COVID-19:Finnish researchers have developed a new machine learning-based method which can synthetically provide data for medical research.
The availability of big data is important for health and drug research and development. Nonetheless, because of ethical and legal safeguards as well as privacy considerations, personal information of health care and medical data are not easily accessible. But as this COVID-19 pandemic continues to claim lives and countries remain under economic and social pressure, it becomes imperative to find ways to advance health care research.
COVID-19 The Finnish Center for Artificial Intelligence (FCAI), a group of experts in artificial intelligence ( AI) from Aalto University, University of Helsinki, and Finland’s VTT Technical Research Centre, has established a way to advance research and to safeguard patient information. On June 25, the FCAI published a groundbreaking machine-learning method application that synthetically produces research data to allow academics and businesses to exchange data while safeguarding the privacy of the patients involved in the study.
The application has many successful avenues, as businesses seek to protect their trade secrets and competitive innovations. That is true in the pharmaceutical industry. The FCAI application builds synthetic data from an original dataset that allows companies in this case, pharmaceutical companies, to exchange data and progress with each other while preserving their own innovations.
The FCAI quickly monitored the application’s release so that it would help the researchers studying the coronavirus pandemic at the earliest possible time. However, the developers keep developing the application by introducing new functionalities and making it easier to use.
Samuel Kaski, Academy Professor and the Director of the Finnish Center for Artificial Intelligence FCAI said, “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.”
The researchers are now taking a step forward-they are focusing on how they can use the synthetic data to create a model based on different biomarkers-other forms of disease-indicating molecules, cells, or hormones. “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. The model will use biomarkers to determine whether a coronavirus test of a test subject is positive or negative.