The first time I saw the MDClone platform, I felt that my dream had come true. Over the years, we couldn’t provide a solution for our researchers to be independent. This is the reason that I immediately saw the value and made a decision to recommend the CEO to collaborate with MDClone and adopt the platform as the first organization in Israel and in the world.”
— SARA TZAFRIR, CIO, RAMBAM HEALTH CARE CAMPUS
Rambam Health Care Campus was established in 1938 under the British Mandate as the Governmental Hospital. It became an Israeli governmental hospital with the founding of the State of Israel, and over the last 80 years, it has become world renowned for experience and expertise in a wide range of clinical and research endeavors.
Rambam is a 1,000-bed, world-class teaching hospital with a diverse patient population, as it is the major tertiary (referral) medical center for all of Northern Israel, including 12 district hospitals and defense and peacekeeping forces stationed in the region. Serving more than 2M residents and others referred from all over Israel, the Mediterranean region, and around the world, Rambam is strategically located in Haifa on the Mediterranean coast and plays a critical role in the healthcare of the region’s residents, in addition to making a major contribution to the economy of the north.
Rambam, with the lead of the Digital Information Technology Division, has established itself as a pioneering force in the growing field of Big Data for medical applications, and the hospital is a leader in this field both in terms of data collection and data analysis. Rambam’s Digital Information Technology Division established a computerized database of medical records in the early 2000s, and today the database contains more than 20 years’ worth of detailed data from patients treated at Rambam since then. Now, the CIO’s main goal has been to enable Rambam’s researchers to independently study and analyze data.
Rambam’s electronic medical record (EMR) database contains more than 2.5 million unique patient health records representing 25 million unique visits to the ER and to the hospital’s different departments and outpatient clinics. Rambam’s Digital Information Technology Division — along with the epidemiology department, who has extensive knowledge in healthcare information and data — has made huge efforts to create valid, complete, and accurate standardized data. Because a large share of the data is entered by humans and is therefore susceptible to error, Rambam sought to validate the data in order to ensure that answers to queries will be as precise as possible.
Initially, Rambam faced challenges such as:
IRB Approvals
Running database analyses based on hospital records and information systems was previously a major task for Rambam. Real patient data needed to go through an institutional review board (IRB), delaying typical study start times by several months.
Structured and Unstructured Data
Numerous data types are entered into Rambam’s central database every day, both structured and unstructured, such as MRI and CT scan images, EMR tables, bloodwork results, and text from medical reports.
Necessity of IT Staff
Rambam had to work with IT staff to be able to run queries, leading to a time-consuming and convoluted process.
“I had to work closely with the IT department, back and forth. This process could have taken me months and months, because these people are all so busy, and it’s hard for me to know what data is available.”
Although the hospital had full, interconnected electronic medical records, accessing the data was difficult and time-consuming. It required IT staff to provide the data to the researcher — and with several iterations.
HEADQUARTERS
Haifa, Israel
SIZE
80 Medical Departments and Clinics
1,000 Beds
More than 5,000 Employees
12M Diagnostic Tests Annually
36,000 Surgeries Annually
220,000 ER Visits Annually
Serves 2M+ Residents of Northern Israel
Referral Center for 12 District Hospitals
SPECIALTIES
Internal Medicine
Surgery
Gynecology
Children
Medical Imaging
Mental Health
Laboratories
Dentistry
WEBSITE
rambam.org.il
In 2017, Rambam became the first health system to implement MDClone’s platform.
Using MDClone, Rambam’s big data operations could immediately convert personal data into synthetic data, protecting patient confidentiality. The hospital’s management mandated the use of anonymous, synthetic data to alleviate any privacy concerns.
“Studies comparing real data files and synthetic files show that the results are similar,” said Ronit Almog, MD, Director of Rambam’s Epidemiology Unit.
MDClone gives users such as research physicians the ability to access the data in a simple manner without the need for the IT department. Rambam clinicians and researchers can now easily receive answers to such queries as:
“During the past five years, what were the lab results of cardiology patients on day two of treatment with a particular drug?”
