The evolving COVID-19 pandemic has forced the healthcare system to find new ways to meet the needs of affected patients with unprecedented speed, agility, and efficiency. Although advanced, cutting-edge data analysis has the potential to provide healthcare professionals with the tools needed to quickly answer urgent medical questions, they rely on large-scale access to real-world data. Hospitals and healthcare systems help provide the data volume needed to realize their full potential in this health data revolution.

Thanks to advances in machine learning, we can now analyze millions of medical cases in minutes. This speed was unimaginable five years ago. Hospital systems across the country, including MedStar Health, where I work, have begun to responsibly share a large number of de-identified patient data repositories, which is the fuel to promote this faster and more representative medical research institution. Our positioning is to ensure that aggregated, de-identified patient data is used for the public interest to quickly and accurately find answers to the most pressing medical questions.

Currently, 20 health systems across the country are pooling resources to apply information obtained from interactions with doctors, laboratories, and medical equipment. But we need more hospitals to participate to further realize the promise of generating better insights to improve patient care and find faster treatments. The advantages of putting together large, generalizable data sets are endless. Here are three to remember.

First, we now have the ability to discover trends and connect information from seemingly unrelated cases by applying advanced analytics, artificial intelligence (AI), and machine learning. Connecting these key points can provide greater diagnostic accuracy or new insights into the performance of treatment or clinical practice in the real world. E.g, A recent study It shows that the cardiac ultrasound images evaluated by artificial intelligence can predict the mortality of COVID-19 patients, even if the same image explained by human medical experts cannot be predicted.

Second, a scalable data platform provides clinicians and researchers with speed advantages. If we have enough combined data at hand, we can shorten the time required to solve emerging and pressing medical problems. Due to concerns about rare side effects, please consider suspending the launch of the COVID-19 vaccine earlier this year. With the help of correct data sets across multiple healthcare systems, we can analyze the unidentified medical records of all people who were vaccinated at the time in less than a day, and determine possible causes in a fast and effective manner.

Finally, large data sets allow us to include de-identified data on patients from different communities, regions, and ethnicities. Clinical trials are notorious for not including enough participants from underrepresented communities. Medical research from real-world datasets is more likely than ever to effectively represent our communities across the country. The study of data from different communities can accelerate our understanding of how social determinants affect health.

Researchers like me are very excited about the advancement of health data science and the role that academic health systems play in improving everyone’s health. Machine learning has shifted our research focus from “How do we get the data we want?” “What questions can we ask about this data today?” This is why MedStar Recently joined Become a member of Truveta along with other healthcare systems, the company is helping to realize this health data revolution. The health care system involved is monitoring the proper and ethical use of the data.

Due to the limitations of electronic health record sharing and collaborative work methods, data in healthcare is too scattered, incomplete, or different in disconnected systems. As healthcare professionals, we understand that the public cares about how their personal medical data is processed. However, the health care system has a long history and a good record as the responsible steward of these data. It is supported by the law and will be severely punished if violated. We are in a unique position to ensure that patient data is protected and used only for legitimate academic purposes.

Together, we can apply this method to the implementation of data science, not only to optimize our approach to address the current needs of patients, but also to reshape the future of medicine. Healthcare leaders should start a dialogue with their CTOs and data scientists, and study how their systems can work with other organizations to unlock the possibilities of this evolving health data revolution.