Machine Learning against COVID-19 pandemic

Review our ML solutions for epidemiological safety and disease detection


Medical PPE detector for epidemiological safety

Detect epidemiological safety rules breaches with ML-based PPE detector

The Challenge

Healthcare providers are in search for faster and more efficient control of PPE compliance during 2019-nCoV pandemic to prevent medical staff and patients from contamination and spreading the virus.

Healthcare systems all over the world are under significant pressure due to cases of coronavirus 2019-nCoV. As this trend is still intensive, adherence to personal protection rules by healthcare staff is critical. The absence of basic PPE items on medical workers and patients can be one of the causes of the healthcare system collapse due to lack of healthy and able-bodied medical staff.

The Solution: how it works?

Medical PPE detector for epidemiological safety is a machine learning solution developed to help healthcare providers during the COVID-19 pandemic.

  • Detect PPE incompliance. It allows organizations to automatically detect the absence of a medical mask or respirator, gloves and eyeglasses on a person through surveillance cameras. When a violation is detected, the algorithm automatically reports to the controller or safety engineer.

  • Identify people with high temperature. Optionally, it is capable of measuring the body temperature of a person in real time. If temperature is higher than normal, the solution alarms medical staff to take actions. 

  • Recognize violators among staff.  In addition, the solution is capable of face recognition. On request, this optional function can be activated to identify epidemiological safety rules violators  among the staff and automatically report this to management.

Solution's performance

Key features

  • Round-the-clock monitoring and detection;

  • Capable of identifying the absence of four object classes: coat, gloves, mask or respirator, eyeglasses;

  • Compatible with any high resolution camera;

  • Easy integration through RESTful API;

  • Ability to work in low light conditions;

  • Ability to measure body temperature.


AI platform for Computer-Assisted COVID-19 and pneumonia diagnosis

Detect and classify lung diseases including COVID-19, pneumonia, SARS, MERS, etc.


The Challenge

Medical staff all over the world are under great pressure due to a significant rise in the number of patients. As proper diagnosis is crucial for further treatment and pandemic decline, healthcare providers struggle to diagnose patients both fast and correctly.

The Solution: how it works?

Detector for COVID-19 and other lung diseases is a machine learning solution developed to fasten diagnostic process by classifying illnesses and calculating its probability.

  • Speed-up the lung diagnosis process. The solution serves as an assistant, which aims to reduce the pressure on medical staff during COVID-19 pandemic .It reduces time and effort doctors spend on diagnostic, however leaving more space for decision making and treatment.

  • Automatically identify and classify diseases.  The solution is  trained to analyse images and DICOM files. It is capable of classifying  such  illnesses as Pneumotorax, Pneumonia, Bacterial Pneumonia, Viral Pneumonia,COVID-19.

  • Recognize patients at highest risk. The solutions analyses images and as an output represents the probability of each disease it has detected. In this way it helps doctors understand the risk and make decisions about treatment and observation in time.

Key features

  • Easy integration, ability to be connected straight to CT/MRT;

  • User-friendly interface;

  • Possibility to work in teams and share data with colleagues: 

  • Ability to identify and analyse the probability of  Pneumotorax, Pneumonia, Bacterial Pneumonia, Viral Pneumonia,COVID-19;

  • Ability to process and analyze wide range of image formats: png, jpeg, DICOM, etc;

  • Space for feedback and notes. Feedback from doctors and other healthcare professionals will be taken into consideration


COVID-19 epindemic scenario calculator

(demonstration version)

Simulate pandemic scenarios and evaluate the effectiveness of potential prevention measures


The Challenge

​Political leaders and managers at all levels are responsible for decision-making and taking actions to beat the pandemic. Although a lot of COVID-19 data is available, it is extremely hard to make adequate forecasts manually, as there are a lot of important parameters which should be encountered.  At the same time such forecasts are crucial for proper resources allocation and in-time actions in cities and regions.

Demonstrative model

We represent you a demonstration version of calculator, created to show the importance of epidemic scenarios simulation which allow to see the impact of restrictive actions taken for cities. The calculator you may review now is a simplified version, which aims to demonstrate how the compartmental model, a method used to mathematically model infectious diseases, may be applied for COVID-19 challenge.  This approach (the SEIR model) together with the system dynamics makes it possible to describe the epidemic in the city.

This demonstration version only aims to represent the forecasting mechanism with slightly close-to-life data, and is inappropriate for decision making.

If you're in search for a tool able to forecast real trends and reveal hidden insights for smarter decisions, contact us directly.  

The full version, supplemented with data and algorithms relevant to your request, will be able to provide a broader vision of possibilities and consequences for quarantine, social distancing and other measures taken to disrupt virus spreading. 

Any questions?

We are open for partnership and cooperation. Feel free to contact us anytime.

Our partners
Eugene Khvedchenia
Eugene Khvedchenia

Computer Vision Consultant

  • LinkedIn
Mykhailo Nerubaiskyy
Mykhailo Nerubaiskyy

M.D. Clinical Radiology. Computed Tomography.

  • LinkedIn