Multiparametric prediction with application to early detection of cardiovascular events

Cardiovascular diseases are a major public health concern, and a cause of considerable morbidity and mortality. As a consequence, the prediction of severe events is of great importance for professionals, since it provides the adequate tools to diagnose. The main goal of this work is the development of algorithms that perform the early detection of critical events, using multi-parametric approaches that combine physiological measurements (e.g. ECG, blood pressure, weight) and other sources of information (e.g. medication). Two main scientific challenges will be addressed: prediction methods and information fusion schemes, based on computational intelligence methodologies. The main hypothesis is that physiological time series with similar progression have prognostic value in future clinical states. The main applications will be the prediction of hypertension or decompensation episodes for heart failure patients. The clinical validation will be carried out in the context of tele-monitoring studies using private dataset (myHeart), and intensive care units using public datasets (mimic II-Physionet). This paper presents the main guidelines of research and some preliminary results on the similarity assessment from heart failure patients.

[1]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[2]  J. Morais,et al.  Personalization Based on Grouping Strategies for Short-Term Cardiovascular Event Risk Assessment , 2015, Cardiovascular engineering and technology.

[3]  Shaibal Barua,et al.  Multi-sensor Information Fusion for Classification of Driver's Physiological Sensor Data , 2013 .

[4]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[5]  Jorge Munoz-Gama,et al.  Process mining in healthcare: A literature review , 2016, J. Biomed. Informatics.

[6]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.

[7]  Wil M. P. van der Aalst,et al.  Process mining: a research agenda , 2004, Comput. Ind..

[8]  Mohamed Sheik,et al.  A Prediction System Based on Fuzzy Logic , 2008 .

[9]  Jorge Henriques,et al.  Improvement of CVD risk assessment tools' performance through innovative patients' grouping strategies , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  J. Morais,et al.  Short-Term Cardiovascular Disease Risk Assessment: Comparison of Two Combination Approaches , 2015 .

[11]  Shien-Ming Wu,et al.  Time series and system analysis with applications , 1983 .

[12]  Jorge Henriques,et al.  Trend prediction methodology based on time series similarity analysis and haar wavelet decomposition , 2013, 2013 2nd Experiment@ International Conference (exp.at'13).

[13]  Zhong Shi-sheng,et al.  Time series prediction using wavelet process neural network , 2008 .

[14]  Michel Camilleri Forecasting Using Non-Linear Techniques In Time Series Analysis : An Overview Of Techniques and Main Issues , 2004 .

[15]  Paulo Carvalho,et al.  Long term cardiovascular risk models' combination , 2011, Comput. Methods Programs Biomed..

[16]  Wil M. P. van der Aalst,et al.  Time prediction based on process mining , 2011, Inf. Syst..

[17]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .