Routine clinical monitoring fails to identify children at high risk of lung function decline

Perrem, Lucy

doi:10.1016/j.jcf.2022.08.017

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The safe chronic respiratorysensing principles should be divided into three vital types 2 : (1) indirect measurements via physiological data, which includes using algorithms for analysing signals from the chest wall impedance and pulse oxygen saturation, 8 because biological signals such as electrocardiograms (ECG), photoplethysmography (PPG), and seismocardiography (SCG) can be altered by breathing and the rate of respiration can be obtained from these data points using suitable algorithms; and (2) immediate identification of respiratory‐related mechanical motion in the thoracic aorta. (3) Using different kinds of sensors, such as a sound sensor, direct monitoring of pulmonary flow of gases in the nose area 9 .…”

Section: Related Workmentioning

confidence: 99%

3D mask based lung function monitoring system using machine learning for early identification of lung disorders

Bhansali,

Rekha,

Shahapure

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Early identification of illness can aid in lowering the death rate related to lung illnesses. Asthma, Chronic Obstructive Pulmonary Disease (COPD), and bronchiectasis are all chronic respiratory illnesses that cause irritation and oedema of the airway due to increased mucus discharge. Monitoring the asthmatic patient's physiological state is vital to avoiding dangerous circumstances. This study offers a regular lung function monitoring system that employs Machine Learning (ML) approach to aids in the prompt detection of symptoms of illness and the prevention of significant epidemics of the lung condition. A collection of sensors are coupled to the microcontroller in a 3D mask created using 3D printing technology. When a person wearing a face mask breathes in and out, the sensor values are instantly retrieved. The sensor data is sent to the cloud via a Wi‐Fi module for additional evaluation, and categorisation is performed using genetic algorithms, Support Vector Machine (SVM), and Principal Component Analysis (PCA). The GA, SWM, and PCA algorithms identify lung sickness using data from sensors obtained from the 3D masks through the web interface. There were 250 participants in total, comprising persons from all ages, smoker and those who do not smoke as well as asthmatics. The classifiers are trained utilising a set of pretrained values obtained from freely accessible datasets. Furthermore, patients are alerted when physiological indicators deviate from normal and when favourable atmospheric circumstances change.

show abstract

Section: Related Workmentioning

confidence: 99%