with reduced risks of CVD and all-cause mortality. BMI mediates the association of RE with total CVD events.

A new approach for Alzheimer's disease treatment through P-gp regulation via ibuprofen.

This study was aimed to investigate whether ibuprofen could alter the P-glycoprotein expression and function under Alzheimer's Disease condition and whether this alteration was induced by the inhibition of inflammatory reaction. APP/PS1 mice were used as AD model mice and ibuprofen-treated AD mice were given ibuprofen for 5 months. Then, Abcb1a/1b mRNA levels and P-gp expression were evaluated by qRT-PCR and western blot. Abcb1 mRNA levels were significantly reduced in AD mice compared to control mice, and it could be restored by ibuprofen treatment. Meanwhile, P-gp expression result showed a similar trend. Aß plaques in cerebral cortices and hippocampus were investigated via immunohistochemical, and the results revealed that Aß plaques were reduced in ibuprofen-treated AD mice compared with the AD mice, indicated that P-gp function may be recovered by ibuprofen treatment. qRT-PCR and ELISA were used to determined TNF-α, IL-1ß, IL-6 and NF-κB levels. The results demonstrated that TNF-α, IL-1ß mRNA levels and NF-κB expression were all significantly upregulated in AD mice in comparison with the control mice, and ibuprofen treatment could suppress the increase of inflammatory factors. In conclusion, the P-gp expression and function were suppressed in AD condition by activating inflammatory reaction, and then causing the Aß efflux decreased. However, upregulating P-gp could increase the Aß efflux in further to treat AD via inhibiting the inflammatory factors expression.

[Survey on newly-developed advanced schistosomiasis patients in schistosomiasis transmission-interrupted areas].

OBJECTIVE: To understand the status of newly-developed advanced schistosomiasis patients in schistosome transmission-interrupted areas. METHODS: The newly diagnosed advanced schistosomiasis patients confirmed by professionals at province and county levels according to the available standards were investigated. Their detailed epidemiology history and present signs/ symptoms were surveyed, and the relevant medical examinations were performed. RESULTS: There were 75 patients including 22 males and 53 females. The average age was (70.0 +/- 7.0) years and they were all infected with schistosome previously. They received anti-schistosome therapy (mean 1.85 times) and stool examinations (mean 26.24 times) continuously from 1976 to 1985, and the results of stool examination were all negative. In majority of the patients' resident areas, the last time that Oncomelania hupensis snails were found was 1976, and the latest was 1983. During this period, no patients were up to the diagnostic criteria of advanced schistosomiasis after multiple examinations, and they were diagnosed as advanced cases between 2008 and 2011. The survey indicated that liver fibrosis was found in all the patients with 82.7% showing grad III pathological change, 90.7% of them had splenomegaly, 20.0% had ascites, and 22.7% had portal vein broadening. The mean value of enzyme indexes of liver function was 31.81 U/L (ALT), 53.19 U/L (AST) and 89.28 U/L (gamma-GT), and the positive rate was 21.3%, 49.3% and 57.3%, respectively. As for the fibrosis indexes, the positive rate of HA, LN, C VI and P III P was 73.3%, 13.3%, 17.3% and 9.3%, respectively, and the mean value of HA was 3 times higher than that of the upper limit of normal standard. Conclusions Newly-developed advanced schistosomiasis patients are those who were dignosed and cured parasitologically but progressed pathologically without any chance of re-infection. Anti-fibrosis therapy is necessary as the patients show considerable progressive liver fibrosis.

[Pollen viability and stigma receptivity of Cistanche deserticola].

OBJECTIVE: To study the characteristics of pollen viability and stigma receptivity of C. deserticola and provide theory basis for seed production and breeding of C. deserticola. METHOD: Different physiological measurement methods were applied to evaluate pollen viability and stigma receptivity. The results of different methods were compared with the seed setting percentage of the cross-pollination in the field test and pollen germination percentage by fluoroscope observation methods. The changes of pollen vitality and stigma receptivity in different conditions were tested using proper methods. RESULT: The optimum methods on pollen viability and stigma receptivity detection were MTT-test and Benzidine-Hydrogen Peroxide method respectively. Results showed that the mean pollen viability and stigma receptivity were both the highest in inchoate anthesis with pollen germination percentage up to 95%, and can maintain viable for 4-5 d, but at the lower temperature of 4 degrees C, the pollen can be stored up to 10 days. CONCLUSION: The physiological characteristics of pollen and stigma of C. deserticola displayed good ecological adaptation, which are much more adaptive to the large area of cultivation condition.

Improvement in dielectric and tunable properties of Fe-doped Ba0.6Sr0.4TiO3 thin films grown by pulsed-laser deposition.

Fe-doped Ba(0.6)Sr(0.4)TiO3 (BST) thin films were prepared on Pt/Si substrates by the pulsed-laser deposition method. The concentrations of Fe dopants vary from 0.1 mol% to 1.0 mol%. Our results indicate that a certain amount of Fe dopants can decrease the dielectric loss of BST thin films without causing the significant reduction of the tunability. The leakage current of BST thin films also was reduced by the addition of Fe dopants. BST thin films doped with 0.3 mol% Fe ions show a minimum dielectric loss of 0.88% at 10(6) Hz, which is 1.7% for the undoped BST films. Moreover, the 0.3 mol% Fe-doped BST films reveal a maximum figure of merit (FOM) of 51, indicating the improved comprehensive dielectric and tunable properties.