How to achieve earlier lung disease detection:

the automated approach 

Most of us never think about our breathing, it’s just something we do. For example, research of Lung Foundation Australia, shows that almost half of all Australians rarely or never think about their lung health. Despite this, almost two-thirds of Australians reported that they have experienced at least one lung related health issue. People often put the symptoms down to aging or lack of fitness. Lung disease is any problem in the lungs that prevents them from working properly – this may be a disease of the airways, lung tissue or lung circulation. There are over 30 types of lung disease, ranging from asthma and influenza to occupational lung disease and lung cancer. And don’t forget about COVID-19 pandemic!

Lung disease doesn’t discriminate. It affects men, women, children, smokers, ex-smokers and never smokers. Getting an early diagnosis is critical to improving outcomes, treatment options and saving lives.  

Symptoms of lung disease include weariness, coughing up mucus, coughing up blood, and chest pain. Often lung disease is diagnosed in its latter stages reducing the chance of effective treatment. Early detection can help to fully treat or at the very least, stall the progression of lung disease.

Challenges of diagnosing Pneumonias, COVID-19 and other lung diseases

Pneumonia is a really difficult disease to diagnose because it could be caused by any number of pathogens that lead to a bacterial, fungal or viral infection in the lungs and it can be contracted almost anywhere, including in hospitals. The problem is, that it is not a single disease but a group of specific infections, each of which has a different epidemiology, pathogenesis, presentation and clinical course.  

Pneumonia is one of the most common infectious diseases that is treated in hospitals in many countries of the World. Despite advances in diagnosis and treatment, it contributes to significant mortality and morbidity.

The disease globally has a significant impact on the health economy. As a British Lung Foundation research shows, It remains the sixth largest cause of death in the UK, where it is responsible for 5.1% of deaths. The fact is, that In the UK, pneumonia affects the older population, with more than half of cases occurring in people aged ≥61 years.

According to the WHO statistics, nowadays pneumonia is one of the leading causes of death worldwide.

However, the research of Le Roux and Zar says that worldwide, it is the leading cause of death in children who have passed the neonatal period. In the UK, pneumonia accounts for much more admissions and bed days than any other lung disease, with over 200,000 admissions per year – this equates to 2.3 million bed days. Between 5% and 15% of patients who are hospitalised with pneumonia die within 30 days of admission. This figure rises to 30% for patients who are admitted to intensive care.

Why are images so important?

Now Imaging exams have been a main clinical diagnostic criteria for a lot of types of pneumonia and  for coronavirus disease (COVID-19), what is especially important. Imaging features of multiple patchy areas of ground glass opacity and consolidation predominantly in the periphery of the lungs are characteristic manifestations on chest X-Ray or CT and extremely helpful in the early detection and diagnosis of this disease. That aids prompt diagnosis and the eventual control of this emerging global health emergency.


In the clinical work of this pandemic, the radiologists play a key role in the fast identification and early diagnosis of a suspected patient. This can become a great benefit not only to the patient but to the larger public health surveillance and response systems as well.

Сhest radiography is helpful as a screening tool on the frontlines in medical settings with limited resources or in cases where the patient’s physical condition does not allow for transport to the radiology department CT scanner. As the disease progresses beyond the early stage, chest radiography can detect multiple patchy opacities throughout the lungs.

Computed tomography (CT) imaging is very sensitive to detecting early disease, assessing the nature and extent of lesions, and discovering subtle changes that are often not visible on chest radiography. The imaging features of lesions are always described with the following factors: distribution, quantity, shape, pattern, density, and concomitant signs.

Chest X-rays have long been considered the best tool to detect any form of pneumonia.  But the problem is, that pneumonia can appear similar to other conditions on a scan, and imaging cannot identify the infectious pathogen, making the diagnosis of pneumonia via X-ray a challenge. This is especially true when patients are experiencing multiple health problems simultaneously. 

However, artificial intelligence and machine learning  can be used for solving complex data analysis problems, optimization of practices, and the diagnosis of life-threatening diseases like pneumonia. 

  • For example, algorithm ‘CheXNet', that is an artificial neural network designed to detect pneumonia from chest X-rays, at a performance rate greater than the average radiologist.  

  • Next example,“hive mind” — that uses Artificial Swarm Intelligence (ASI) to combine and utilize the individual capacities of a small group of radiologists, together, in real time, to procure an optimal diagnosis or solution. This technique shows better results than individual doctors or algorithms detecting pneumonia by X-ray.

Already existing software solution for early lung disease detection

Current situation requires fast, widely accessible diagnostic tools which would preferably be available yesterday or right now. In a realistic clinical context of the current COVID-19 pandemic, speed, availability and ease-of-application are most important. In this case AI and ML solutions will play a key role.

Detector  is an application based on the maсhine learning model, which can identify and classify 14 types of inflammatory lung diseases such as Bacterial Pneumonia, COVID-19, Chlamydophila, Fungal Pneumonia, Klebsiella, Legionella, Pneumocystis and other viral types of pneumonia, ARDS, Pneumothorax, and Hydrothorax.

The web application installed on your computer reads and analyzes the images obtained from the digital X-ray machine in png, jpeg and DICOM files formats. 

The algorithm identifies the infected areas that the physician should pay attention to for diagnosis.

Based on the reference information provided in the development the algorithm shows the likelihood of a particular disease as a percentage. As well, users have the ability to share the received data with colleagues through the network for consultations which reduces the probability of making the wrong diagnosis.

In fact, the application is a physician's assistant. And its goal is to reduce the burden on the radiologists when the healthcare systems are operating beyond their capabilities and to reduce the likelihood of a diagnostic error caused by overwork and psychological pressure.

AI platform for Computer-Assisted COVID-19 and Pneumonia Diagnosis


The solution’s machine learning algorithms are trained to accurately detect and diagnose such conditions as pneumothorax, pneumonia (bacterial or viral), and COVID-19 by “looking” at medical images and lung scans. By serving as a doctor’s intelligent assistant, it allows them to assess the risks faster and speed up diagnostics, thus potentially saving more patients through correct treatment.

Thank you for reading! 

Feel free to rate the article here: