Deep-gated recurrent unit and diet network-based genome-wide association analysis for detecting the biomarkers of Alzheimer's disease.

Genome-wide association analysis (GWAS) is a commonly used method to detect the potential biomarkers of Alzheimer's disease (AD). Most existing GWAS methods entail a high computational cost, disregard correlations among imaging data and correlations among genetic data, and ignore various associations between longitudinal imaging and genetic data. A novel GWAS method was proposed to identify potential AD biomarkers and address these problems. A network based on a gated recurrent unit was applied without imputing incomplete longitudinal imaging data to integrate the longitudinal data of variable lengths and extract an image representation. In this study, a modified diet network that can considerably reduce the number of parameters in the genetic network was proposed to perform GWAS between image representation and genetic data. Genetic representation can be extracted in this way. A link between genetic representation and AD was established to detect potential AD biomarkers. The proposed method was tested on a set of simulated data and a real AD dataset. Results of the simulated data showed that the proposed method can accurately detect relevant biomarkers. Moreover, the results of real AD dataset showed that the proposed method can detect some new risk-related genes of AD. Based on previous reports, no research has incorporated a deep-learning model into a GWAS framework to investigate the potential information on super-high-dimensional genetic data and longitudinal imaging data and create a link between imaging genetics and AD for detecting potential AD biomarkers. Therefore, the proposed method may provide new insights into the underlying pathological mechanism of AD.

Imaging Genetics Study Based on a Temporal Group Sparse Regression and Additive Model for Biomarker Detection of Alzheimer's Disease.

Imaging genetics is an effective tool used to detect potential biomarkers of Alzheimer's disease (AD) in imaging and genetic data. Most existing imaging genetics methods analyze the association between brain imaging quantitative traits (QTs) and genetic data [e.g., single nucleotide polymorphism (SNP)] by using a linear model, ignoring correlations between a set of QTs and SNP groups, and disregarding the varied associations between longitudinal imaging QTs and SNPs. To solve these problems, we propose a novel temporal group sparsity regression and additive model (T-GSRAM) to identify associations between longitudinal imaging QTs and SNPs for detection of potential AD biomarkers. We first construct a nonparametric regression model to analyze the nonlinear association between QTs and SNPs, which can accurately model the complex influence of SNPs on QTs. We then use longitudinal QTs to identify the trajectory of imaging genetic patterns over time. Moreover, the SNP information of group and individual levels are incorporated into the proposed method to boost the power of biomarker detection. Finally, we propose an efficient algorithm to solve the whole T-GSRAM model. We evaluated our method using simulation data and real data obtained from AD neuroimaging initiative. Experimental results show that our proposed method outperforms several state-of-the-art methods in terms of the receiver operating characteristic curves and area under the curve. Moreover, the detection of AD-related genes and QTs has been confirmed in previous studies, thereby further verifying the effectiveness of our approach and helping understand the genetic basis over time during disease progression.

Differentiation of Recurrence from Radiation Necrosis in Gliomas Based on the Radiomics of Combinational Features and Multimodality MRI Images.

PURPOSE: To classify radiation necrosis versus recurrence in glioma patients using a radiomics model based on combinational features and multimodality MRI images. METHODS: Fifty-one glioma patients who underwent radiation treatments after surgery were enrolled in this study. Sixteen patients revealed radiation necrosis while 35 patients showed tumor recurrence during the follow-up period. After treatment, all patients underwent T1-weighted, T1-weighted postcontrast, T2-weighted, and fluid-attenuated inversion recovery scans. A total of 41,284 handcrafted and 24,576 deep features were extracted for each patient. The 0.623 + bootstrap method and the area under the curve (denoted as 0.632 + bootstrap AUC) metric were used to select the features. The stepwise forward method was applied to construct 10 logistic regression models based on different combinations of image features. RESULTS: For handcrafted features on multimodality MRI, model 7 with seven features yielded the highest AUC of 0.9624, sensitivity of 0.8497, and specificity of 0.9083 in the validation set. These values were higher than the accuracy of using handcrafted features on single-modality MRI (paired t-test, p < 0.05, except sensitivity). For combined handcrafted and AlexNet features on multimodality MRI, model 6 with six features achieved the highest AUC of 0.9982, sensitivity of 0.9941, and specificity of 0.9755 in the validation set. These values were higher than the accuracy of using handcrafted features on multimodality MRI (paired t-test, p < 0.05). CONCLUSIONS: Handcrafted and deep features extracted from multimodality MRI images reflecting the heterogeneity of gliomas can provide useful information for glioma necrosis/recurrence classification.

Incorporating spatial-anatomical similarity into the VGWAS framework for AD biomarker detection.

