For health and drug research and development, availability of big data is necessary. However, personal details of healthcare and medical data are not easily accessible because of ethical and legal safeguards as well as privacy issues. But as this COVID-19 pandemic continues to claim lives and countries continue to be under economic and social duress, it becomes imperative that we find ways for healthcare research to progress. 

The Finnish Center for Artificial Intelligence (FCAI), a consortium of Artificial Intelligence (AI) experts from Aalto University, University of Helsinki, and VTT Technical Research Centre of Finland, has developed a way for research to progress as well as safeguard patient information. The FCAI, on June 25, released an innovative machine-learning method application that produces research data synthetically to enable academics and companies to share data whilst safeguarding the privacy of the individuals involved in the study.

The application has many avenues of success as industries want to protect their trade secret and inventions from competitors. This rings true for the pharmaceutical industry. The FCAI's application builds synthetic data from an original dataset which enables companies, Pharma companies in this scenario, to share data and progress with each other while protecting their own inventions. 

The FCAI fast-tracked the release of the application so that the researchers investigating the coronavirus pandemic would benefit from it at the earliest. The researchers, however, continue to improve the app by adding newer functionalities and making it easier to use. 

"There are still many things we don't know about the new coronavirus: for example, we do not know well enough what the virus causes in the body and what the real risk factors are. When researchers have synthetic data, we start understanding these things better," says Samuel Kaski, Academy Professor and the Director of the Finnish Center for Artificial Intelligence FCAI. 

The researchers are now taking a step forward - they're working on how they can use the synthetic data to construct a model that, based on specific biomarkers - certain types of molecules, cells, or hormones that indicate disease. "The original data set with which we do this has been publicly available. Now we are trying to reproduce the results of the original research with the help of synthetic data and build a predictive model from the synthetic data that was achieved in the original research," explains Joonas Jälkö, a doctoral researcher at Aalto University. Using biomarkers, the model can predict whether a test subject's coronavirus test is positive or negative.