Javier Ramos

Prediabetes is a type of hyperglycemia in which patients have blood glucose levels above normal but below the threshold for type 2 diabetes mellitus (T2DM). Prediabetic patients are considered to be at high risk for developing T2DM, but not all will eventually do so. Because it is difficult to identify which patients have an increased risk of developing T2DM, we developed a model of several clinical and laboratory features to predict the development of T2DM within a 2-year period. We used a supervised machine learning algorithm to identify at-risk patients from among 1647 obese, hypertensive patients. The study period began in 2005 and ended in 2018. We constrained data up to 2 years before the development of T2DM. Then, using a time series analysis with the features of every patient, we calculated one linear regression line and one slope per feature. Features were then included in a K-nearest neighbors classification model. Feature importance was assessed using the random forest algorithm. The K-nearest neighbors model accurately classified patients in 96% of cases, with a sensitivity of 99%, specificity of 78%, positive predictive value of 96%, and negative predictive value of 94%. The random forest algorithm selected the homeostatic model assessment–estimated insulin resistance, insulin levels, and body mass index as the most important factors, which in combination with KNN had an accuracy of 99% with a sensitivity of 99% and specificity of 97%. We built a prognostic model that accurately identified obese, hypertensive patients at risk for developing T2DM within a 2-year period. Clinicians may use machine learning approaches to better assess risk for T2DM and better manage hypertensive patients. Machine learning algorithms may help health care providers make more informed decisions.

Many indices have been proposed for cardiovascular risk stratification from electrocardiogram signal processing, still with limited use in clinical practice. We created a system integrating the clinical definition of cardiac risk subdomains from ECGs and the use of diverse signal processing techniques. Three subdomains were defined from the joint analysis of the technical and clinical viewpoints. One subdomain was devoted to demographic and clinical data. The other two subdomains were intended to obtain widely defined risk indices from ECG monitoring: a simple-domain (heart rate turbulence (HRT)), and a complex-domain (heart rate variability (HRV)). Data provided by the three subdomains allowed for the generation of alerts with different intensity and nature, as well as for the grouping and scrutinization of patients according to the established processing and risk-thresholding criteria. The implemented system was tested by connecting data from real-world in-hospital electronic health records and ECG monitoring by considering standards for syntactic (HL7 messages) and semantic interoperability (archetypes based on CEN/ISO EN13606 and SNOMED-CT). The system was able to provide risk indices and to generate alerts in the health records to support decision-making. Overall, the system allows for the agile interaction of research and clinical practice in the Holter-ECG-based cardiac risk domain.

Calculating the estimated glomerular filtration rate (eGFR) using creatinine-based equations may underestimate cardiovascular risk. Cystatin C-based eGFR may be a stronger prognostic biomarker than creatinine-based eGFR when assessing cardiovascular outcomes and mortality. Our aim was to determine whether levels of serum cystatin C, as an estimator of GFR, had a higher predictive value than creatinine-based eGFR for incident cardiovascular disease among hypertensive patients. We retrospectively analyzed the records of 2016 hypertensive patients from the Hypertension Unit at Mostoles University Hospital between 2006 and 2016. We calculated the eGFR using 3 CKD-EPI equations. The outcomes we included in our study were cardiovascular death, non-cardiovascular death, stroke, incident heart failure, and myocardial infarction. We used the Cox regression hazard model to estimate the hazard ratio. Our analysis found that, in terms of cardiovascular morbidity and mortality, both cystatin C-based eGFR (HR 2.88, 95% CI 1.86–4.47, PPPP<0.0001). Our findings suggest that both cystatin C-based eGFRs may be stronger predictors of all-cause mortality and cardiovascular events in our hypertensive cohort when compared to creatinine-based eGFR, and may improve the risk assessment in certain populations.

Energy efficiency has been a leading issue in Wireless Sensor Networks (WSNs) and has produced a vast amount of research. Although the classic tradeoff has been between the quality of gathered data versus the lifetime of the network, most works gave preference to an increased network lifetime at the expense of the data quality. A common approach for energy efficiency is partitioning the network into clusters with correlated data, where the representative nodes simply transmit or average measurements inside the cluster. In this paper, we explore the joint use of in-network processing techniques and clustering algorithms. This approach seeks both high data quality with a controlled number of transmissions using an aggregation function and an energy efficient network partition, respectively. The aim of this combination is to increase energy efficiency without sacrificing the data quality. We compare the performance of the Second-Order Data-Coupled Clustering (SODCC) and Compressive-Projections Principal Component Analysis (CPPCA) algorithm combination, in terms of both the energy consumption and the quality of the data reconstruction, to other combinations of the state-of-the-art clustering algorithms and in-network processing techniques. Among all the considered cases, the SODCC + CPPCA combination revealed a perfect balance between data quality, energy expenditure, and ease of network management. The main conclusion of this paper is that the design of WSN algorithms must be processing-oriented rather than transmission-oriented, i.e., investing energy on both the clustering and in-network processing algorithms ensures both energy efficiency and data quality.

Fast and accurate quality estimation of the electrocardiogram (ECG) signal is a relevant research topic that has attracted considerable interest in the scientific community, particularly due to its impact on tele-medicine monitoring systems, where the ECG is collected by untrained technicians. In recent years, a number of studies have addressed this topic, showing poor performance in discriminating between clinically acceptable and unacceptable ECG records. This paper presents a novel, simple and accurate algorithm to estimate the quality of the 12-lead ECG by exploiting the structure of the cross-covariance matrix among different leads. Ideally, ECG signals from different leads should be highly correlated since they capture the same electrical activation process of the heart. However, in the presence of noise or artifacts the covariance among these signals will be affected. Eigenvalues of the ECG signals covariance matrix are fed into three different supervised binary classifiers. The performance of these classifiers were evaluated using PhysioNet/CinC Challenge 2011 data. Our best quality classifier achieved an accuracy of 0.898 in the test set, while having a complexity well below the results of contestants who participated in the Challenge, thus making it suitable for implementation in current cellular devices.

Successful deployment of cognitive radios requires efficient sensing of the spectrum and dynamic adaptation of the available resources according to the sensed (imperfect) information. While most works design these two tasks separately, in this paper we address them jointly. In particular, we investigate an interweave cognitive radio with multiple secondary users that access orthogonally a set of frequency bands originally devoted to primary users. The schemes are designed to minimize the cost of sensing, maximize the performance of the secondary users (weighted sum rate), and limit the probability of interfering with the primary users. The joint design is addressed using nonlinear optimization and dynamic programming, which is able to leverage the time correlation in the activity of the primary network. A two-step strategy is implemented: it first finds the optimal resource allocation for any sensing scheme and then uses that solution as input to solve for the optimal sensing policy. The two-step strategy is optimal, gives rise to intuitive optimal policies, and entails a computational complexity much lower than that required to solve the original formulation.