MOTIVATION: The detection of potential biomarkers of Alzheimer's disease (AD) is crucial for its early prediction, diagnosis and treatment. Voxel-wise genome-wide association study (VGWAS) is a commonly used method in imaging genomics and usually applied to detect AD biomarkers in imaging and genetic data. However, existing VGWAS methods entail large computational cost and disregard spatial correlations within imaging data. A novel method is proposed to solve these issues. RESULTS: We introduce a novel method to incorporate spatial correlations into a VGWAS framework for the detection of potential AD biomarkers. To consider the characteristics of AD, we first present a modification of a simple linear iterative clustering method for spatial grouping in an anatomically meaningful manner. Second, we propose a spatial-anatomical similarity matrix to incorporate correlations among voxels. Finally, we detect the potential AD biomarkers from imaging and genetic data by using a fast VGWAS method and test our method on 708 subjects obtained from an Alzheimer's Disease Neuroimaging Initiative dataset. Results show that our method can successfully detect some new risk genes and clusters of AD. The detected imaging and genetic biomarkers are used as predictors to classify AD/normal control subjects, and a high accuracy of AD/normal control classification is achieved. To the best of our knowledge, the association between imaging and genetic data has yet to be systematically investigated while building statistical models for classifying AD subjects to create a link between imaging genetics and AD. Therefore, our method may provide a new way to gain insights into the underlying pathological mechanism of AD. AVAILABILITY AND IMPLEMENTATION: https://github.com/Meiyan88/SASM-VGWAS.

Epidemiologic study of pterygium in Taiwan.

PURPOSE: To investigate the incidence, prevalence, and factors related to pterygium in Taiwan. STUDY DESIGN: An ecological study METHODS: We analyzed a random sample of 1 million individuals in Taiwan drawn from the National Health Insurance Database (NHIRD), established in 2005, for the period 2000 to 2011. Patients with pterygium were identified using ICD-9-CM diagnostic codes. The prevalence and annual age- and gender-adjusted incidence of pterygium were calculated for each county in Taiwan. The risk factors including ultraviolet (UV) exposure, outdoor occupation, educational level, and average socioeconomic status of each county of each index year were identified. Univariate and backward elimination multivariate selection by the mixed-effects model were performed to identify significant risk factors related to the incidence of pterygium in Taiwan. RESULTS: A total of 22,063 individuals with pterygium (10,125 men and 11,938 women) were identified in this study. The prevalence of pterygium was 2.14% in the overall population and 3.48% in the population aged 40 years or older. The occurrence of pterygium was greater in women. In addition, this study demonstrated that UV exposure and low educational level are correlated with the age- and gender-adjusted incidence of pterygium. CONCLUSION: Our study is the first to use the NHIRD to determine the prevalence (2.14%) and annual age- and gender-adjusted incidence of pterygium among the general population of Taiwan. The relationship of pterygium with UV exposure and educational level suggests a complex and multifactorial etiology for this disease.

Spatial correlations exploitation based on nonlocal voxel-wise GWAS for biomarker detection of AD.

Potential biomarker detection is a crucial area of study for the prediction, diagnosis, and monitoring of Alzheimer's disease (AD). The voxelwise genome-wide association study (vGWAS) is widely used in imaging genomics studies that is usually applied to the detection of AD biomarkers in both imaging and genetic data. However, performing vGWAS remains a challenge because of the computational complexity of the technique and our ignorance of the spatial correlations within the imaging data. In this paper, we propose a novel method based on the exploitation of spatial correlations that may help to detect potential AD biomarkers using a fast vGWAS. To incorporate spatial correlations, we applied a nonlocal method that supposed that a given voxel could be represented by weighting the sum of the other voxels. Three commonly used weighting methods were adopted to calculate the weights among different voxels in this study. Then, a fast vGWAS approach was used to assess the association between the image and the genetic data. The proposed method was estimated using both simulated and real data. In the simulation studies, we designed a set of experiments to evaluate the effectiveness of the nonlocal method for incorporating spatial correlations in vGWAS. The experiments showed that incorporating spatial correlations by the nonlocal method could improve the detecting accuracy of AD biomarkers. For real data, we successfully identified three genes, namely, ANK3, MEIS2, and TLR4, which have significant associations with mental retardation, learning disabilities and age according to previous research. These genes have profound impacts on AD or other neurodegenerative diseases. Our results indicated that our method might be an effective and valuable tool for detecting potential biomarkers of AD.

Risk factor for first-incident hip fracture in Taiwanese postmenopausal women.

