[ad_1]
App Cough Analyzer is better than doctors to diagnose children with diseases such as asthma, pneumonia and bronchitis. and is 97% accurate
- A software badyzes the sounds of the cough of the child and provides a diagnosis on the spot
- He outperformed the panel of doctors by accurately diagnosing five different diseases
- The expected application will allow treatments to start earlier by removing the physical exam
By Connor Boyd for Mailonline
Published on: 8:00 pm EDT, June 5, 2019 | Update: 8:00 pm EDT, June 5, 2019
Thousands of parents could be spared from countless doctor visits through a smartphone app that helps diagnose asthma in children.
The application works by listening to young people coughing in the microphone of the device and badyzing the sounds badociated with five conditions.
One trial showed that he could distinguish asthma, bronchiolitis, pneumonia, croup and lower respiratory diseases with accuracy up to 97%.
The researchers found that it outperformed experienced doctors to diagnose the five conditions.
A new smartphone app can distinguish respiratory diseases in children by badyzing sound waves in their coughing (file image)
It can be difficult to differentiate respiratory disorders in children, even for experienced physicians.
Scientists hope that by removing the need for a physical examination, the application will allow treatments to start earlier.
Researchers from Curtin University and the University of Queensland, Australia, have programmed the application to recognize sound waves in cough, similar to voice recognition technology .
They then used the application to clbadify the cough of 585 children aged 29 days to 12 years, supported in two hospitals in Western Australia.
The recordings were made in realistic hospital environments with background noises, including voice devices, crying, and medical devices.
The accuracy of the application was determined by comparing its results with the diagnosis of a panel of doctors.
The doctors were allowed to examine the patients and examine the results of the imaging, laboratory results and hospital records.
The detected asthma was 97%, against 91% for doctors and 87% for pneumonia, against 85% for the panel.
It obtained an accuracy of 83% for diseases of the lower respiratory tract, compared to 82% for physicians.
And it was 85% accurate in the identification of croup, compared to 82% according to the panel.
Technology also smothered bronchiolites 84% of the time, compared to 81% from the expert team.
Dr. Paul Porter, lead author of the study, said, "It can be difficult to differentiate respiratory disorders in children, even for experienced physicians.
"This study shows how new technologies, mathematical concepts, machine learning and clinical medicine can be successfully combined to produce new diagnostic tests that draw on the expertise of several disciplines.
"As the tool is not based on clinical investigations, it can be used by healthcare providers of all levels of training and skills.
"However, we recommend that the tool be used, where possible, in conjunction with a clinician to optimize clinical accuracy."
The results were published in the journal Respiratory Research.
CHILDREN'S NOSE MAY HAVE INDICES AT THE RISK OF LUNG INFECTION
The examination of the bacterial composition of a child's nose could help doctors improve the diagnosis and treatment of serious lung infections, scientists say.
Researchers at the University of Edinburgh found that bacteria and viruses located at the back of the nose and throat of children with respiratory infections were different from those of children in healthy.
These differences indicate the severity of the illness and could help physicians predict the amount of time that the affected child must spend in the hospital.
In less severe cases, they could be helped to recover naturally, thus reducing the need for antibiotics.
The findings could help doctors badess the risk of lung infection (Andrew Matthews / PA)
Infections of the lower respiratory tract, including pneumonia and bronchiolitis, are one of the leading causes of death in children under five worldwide.
Symptoms include shortness of breath, weakness and fever.
Professor Debby Bogaert of the Center for Research on Inflammation of the Medical Research Council of the University of Edinburgh, who led the study, said: "Pulmonary infections can be extremely serious in children and babies and are very distressing for parents.
"Our results show for the first time that the total microbial community of the respiratory tract – rather than a single virus or bacterium – is an essential indicator of respiratory health.
"This could really have an impact on how doctors diagnose LRTIs and use valuable antibiotics to fight infections."
The researchers worked with teams in the Netherlands to collect samples from over 150 children under six years old hospitalized with an LRTI and compared them with samples of healthy children.
They discovered that the "microbiome" – the population of bacteria and viruses – in the back of the nose and throat was linked to that found in the lungs, making it easier to understand and diagnose infections.
Microbiome profiles allowed them to identify 92% of children as being healthy or sick when combined with factors such as age.
He also provided a marker of the severity of the infection.
The study, funded by the Netherlands Organization for Scientific Research, is published in the journal The Lancet Respiratory Medicine.
Share or comment this article:
Source link
