P. de Carvalho

An effective wavelet strategy for the trend prediction of physiological time series with application to pHealth systems

This work proposes a wavelet decomposition based scheme to estimate the evolution trend of physiological time series. The scheme does not involve the explicit development of a model and is essentially supported on the hypothesis that future evolution of a biosignal can be estimated from similar historic patterns. The strategy considers an a-trous wavelet decomposition, where the most representative trends are extracted from the historic similar patterns. Then, a set of distance-based measures able to assess the prediction likelihood of each representative trend, is introduced. From these measures and through an optimization process, a subset of these trends is selected and aggregated to derive the required time series evolution trend. The effectiveness of the methodology is validated in the prediction of blood pressure signals collected in two telemonitoring studies: TEN-HMS and MyHeart. Additionally, Friedman and Nemenyi statistics tests are implemented to rank several methods, confirming the value of the proposed strategy.

Phase space reconstruction approach for ventricular arrhythmias characterization

Ventricular arrhythmias, especially tachycardia and fibrillation are one of the main causes of sudden cardiac death. Therefore, the development of methodologies, enable to detect their occurrence and to characterize their time evolution, is of fundamental importance. This work proposes a non-linear dynamic signal processing approach to address the problem. Based on the phase space reconstruction of the electrocardiogram (ECG), some features are extracted for each ECG time window. Features from current and previous time windows are provided to a dynamic neural network classifier, enabling arrhythmias detection and evolution trends assessment. Sensitivity and specificity values, evaluated from public MIT-BIH databases, show the effectiveness of the proposed strategy.

Improvement of CVD risk assessment tools' performance through innovative patients' grouping strategies

There are available in the clinical community several practical risk tools to assess the risk of occurrence of a cardiovascular event. Although valuable, these tools typically present some lack of performance (low sensitivity/low specificity) when applied to a general (average) patient. This flaw is addressed in this work through an innovative personalization strategy that is supported on the evidence that current risk assessment tools perform differently among different populations/groups of patients. The proposed methodology is based on two main hypotheses: i) patients are grouped through a proper dimension reduction technique complemented with an unsupervised learning algorithm, ii) for each group the most suitable risk assessment tool can be selected improving the risk prediction performance. As a result, risk personalization is simply achieved by the identification of the group that patients belong to. The validation of the strategy is carried out through the combination of three current risk assessment tools (GRACE, TIMI, PURSUIT) developed to predict the risk of an event in coronary artery disease patients. The combination of these tools is validated with a real patient testing dataset: Santa Cruz Hospital, Portugal, N=460 ACS-NSTEMI1 patients. Considering the obtained results with the available dataset it is possible to state that the main objective of this work was achieved.

Long term cardiovascular risk models’ combination - a new approach

This work addresses two major drawbacks of the current cardiovascular risk score systems: reduced number of risk factors considered by each individual tool and the inability of these tools to deal with incomplete information. To achieve this goal a two phase strategy was followed. In the first phase, a common representation procedure was considered, based on a Naïve-Bayes classifier methodology. Conditional probabilities parameters were initially evaluated through a frequency estimation method and after that optimized using a Genetic Algorithm approach. In a second phase, a combination scheme was proposed exploiting the particular features of Bayes probabilistic reasoning. This strategy was applied to describe and combine SCORE, ASSIGN and Framingham models. Validation results were obtained based on individual models, assuming their statistical correctness. The achieved results are very promising, showing the potential of the strategy to accomplish the desired goals.

Combining pervasive technologies and Cloud Computing for COPD and comorbidities management

Integrated care of patients with COPD and comorbidities requires the ability to regard patient status as a complex system. It can benefit from technologies that extract multiparametric information and detect changes in status along different axes. This raises the need for generation of systems that can unobtrusively monitor, compute, and combine multiorgan information. In this paper, the concept and ongoing work for such an approach is presented as regards the multiple types of data recorded, features extracted, and examples of how they are combined in the EU-funded project WELCOME (Wearable Sensing and Smart Cloud Computing for Integrated Care to COPD Patients with Comorbidities) [1], for the integrated management of COPD and comorbidities.

HeartCycle: Advanced sensors for telehealth applications

Current treatment of Cardiovascular Disease (CVD) - the most frequent cause of hospitalization for people over 65 - involves changes of diet and lifestyle, requiring in addition physical exercise to support these. Nowadays, patients receive sporadic feedback at doctor visits, or later on, when facing symptoms. The HeartCycle project aimed at providing 1) daily monitoring, 2) close follow up, 3) help on treatment routine and 4) decreasing non-compliance to treatment regimes. The present paper illustrates a new toolbox of advanced sensors developed within the HeartCycle project. Ongoing clinical studies support these developments.

Cardiovascular risk and status assessment

This work focuses on the development of models to support the assessment of a patients global cardiovascular condition. Three types of models, based on different types of information, have been developed: long term cardiovascular risk models, that evaluate the risk of occurring of cardiovascular event within a long period of time (years); short term cardiovascular risk models, to assess the risk of death within a short period of time (months); cardiovascular status assessment models, to estimate the current cardiovascular condition of a patient. Three major drawbacks of current cardiovascular tools are addressed: reduced number of risk factors considered by each individual tool, inappropriateness of these tools to incorporate empirical clinical expertise and incapacity of these tools to deal with incomplete information. Methodologies and preliminary results, obtained under FP7 HeartCycle project, as well as future directions of research are also presented in this paper.

Personalization Algorithms Applied to Cardiovascular Disease Risk Assessment

Cardiovascular disease (CVD) is the major cause of death in the world. Clinical guidelines recommend the use of risk assessment tools (scores) to identify the CVD risk of each patient as the correct stratification of patients may significantly contribute to the optimization of the health care strategies. This work further explores the personalization of CVD risk assessment, supported on the evidence that a specific CVD risk assessment tool may have good performance within a given group of patients and might perform poorly within other groups. Two main personalization methods based on the proper creation of groups of patients are presented: i) clustering patients approach; ii) similarity measures approach. These two methodologies were validated in a Portuguese population (460 Acute Coronary Syndrome with non-ST segment elevation (ACS-NSTEMI) patients). The similarity measures approach had the best performance, achieving maximum values of sensitivity, specificity and geometric mean of, respectively, 77.7%, 63.2%, 69.7%. These values represent an enhancement in relation to the best performance obtained with current CVD risk assessment tools applied in clinical practice (78.5%, 53.2%, 64.4%).

Telehealth streams reduction based on pattern recognition techniques for events detection and efficient storage in EHR

This work proposes a framework for telehealth streams analysis, founded on a pattern recognition technique that evaluates the similarity between multi-sensorial biosignals. The strategy combines the Haar wavelet with the Karhunen-Loève transforms to describe biosignals by means of a reduced set of parameters. These, that reflect the dynamic behavior of the biosignals, can support the detection of relevant clinical conditions. Moreover, the simplicity and fast execution of the proposed approach allow its application in real-time operation, as well as provide a practical way to manage historical electronic health records: i) common and uncommon behaviors can be distinguished; ii) the creation of different models, tailored to specific conditions can be efficiently stored. The efficiency of the methodology is assessed through its performance analysis, namely by computing the required number of operations and the compression rate. Its effectiveness is evaluated in the prediction of decompensation episodes using biosignals daily collected in the myHeart study (blood pressure, weight, respiration and heart rates).