Automatic recognition of numeric values from the monitor of vital signs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F20%3A00345578" target="_blank" >RIV/68407700:21460/20:00345578 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/EHB50910.2020.9279883" target="_blank" >http://dx.doi.org/10.1109/EHB50910.2020.9279883</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EHB50910.2020.9279883" target="_blank" >10.1109/EHB50910.2020.9279883</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic recognition of numeric values from the monitor of vital signs

Popis výsledku v původním jazyce

Stabilization and resuscitation of newborns is an extremely professional and mentally demanding process. It is crucial for its success to quickly and correctly evaluate the condition of the newborn and adapt the use of appropriate interventions. For analyzes the effectiveness of the procedures and used drugs, it is appropriate to analyze the entire course of the action - debriefing, and timeline of the development of the newborn's vital functions is created. To streamline image data processing, an application was created which enables automatic recognition of numerical values of heart rate and blood oxygen saturation from video record of the vital signs monitor using a convolutional neural network. The application plots HR and SpO2 values against the time of delivery and allow to save to text file. The average accuracy of the value recognition at the scanning frequency 1 second was more than 93 % for all analyzed parameters.

Název v anglickém jazyce

Automatic recognition of numeric values from the monitor of vital signs

Popis výsledku anglicky

Stabilization and resuscitation of newborns is an extremely professional and mentally demanding process. It is crucial for its success to quickly and correctly evaluate the condition of the newborn and adapt the use of appropriate interventions. For analyzes the effectiveness of the procedures and used drugs, it is appropriate to analyze the entire course of the action - debriefing, and timeline of the development of the newborn's vital functions is created. To streamline image data processing, an application was created which enables automatic recognition of numerical values of heart rate and blood oxygen saturation from video record of the vital signs monitor using a convolutional neural network. The application plots HR and SpO2 values against the time of delivery and allow to save to text file. The average accuracy of the value recognition at the scanning frequency 1 second was more than 93 % for all analyzed parameters.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE E-HEALTH AND BIOENGINEERING EHB 2020

ISBN

978-1-7281-8803-4

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

—

Název nakladatele

Gr. T. Popa University of Medicine and Pharmacy

Místo vydání

Iasi

Místo konání akce

Iasi

Datum konání akce

29. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000646194100009