Objectives: Prediabetes is a major epidemic and is associated with adverse cardio-cerebrovascular outcomes. Early identification of patients who will develop rapid progression of atherosclerosis could be beneficial for improved risk stratification. In this paper, we investigate important factors impacting the prediction, using several machine learning methods, of rapid progression of carotid intima-media thickness in impaired glucose tolerance (IGT) participants.

Methods: In the Actos Now for Prevention of Diabetes (ACT NOW) study, 382 participants with IGT underwent carotid intima-media thickness (CIMT) ultrasound evaluation at baseline and at 15–18 months, and were divided into rapid progressors (RP, n = 39, 58 ± 17.5 μM change) and non-rapid progressors (NRP, n = 343, 5.8 ± 20 μM change, p < 0.001 versus RP). To deal with complex multi-modal data consisting of demographic, clinical, and laboratory variables, we propose a general data-driven framework to investigate the ACT NOW dataset. In particular, we first employed a Fisher Score-based feature selection method to identify the most effective variables and then proposed a probabilistic Bayes-based learning method for the prediction. Comparison of the methods and factors was conducted using area under the receiver operating characteristic curve (AUC) analyses and Brier score.

Results: The experimental results show that the proposed learning methods performed well in identifying or predicting RP. Among the methods, the performance of Naïve Bayes was the best (AUC 0.797, Brier score 0.085) compared to multilayer perceptron (0.729, 0.086) and random forest (0.642, 0.10). The results also show that feature selection has a significant positive impact on the data prediction performance.

Conclusions: By dealing with multi-modal data, the proposed learning methods show effectiveness in predicting prediabetics at risk for rapid atherosclerosis progression. The proposed framework demonstrated utility in outcome prediction in a typical multidimensional clinical dataset with a relatively small number of subjects, extending the potential utility of machine learning approaches beyond extremely large-scale datasets.

Background: HDL carries a rich protein cargo and examining HDL protein composition promises to improve our understanding of its functions. Conventional mass spectrometry methods can be lengthy and difficult to extend to large populations. In addition, without prior enrichment of the sample, the ability of these methods to detect low abundance proteins is limited. Our objective was to develop a high-throughput approach to examine HDL protein composition applicable to diabetes and cardiovascular disease (CVD).

Methods: We optimized two multiplexed assays to examine HDL proteins using a quantitative immunoassay (Multi-Analyte Profiling- MAP) and mass spectrometric-based quantitative proteomics (Multiple Reaction Monitoring-MRM). We screened HDL proteins using human xMAP (90 protein panel) and MRM (56 protein panel). We extended the application of these two methods to HDL isolated from a group of participants with diabetes and prior cardiovascular events and a group of non-diabetic controls.

Results: We were able to quantitate 69 HDL proteins using MAP and 32 proteins using MRM. For several common proteins, the use of MRM and MAP was highly correlated (p < 0.01). Using MAP, several low abundance proteins implicated in atherosclerosis and inflammation were found on HDL. On the other hand, MRM allowed the examination of several HDL proteins not available by MAP.

Conclusions: MAP and MRM offer a sensitive and high-throughput approach to examine changes in HDL proteins in diabetes and CVD. This approach can be used to measure the presented HDL proteins in large clinical studies.