Literature DB >> 10023841

Detection of lung injury with conventional and neural network-based analysis of continuous data.

J Räsänen1, M A León.   

Abstract

OBJECTIVE: To test if analysis of pressure and flow waveform patterns with an artificial intelligence neural network could distinguish between normal and injured lungs.
METHODS: Acute lung injury was induced in ten healthy anesthetized, mechanically ventilated dogs with repeated injections of oleic acid, until arterial blood oxyhemoglobin saturation reached 85% breathing room air. Airway pressure, esophageal pressure, airway flow, and arterial and mixed venous saturation signals were stored at 2 min intervals. Hemodynamic and blood gas data were collected every 10 min. Back-propagation neural networks were trained with normalized airway pressure and flow waveforms from normal and fully injured lungs.
RESULTS: The networks scored lung injury on a continuous scale from +1 (normal) to -1 (injured). Network scores unequivocally distinguished between normal and fully injured lungs and suggested a gradual transition from normal to injury pattern. However, the response of the network was slow compared to compliance, resistance and venous admixture.
CONCLUSIONS: Normal and fully injured lungs display distinct flow and pressure waveform patterns which are independent of changes in calculated pulmonary mechanics variables. These patterns can be recognized by a neural network. Further research is needed to determine the full potential of automated pattern recognition for lung monitoring.

Entities:  

Mesh:

Year:  1998        PMID: 10023841     DOI: 10.1023/a:1009938725385

Source DB:  PubMed          Journal:  J Clin Monit Comput        ISSN: 1387-1307            Impact factor:   2.502


  8 in total

Review 1.  Monitoring of pressure, flow, and volume during mechanical ventilation.

Authors:  M J Tobin
Journal:  Respir Care       Date:  1992-09       Impact factor: 2.258

Review 2.  What derived variables should be monitored during mechanical ventilation?

Authors:  J J Marini
Journal:  Respir Care       Date:  1992-09       Impact factor: 2.258

3.  A breathing circuit alarm system based on neural networks.

Authors:  J A Orr; D R Westenskow
Journal:  J Clin Monit       Date:  1994-03

4.  Neural network-based detection of esophageal intubation.

Authors:  M A León; J Räsänen; D Mangar
Journal:  Anesth Analg       Date:  1994-03       Impact factor: 5.108

5.  A pulse method of measuring respiratory system compliance in ventilated patients.

Authors:  P M Suratt; D Owens
Journal:  Chest       Date:  1981-07       Impact factor: 9.410

6.  PaO2 change during progressive pulmonary edema in dogs.

Authors:  I Kudoh; Y Segawa; K Numata; H Kitamura
Journal:  Crit Care Med       Date:  1985-12       Impact factor: 7.598

7.  Use of flow-volume curves in detecting secretions in ventilator-dependent patients.

Authors:  A Jubran; M J Tobin
Journal:  Am J Respir Crit Care Med       Date:  1994-09       Impact factor: 21.405

8.  Continuous monitoring of gas exchange and oxygen use with dual oximetry.

Authors:  J Räsänen; J B Downs; M R Hodges
Journal:  J Clin Anesth       Date:  1988       Impact factor: 9.452

  8 in total
  1 in total

1.  Robustness of two different methods of monitoring respiratory system compliance during mechanical ventilation.

Authors:  Gaetano Perchiazzi; Christian Rylander; Mariangela Pellegrini; Anders Larsson; Göran Hedenstierna
Journal:  Med Biol Eng Comput       Date:  2017-02-27       Impact factor: 2.602

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.