A functional supervised learning approach to the study of blood pressure data

Georgios I Papayiannis; Emmanuel A Giakoumakis; Efstathios D Manios; Spyros D Moulopoulos; Kimon S Stamatelopoulos; Savvas T Toumanidis; Nikolaos A Zakopoulos; Athanasios N Yannacopoulos

doi:10.1002/sim.7587

A functional supervised learning approach to the study of blood pressure data

Stat Med. 2018 Apr 15;37(8):1359-1375. doi: 10.1002/sim.7587. Epub 2017 Dec 20.

Authors

Georgios I Papayiannis^{1

2

3}, Emmanuel A Giakoumakis⁴, Efstathios D Manios⁵, Spyros D Moulopoulos⁵, Kimon S Stamatelopoulos⁵, Savvas T Toumanidis⁵, Nikolaos A Zakopoulos⁵, Athanasios N Yannacopoulos^{1

3}

Affiliations

¹ Department of Statistics, Athens University of Economics & Business, Athens, Greece.
² Sector of Mathematics, Hellenic Naval Academy, Piraeus, Greece.
³ Stochastic Modeling and Applications Laboratory, Athens University of Economics & Business, Athens, Greece.
⁴ Department of Informatics, Athens University of Economics & Business, Athens, Greece.
⁵ Faculty of Medicine, National & Kapodistrian University of Athens, Athens, Greece.

PMID: 29266314
DOI: 10.1002/sim.7587

Abstract

In this work, a functional supervised learning scheme is proposed for the classification of subjects into normotensive and hypertensive groups, using solely the 24-hour blood pressure data, relying on the concepts of Fréchet mean and Fréchet variance for appropriate deformable functional models for the blood pressure data. The schemes are trained on real clinical data, and their performance was assessed and found to be very satisfactory.

Keywords: Fréchet mean; blood pressure; functional supervised learning; hypertension.

Publication types

Comparative Study

MeSH terms

Algorithms*
Biometry / methods*
Blood Pressure
Blood Pressure Determination
Databases, Factual
Humans
Hypertension / classification*
Hypotension / classification*
Models, Statistical
Nonlinear Dynamics
Supervised Machine Learning*