Our Technology

Our underlying technology is the product of over 8 years of research focused on the transmission of pathogens in the urban and sub-urban spatial resolution scales. Understanding the dynamics of how pathogen spread within these areas is critical for the effective prevention and containment of communicable diseases.

EDAS Local Transmission Zone (LTZ) technology implements this knowledge by using extensive Machine-Learning algorithms to track the epidemiology of infectious diseases in the community and to accurately diagnose the causative agent of a specific patient at a specific time and location. Our technology allows us to accurately predict, monitor and identify specific pathogens in real time and remotely, based on patients’ demographics parameters only.

The company had been granted a US patent #US9075909B2 for its revolutionary technology.

The robustness of our technology allowed us a very fast adaptation to to new diseases, fully predicting and monitoring them within few weeks only, reaching similar levels of accuracy.

Our scientific framework is based on two elements:

  1. Pathogens are transmitted through human contact networks, so the pathogen propagation is dictated by and can be inferred from the infected community structure.

  2. By identifying a human disease caused by a particular pathogen, we can assign "pathogen content" to the community contact network.


As pathogen transmission has been shown to occur primarily within LTZs, we use clinically diagnosed pathogens (regional laboratory test results) in hospitals to ‘flag’ LTZs in the community and predict the ‘next patient’ disease factor through learning models. The model calculates the LTZ regions for each pathogen and defines the level of infection of each LTZ based on historical behavior and correlation between LTZs. The models then combines LTZs with gender and age to create an up-to-date infection map (geographical and demographic) according to the pathogenic information collected.


The LTZ size can vary from multiple buildings in a street to a neighborhood, and sometimes it contains multiple areas without a geographical sequence.

In our LTZ methodology and concept application, we use AI and ML modules based on historical regional laboratory test results to track and predict the respiratory disease epidemiology. Our ML models are trained to aggregate test results across multiple geographic segments and multiple time frames, as well as descriptive features such as age, gender, month, and baseline clinical data.

Our Executive Summary

Get a snapshot of EDAS Healthcare and its benefits with our Executive Summary.

Our latest Blog post:

  • phone
  • whatsapp
  • email
  • Twitter
  • LinkedIn
  • RSS

Privacy & Terms  |  © 2020 EDAS Healthcare Ltd.

Site design by   2CENTS ltd.