On-mask sensor network for lung disease monitoring. (May 2023)

• Record Type: Journal Article
• Authors: Smily Jeya Jothi, E.; Justin, Judith; Vanithamani, R.; Varsha, R.
• Is Part Of: Biomedical signal processing and control. Volume 83(2023)
• Publication Date: 2023-05
• Subjects: Asthma -- COPD -- Bronchiectasis -- Lung monitoring -- SVM -- Random Forest -- KNN -- Machine Learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2023.104655
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Proposes a continuous lung function monitoring system using Machine Learning (ML) techniques to aid in the early identification of the disease symptoms and obviates severe outbreaks of the lung disorder. 3D mask made of Poly Lactic Acid (PLA) filament, developed using 3D printing technology, contains a series of sensors interfaced to the microcontroller. The sensor values are instantaneously fetched when the person wearing the mask inhales and exhales. The acquired data from the sensors are directed to the cloud through a Wi-Fi module for further analysis, and classification is done by Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN) algorithms. The training of the classifiers is carried out using a set of pre-trained values taken from publicly available databases. Abstract: A lung disease usually falls into three categories: lung tissue disease, lung circulation disease, and lung airway disease. Several chronic breathing disorders cause inflammation and swell of the airways due to excessive mucus secretion, including asthma, Chronic Obstructive Pulmonary Disease (COPD), and bronchiectasis. The airways overreact to various stimuli, narrowing the bronchi and leading to broncho-constriction associated with chest tightness, cough, and dyspnea. The repercussions of airway diseases can be minor, interfering in daily routines, while the symptoms may sometimes flare up and become life-threatening. Monitoring of physiological status of pulmonary patients is essential to avoid any critical situations. This work proposes a continuous lung function monitoring system using Machine Learning (ML) techniques to aid in the early identification of the disease symptoms and obviates severe outbreaks of the lung disorder. 3D mask made of Poly Lactic Acid (PLA) filament, developed using 3D printing technology, contains a series of sensors interfaced to the microcontroller. The sensor values are instantaneously fetched when the person wearing the mask inhales and exhales. The acquired data from the sensors are directed to the cloud through a Wi-Fi module for further analysis, and classification is done by Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN) algorithms. The training of the classifiers is carried out using a set of pre-trained values taken from publicly available databases. Furthermore, patients are warned when there are deviations from the normal value of the physiological parameters and changes in favourable atmospheric conditions.