Predicting progression of mild cognitive impairment (MCI) to Alzheimer’s disease (AD) is clinically important. In this study, we propose a dual-model radiomic analysis with multivariate Cox proportional hazards regression models to investigate promising risk factors associated with MCI conversion to AD. T1 structural magnetic resonance imaging (MRI) and 18F-Fluorodeoxyglucose (FDG) positron emission tomography (PET) data, from the AD Neuroimaging Initiative database, were collected from 131 patients with MCI who converted to AD within 3 years and 132 patients with MCI without conversion within 3 years. These subjects were randomly partition into 70% training dataset and 30% test dataset with multiple times. We fused MRI and PET images by wavelet method. In a subset of subjects, a group comparison was performed using a two-sample t-test to determine regions of interest (ROIs) associated with MCI conversion. 172 radiomic features from ROIs for each individual were established using a published radiomics tool. Finally, L1-penalized Cox model was constructed and Harrell’s C index (C-index) was used to evaluate prediction accuracy of the model. To evaluate the efficacy of our proposed method, we used a same analysis framework to evaluate MRI and PET data separately. We constructed prognostic Cox models with: clinical data, MRI images, PET images, fused MRI/PET images, and clinical variables and fused MRI/PET images in combination. The experimental results showed that captured ROIs significantly associated with conversion to AD, such as gray matter atrophy in the bilateral hippocampus and hypometabolism in the temporoparietal cortex. Imaging model (MRI/PET/fused) provided significant enhancement in prediction of conversion compared to clinical models, especially the fused-modality Cox model. Moreover, the combination of fused-modality imaging and clinical variables resulted in the greatest accuracy of prediction. The average C-index for the clinical/MRI/PET/fused/combined model in the test dataset was 0.69, 0.73, 0.73 and 0.75, and 0.78, respectively. These results suggested that a combination of radiomic analysis and Cox model analyses could be used successfully in survival analysis and may be powerful tools for personalized precision medicine patients with potential to undergo conversion from MCI to AD.

No abstract

With rapidly growing amount of data available on the web, it becomes increasingly likely to obtain data from different perspectives for multi-view learning. Some successive examples of web applications include recommendation and target advertising. Specifically, to predict whether a user will click an ad in a query context, there are available features extracted from user profile, ad information and query description, and each of them can only capture part of the task signals from a particular aspect/view. Different views provide complementary information to learn a practical model for these applications. Therefore, an effective integration of the multi-view information is critical to facilitate the learning performance.In this paper, we propose a general predictor, named multiview machines (MVMs), that can effectively explore the full-order interactions between features from multiple views. A joint factorization is applied for the interaction parameters which makes parameter estimation more accurate under sparsity and renders the model with the capacity to avoid overfitting. Moreover, MVMs can work in conjunction with different loss functions for a variety of machine learning tasks. The advantages of MVMs are illustrated through comparison with other methods for multi-view prediction, including support vector machines (SVMs), support tensor machines (STMs) and factorization machines (FMs).A stochastic gradient descent method and a distributed implementation on Spark are presented to learn the MVM model. Through empirical studies on two real-world web application datasets, we demonstrate the effectiveness of MVMs on modeling feature interactions in multi-view data. A 3.51% accuracy improvement is shown on MVMs over FMs for the problem of movie rating prediction, and 0.57% for ad click prediction.

Performance tuning for data centers is essential and complicated. It is important since a data center comprises thousands of machines and thus a single-digit performance improvement can significantly reduce cost and power consumption. Unfortunately, it is extremely difficult as data centers are dynamic environments where applications are frequently released and servers are continually upgraded.In this paper, we study the effectiveness of different processor prefetch configurations, which can greatly influence the performance of memory system and the overall data center. We observe a wide performance gap when comparing the worst and best configurations, from 1.4% to 75.1%, for 11 important data center applications. We then develop a tuning framework which attempts to predict the optimal configuration based on hardware performance counters. The framework achieves performance within 1% of the best performance of any single configuration for the same set of applications.

No abstract