AI Based Diagnosis of Pneumonia

Pneumonia is a lung infection caused by bacteria, viruses and fungi. In this infection, the air sac (alveoli) of the lungs gets inflamed and breathing becomes difficult which causes mild to severe illness among people. They are diagnosed by performing chest X-ray, blood test, pulse oximetry. Pneumon...

Full description

Saved in:
Bibliographic Details
Published in:Wireless personal communications 2022-10, Vol.126 (4), p.3677-3692
Main Authors: Vidhya, B., Nikhil Madhav, M., Suresh Kumar, M., Kalanandini, S.
Format: Article
Language:English
Subjects:
Acoustics
Algorithms
Alveoli
Artificial intelligence
Audio data
Communications Engineering
Computer Communication Networks
Deep learning
Diagnosis
Engineering
Lungs
Machine learning
Networks
Oximetry
Performance evaluation
Pneumonia
Signal,Image and Speech Processing
Software
Sound
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Pneumonia is a lung infection caused by bacteria, viruses and fungi. In this infection, the air sac (alveoli) of the lungs gets inflamed and breathing becomes difficult which causes mild to severe illness among people. They are diagnosed by performing chest X-ray, blood test, pulse oximetry. Pneumonia can also be identified using lung sounds that are recorded in the digital stethoscope. In this proposed work, a software is developed to diagnose pneumonia from the lung sound using gradient boosting algorithm. Lung sounds give enough symptoms for pneumonia identification. Lung sounds are recorded by doctors using Electronic Stethoscope. The recorded lung sounds are processed using audacity software. This software separates the required sound from unwanted noises. The healthy individual’s audio files are labelled as 0 and the pneumonia patient's audio files are labelled as 1 for training the algorithm. During diagnosis study and the performance evaluation with various machine learning algorithms like support vector machine and k-nearest neighbours (KNN) algorithms, it was observed that the gradient boosting algorithm exhibits good identification property with 97 percent accuracy. This proposed method also reveals excellent diagnoses of pneumonia over other artificial intelligence and deep learning techniques. This method can also be used to predict Covid affected lungs sounds.
ISSN:0929-6212
1572-834X
DOI:10.1007/s11277-022-09885-7