Scientific Research


Case Study

The Wadhwani Institute for Artificial Intelligence (Wadhwani AI) is an independent not-for-profit research institute.

They aim to harness the power of AI to find the break points that cause the world’s deepest problems — and then find innovative solutions to fix them.

The Challenge


Until we find a cure or develop a vaccine for COVID-19, testing continues to be the first line of defense in the global fight against the pandemic. However, ramping up testing capacity is expensive and time consuming, particularly in rural and remote areas. There is a need for a simple, non-invasive technology to triage patients who may be infected with the SARS-CoV-2. The Wadhwani Institute have built a cough analysis technology that could help in identifying at-risk patients, before lab-based tests, even if they are asymptomatic.

It works on a basic smartphone and can be used to assess risk of being infected, without the need for any additional hardware or device. It provides instantaneous results, and will enable healthcare systems to create a funnel through which testing resources can be dedicated to those with a higher probability of being infected with COVID-19.

From all data collected on smartphones, there are three significant lists being collected:

(1) Patient registrations (2) Cough sounds (3) Covid test results.

This data is being collected by different people around hospitals and clinics in India and is growing each day.  Due to the nature of these datasets being collected at different times and locations, there are some gaps in the data which is slowing down the ability to link them to the correct patient.  For example, one of the linkage elements is an email address, and if spelt incorrectly or not even entered on one of the datasets, then it could fail to link to the relevant patient, which could result in patients not being correctly diagnosed.

What they required was a fast, accurate and automated process that will help to identify all the patients from each of the three datasets.  It would require some advanced data matching and merging to correctly identify patients records that have not been spelt the same.

Due to the confidential nature of the data, Wadhwani Institute needed to keep all data on premise and wanted to use a system that would perform accurate patient matching & cleansing across multiple lists without the concern of any data transfer over the cloud.

The Solution

The Wadhwani Institute tried several high-profile data matching technologies and used real life sample data to determine which tool would be the most suitable.  Based on the test results, affordability and its ease of use, they decided WinPure would be the most suitable solution for this project.  As Abhishek Kumar, Senior Engineer states:

The importance of this project required top-quality data matching to successfully link all the patient data, with both speed and simplicity being of great importance.


  • data matching softwareBest-in-Class Patient Matching – As the world’s best data matching software, The Wadhwani Institute can correctly link patient data with speed and ease.
  • User friendly – Simple to use with highly visual interface and without the need for special training, the whole team can use the tool to create a single source of truth.

We tried and tested several other data matching tools but were more impressed with WinPure’s speed, simplicity and its matching results, and we are excited about the potential of using this technology on other projects in the future

Abhishek Kumar

Senior Engineer

Industry Clients