CBRA: Cardiac biomarkers release analyzer.

BACKGROUND AND OBJECTIVES: The most advanced technologies and continuous innovations in the medical field require a necessary interaction between the clinical and the engineering world. In this context, software applications are proposed as a bridge between the two scientific fields and, therefore, as powerful tools, easy to use, and with great analytical skills. In this work, we propose CBRA as an innovative software platform, moving towards personalized medicine, which aims to simplify and speed up the triage of patients and support doctors in the diagnostic and prognostic phase. METHODS: The computational core of the devised software application consists of a model-based identification algorithm, which enables the reconstruction of the cardiac biomarkers release curves in patients with ST-Elevation Acute Myocardial Infarction (STEMI). Identification and parametric optimization techniques allow the application of the proposed approach to each singular patient: based on a few experimental acquisitions, CBRA can extrapolate several quantitative features of high clinical relevance, thus facilitating and rendering more objective the clinical evaluation and therapeutic choices. A dedicated database to collect and manage patients clinical and personal data, as well as a graphical user interface, provides clinicians and researchers with an intuitive and user-friendly environment. RESULTS: In the following work, we present some examples of the possible applications of CBRA, ranging from the management of the cardiac biomarkers time-series, up to the real analysis of the clinical features that CBRA can extract from the reconstructed curve, such as, e.g., maximum concentration values of biomarkers in the plasma and relative times, in the distinct phases of the acute myocardial infarction, or identification of the time to onset of symptoms. CONCLUSIONS: CBRA makes it easy for clinicians to use modeling and parametric identification tools to reconstruct release curves. Furthermore, CBRA provides support to the clinical decision, thanks to its capability to extract information of high clinical relevance, not easily obtainable from the mere visual analysis of experimental samples. Having information about the previously listed clinical parameters could allow, e.g., identify in which stage of AMI the patient is, when She/He goes to the emergency room, with significant benefits in the therapy.

A Multi-Task Framework for Monitoring Health Conditions via Attention-based Recurrent Neural Networks.

Monitoring the future health status of patients from the historical Electronic Health Record (EHR) is a core research topic in predictive healthcare. The most important challenges are to model the temporality of sequential EHR data and to interpret the prediction results. In order to reduce the future risk of diseases, we propose a multi-task framework that can monitor the multiple status ofdiagnoses. Patients' historical records are directly fed into a Recurrent Neural Network (RNN) which memorizes all the past visit information, and then a task-specific layer is trained to predict multiple diagnoses. Moreover, three attention mechanisms for RNNs are introduced to measure the relationships between past visits and current status. Experimental results show that the proposed attention-based RNNs can significantly improve the prediction accuracy compared to widely used approaches. With the attention mechanisms, the proposed framework is able to identify the visit information which is important to the final prediction.

On the Analysis of Diseases and Their Related Geographical Data.

Electronic medical records (EMRs) store data related to patients information enrolled during their stay in health structures. Data stored into EMRs span from data crawled from biological laboratories to textual description of diseases and diagnostic device results (e.g., biomedical images). Each EMR is related to a diagnosis related group (DRG) record. A DRG record is a record associated with a citizen that has been cured in a hospital. It contains a code, called major diagnostic category (MDC), which summarizes the treated disease and allows to reimburse costs related to patient treatments during his staying in health structures. DRGs are used for administrative process (e.g., costs and reimbursement management) as well as disease monitoring. Associating diagnostic codes with external information (such as environmental and geographical data) and with information filtered from EMRs (e.g., biological results or analytes values) can be useful to monitor citizens wellness status. We propose a methodology to analyze such data based on a multistep process. First, we cross reference data by using a semantics-based clustering procedure, extract information from EMRs, and then, cluster them by looking for similar patterns of diseases. Then, biological records in each disease cluster are analyzed to evaluate intracluster similarity by selecting analytes typologies and values. Finally, biological data is related to diagnosis codes and geometrically projected in areas of interest in order to map calculated outlier patients. We applied the methodology on two case studies: 1) diagnosis codes and biochemical analytes of 20 000 biological analyses about hospitalized patients during one observation year and 2) the correlation between cardiovascular diseases and water quality in a southern Italian region. Preliminary findings show the effectiveness of our method.

Serum Calcium Increase Correlates With Worsening of Lipid Profile: An Observational Study on a Large Cohort From South Italy.

Despite the well-documented role of calcium in cell metabolism, its role in the development of cardiovascular disease is still under heavy debate. Several studies suggest that calcium supplementation might be associated with an increased risk of coronary heart disease, whereas others underline a significant effect on lowering high blood pressure and hyperlipidemia. The purpose of this study was to investigate, in a large nonselected cohort from South Italy, if serum calcium levels correlate with lipid values and can therefore be linked to higher individual cardiovascular risk.Eight-thousand-six-hundred-ten outpatients addressed to the Laboratory of Clinical Biochemistry, University of Magna Græcia, Catanzaro, Italy from January 2012 to December 2013 for routine blood tests, were enrolled in the study. Total HDL-, LDL- and non-HDL colesterol, triglycerides, and calcium were determined with standard methods.We observed a significant association between total cholesterol, LDL-cholesterol, HDL-cholesterol, non-HDL cholesterol, triglycerides, and serum calcium in men and postmenopause women. Interestingly, in premenopause women, we only found a direct correlation between serum calcium, total cholesterol, and HDL-cholesterol. Calcium significantly increased while increasing total cholesterol and triglycerides in men and postmenopause women.Our results confirm that progressive increase of serum calcium level correlates with worsening of lipid profile in our study population. Therefore, we suggest that a greater caution should be used in calcium supplement prescription particularly in men and women undergoing menopause, in which an increase of serum lipids is already known to be associated with a higher cardiovascular risk.