Proposal to innovate Arterial Pressure evaluation using a non-Invasive and minimally-Intrusive (nImI) methods based upon Photopletysmography and Machine Learning

Matías Salinas, Jaime Plaza, Gonzalo Tapia, Rodrigo Salas, Carolina Saavedra, Alejandro Veloz, Alexis Arriola, Juan Idiaquez, Julio Riquelme, Antonio Glaría

Keywords: bp, ANN, big data, nImI, PPG, ELM

Abstract

We claim that innovative solutions to the puzzle of non- Invasive and minimally- Intrusive (nImI) Arterial Blood Pressure evaluation is rigorously supported by an already developed set of tested pieces. Such pieces are, but not limited to, the Connectionist Approaches and Machine Learning , Hornik theorems on Feedforward Artificial Neural Networks (FANN) trained as Universal Approximators, the emergence of Big Data paradigm and its recent application in Healthcare, and the access to proven new technologies based upon Volume Clamp methods for continuous, non- Invasive Arterial Blood Pressure monitoring and for wirelessly connecting patient to analysis systems.

Más información

Fecha de publicación: 2017
Año de Inicio/Término: 2017, June 11 and 13
Página final: 3
URL: https://www.researchgate.net/publication/320065115_Proposal_to_innovate_Arterial_Pressure_evaluation_using_a_non-Invasive_and_minimally-Intrusive_nImI_methods_based_upon_Photopletysmography_and_Machine_Learning