“Do we have enough patients that meet three specific criteria in order to conduct a clinical trial?”
“In the last two years, how many chronic kidney disease patients were readmitted to the hospital after an initial admission and follow-on treatment plan?”
“What is the door-to-balloon time in primary percutaneous coronary intervention in ST elevation myocardial infarction?”
These and many other questions can be answered quickly and accurately, thanks to big data analysis of the hospital’s vast data bank. Excellent tools have also been developed for retrieving and analyzing the data at Rambam. Substantial resources have been invested to ensure that the system is user-friendly, so doctors and researchers can easily retrieve high-quality data by themselves.
“Rambam’s difficulties accessing data were completely overcome by the MDClone platform, and it allowed the doctors to access data and get answers to the questions that they want to ask on an almost immediate basis.”
Today, Rambam engages in big data and AI collaboration with startups and industry, as well as with academic institutions, HMOs, the Health Ministry, and other hospitals. Researchers from outside Rambam can access the data by partnering with Rambam researchers and receiving approval. Both internal and external users benefit from Rambam’s high-quality medical data, both synthetic and real, which is unique in Israel.
“The use of synthetic data allows us to test, like in a sandbox, certain hypotheses before we decide on the exact protocol of a study. This is extremely helpful, extremely efficient, and also allows the individual doctors and researchers to do it,” explained Rafael Beyar, MD, former Director of Rambam Health Care Campus.
Now users can, with a few clicks within the MDClone ADAMS Platform, see their data and make adjustments on the fly, shortening the research process from months to hours.
“What I really enjoy about MDClone is the very simple and intuitive platform. It’s very easy to understand, and it didn’t take me long to figure it out. It’s quite simple, it’s quite intuitive, and if you work with data and with patients, you easily know what the questions are that you want to know and how to ask them, then how to receive the output from the system.”
Rambam was the beta site for MDClone and since 2017 has been influential in perfecting this sophisticated big data tool and making the platform as user-friendly and effective as possible.
Researchers at Rambam initially conducted five studies in which they used MDClone to build patient cohorts and extract synthetic data for analysis before returning to MDClone to extract original data for validation of the results. In each case, the synthetic data provided a close estimate to real data results.
The data access process Rambam used was transformative for the health system, providing a self-service model for researchers to quickly test hypotheses using synthetic data and to use PHI (with an IRB) only when needed, prior to publication or the treatment of patients. Because the synthetic data closely resembles PHI, in many cases — including in quality analyses or other hospital operations-oriented initiatives — there was no need to ever use PHI.
Rambam aims to be able to individually predict possible outcomes for certain patients for each intervention based on a history of patients with the same types of diseases.
“This is personalized medicine at its best. I think MDClone is a very strong and important tool in creating the ability to access the data, and I think we are right now using only very little of the power that we have in data. We are looking to the future of digital health, data analysis, and machine learning, as well as the ability to search different aspects related to a disease to identify individual patients with certain diseases to actually predict the outcome,” said Rafael Beyar, MD, former Director of Rambam Health Care Campus.
With MDClone, Rambam can tap into their goldmines of data and explore data related to:
Patients arriving in the emergency department
Patients admitted to Rambam’s various departments
What happens to those patients after discharge
Whether certain patients are readmitted
Whether there are any issues later on regarding these patients’ treatments
“Rambam’s ongoing use of MDClone will provide valuable insight for organizations who want to leverage their own data assets more efficiently and safely than ever before,” said Robert Wartenfeld, MD, MDClone’s CMO and VP of Product Strategy.
The use of synthetic data allows us also to test certain hypotheses before we really decide on the exact protocol of a study we would like to work, so this is extremely helpful, extremely efficient, and allows the individual doctors and researchers to do it themselves.”
Dr. Rafael Beyar, Former CEO and Director General, Rambam Health Care Campus
Don’t miss out on our latest insights. Sign up to MDClone emails and updates today and get exclusive updates, case studies, research findings and more, straight to your inbox.
See ADAMS in Action with Exploratory Research Findings Sent Right to Your Inbox.
