Israeli study might mark beginning of new era for medical privacy

A paper published showed that medical research carried out using synthetic data can produce results which are strongly consistent with research using real patients’ data.

By ROSSELLA TERCATIN
Rambam health care campus. (photo credit: MIKI AND GAL KOREN)
Rambam health care campus.
(photo credit: MIKI AND GAL KOREN)
A new study by Rambam Health Care Campus scientists might mark the beginning of a new era for patients’ privacy. A paper published in the JMIR Medical Informatics journal showed that medical research carried out using synthetic data can produce results which are strongly consistent with research using real patients’ data, as long as certain conditions in creating the database are met.
“For the first time, we were able to prove that there is no significant difference between the results obtained from real patient data analysis and the results obtained from synthetic data analysis,” Prof. Raphael Beyar, former Rambam Hospital director and chairman of the Rambam Friends Association, said in a press release.
Medical synthetic data is data produced by aggregating and processing the relevant characteristics of real patients in order to create a population of fictitious profiles that on the whole present the same statistical property of the original data. Since the profiles are completely made up, there is no way to re-identify the patients.
The team from the Rambam Hospital Research Division, led by Dr. Ronit Almog, director of the Epidemiology Unit, and senior bio-statistician Dr. Anat Reiner Ben-Na’im, compared the results obtained with synthetic data and with real data in five different studies on various topics.
They found that as long as the number of patients was large relative to the number of variables used, the outcome was highly accurate.
“This research is likely to affect the way medical studies are conducted in the future, as we have demonstrated that Big Synthetic Data can be a reliable substitute for real patient information, and in this way it can put an end to the danger of disclosing medical information without compromising the scientific validity of the findings,” Beyar added.
Rambam has been at the forefront in the use of big data thanks to its choice to incorporate its information systems with the technology developed by the Beersheba-based company MDClone.
Among others, last month MDClone launched a cooperation with the US National Institutes of Health in the fight against the coronavirus crisis, providing them with a platform to turn data from academic medical centers into researchable material while protecting patients’ privacy.
“The idea that an Israeli company can help make a difference for global research is very important for us,” chief commercial officer Josh Rubel told The Jerusalem Post.
“The use of synthetic structured data provides a close estimate to real data results and is thus a powerful tool in shaping research hypotheses and accessing estimated analyses, without risking patient privacy,” the Rambam scientists wrote in the paper. “Synthetic data enable broad access to data (e.g., for out-of-organization researchers), and rapid, safe and repeatable analysis of data in hospitals or other health organizations where patient privacy is a primary value.”