OBJECTIVE: The variation in hip fracture risk between countries is greater than 10-fold. The present study aimed at identifying risk factors that resulted in the first occurrence of hip fracture in Taiwanese postmenopausal women. MATERIALS AND METHODS: A case-control study with a patient group of 50 postmenopausal women, who were admitted to Keelung Chang Gung Hospital, Keelung, Taiwan due to the first incident of accidental hip fracture, was used to examine potential risk factors, including bone mass. Fifty women without hip fracture, selected from those undergoing general health evaluation at the Gynecology Outpatient Clinic at Keelung Chang Gung Hospital, were used as the control group and were matched to the case patients according to age. Evaluation consisted of a questionnaire, interview to document risk factors, physical examination (to record body height and body weight), and examination [dual-energy X-ray absorptiometry used to measure bone mineral density (BMD) of the hip and spine]. RESULTS: The average age of participants of both groups was 79.6 years. Lower level of education, younger age at menopause, increased body height, weight-bearing exercise less than three times per week, and lower BMD were associated with first-incident hip fracture. Total hip BMD was a stronger predictor than the BMD of different sites. Participants in the control group had a significantly higher prevalence of chronic diseases and a history of cataracts or glaucoma compared with those in the patient group. CONCLUSION: While total hip BMD is the strongest predictor of hip fracture, increasing awareness of osteoporosis prevention by educating people about good lifestyle habits and how to maintain BMD is prioritized for preventing the first-incident hip fracture in Taiwanese women.

Effects of Antiplatelet Medication on Arteriovenous Fistula Patency After Surgical Thrombectomy.

OBJECTIVES: To study the effect of antiplatelet agents on preventing arteriovenous (AV) fistulae thrombosis in hemodialysis (HD) patients after surgical thrombectomy (ST) for acute AV fistulae occlusion. Whether post-operative antiplatelet drugs have similar effects on the patency of AV fistula after surgical thrombectomy in patients with end-stage renal disease who undergo HD has not been investigated. DESIGN, MATERIALS AND METHODS: We employed the Taiwan National Health Insurance Research Database (NHIRD) from 1999 to 2010 to assess the recurrent occlusion requiring ST and longevity of AV fistula after ST in 1049 patients on regular HD, with or without antiplatelet drugs. RESULTS: From the propensity-score (PS)-matched NHIRD, Multivariate Cox model demonstrated that concomitant antiplatelet medication in the HD patients who received the first ST significantly reduced the duration of recurrent ST (adjusted hazard ratio (HR) 1.69; 95% confidence interval (CI) 1.22-2.35, p=0.002) and the longevity of the fistula (adjusted HR 1.79; 95% CI 1.31-2.46, p<0.001). CONCLUSION: Treatment with antiplatelet drugs in HD patients did not prevent recurrent thrombosis requiring further ST, but significantly jeopardized the longevity of AV fistula after ST.

Application of the World Health Organization Fracture Risk Assessment Tool to predict need for dual-energy X-ray absorptiometry scanning in postmenopausal women.

OBJECTIVE: To evaluate the efficacy of the World Health Organization Fracture Risk Assessment Tool, excluding bone mineral density (pre-BMD FRAX), in identifying Taiwanese postmenopausal women needing dual-energy X-ray absorptiometry (DXA) examination for further treatment. MATERIALS AND METHODS: The pre-BMD FRAX score was calculated for 231 postmenopausal women who participated in public health education workshops in the local Keelung community, Taiwan. DXA scanning and vertebral fracture assessment (VFA) were arranged for women classified as intermediate or high risk for fracture using the pre-BMD FRAX fracture probability. RESULTS: Pre-BMD FRAX classified 26 women as intermediate risk and 37 as having high risk for fracture. Subsequent DXA scans for these 63 women showed that 36 were osteoporotic, 19 were osteopenic, and eight had normal bone density. Concurrent VFA revealed 25 spine factures in which 14 were osteoporotic, seven were osteopenic, and four had normal bone density. The efficacy of the pre-BMD FRAX score to identify those patients with low bone mass by DXA was 87.3% (55/63). When VFA was combined with BMD to identify those patients with high risk (osteopenia, osteoporosis, or spinal fracture), the efficacy of the pre-BMD score increased to 93.7% (59/63). According to the National Osteoporosis Foundation, the overall concordance between pre-BMD FRAX and BMD, expressed through the kappa index, was 0.967. Compared with the evaluation when BMD was used alone, there was a significant increase in efficacy in identifying women who need treatment using BMD plus VFA or FRAX plus BMD. Furthermore, the highest efficacy was achieved when FRAX with BMD and VFA was used. CONCLUSION: The pre-BMD FRAX score not only efficiently predicts postmenopausal patients who are potentially at risk and might require treatment but also reduces unnecessary DXA use. Concurrent VFA during DXA use increases spine fracture detection. This improvement in diagnostic efficacy allows clinicians to provide the most appropriate therapeutic recommendation.