Jewish General uses self-service platform, synthetic data to democratize analytics
Photo: Jewish General Hospital
Jewish General Hospital in Montreal had a problem with its patient data: Despite having plenty of it, the process of extracting insights that improved patient care was arduous and onerous.
THE PROBLEM
It has a large number of staff who are end users of data at Jewish General Hospital and the parent health system, CIUSSS du Centre-Ouest-de-l’Île-de-Montréal. These stakeholders include operational teams focused on improving efficiency and reducing delays, clinical teams looking at clinical quality improvement projects, and a thriving research community at the research organization, the Lady Davis Institute.
"The need for data is constant, and our ecosystem of data sources is quite varied, and in some cases difficult to access," said Dr. Justin Cross, chief digital health officer at Jewish General Hospital. "As in many health systems, data from these source systems has been brought into a centralized data warehouse. From there, it can be granted to the appropriate stakeholders when access conditions are met.
"This process, unfortunately, requires technical knowledge and database skills that most of our data end users simply don’t have," he continued. "Due to this technical need, the data warehouse is managed by a small team of data engineers and data analysts who do have this skill set and can build out views for those with the permissions to have access to source data."
The process works, but the lead times to formulate a question, transmit the question to the appropriate approver, and then structure a technical request for the internal data team has created a long road for data access, in particular for researchers.
PROPOSAL
Jewish General Hospital decided to address this problem with the Adams platforms from health IT vendor MDClone. The platform offered a tool designed to make it possible for anyone with an idea at the institution to be able to ask a question and get results.
"We know good ideas can come from anywhere, and especially from those who may not traditionally be in roles focused on operational efficiency or quality improvement," Cross noted. "The staff working on the frontlines may be noticing things that lead them to consider questions from a completely different lens from that of an internal data team.
"It is absolutely critical that a multi-disciplinary team be included in the planning, design and implementation of a system like this to get maximal value from the platform."
Dr. Justin Cross, Jewish General Hospital
"We wanted to leverage the strength of different viewpoints from across the organization and focus them on our common goal of improving the quality of services we deliver for our patients," he continued. "We wanted our healthcare delivery teams to be able to quickly access the platform, create a query on something they have been seeing in real time, and quickly get answers back that could suggest that a real signal is present."
Similarly, for the researchers, staff wanted them to be able to quickly query the institution’s data repository to see if a research cohort of interest exists.
"The special element that makes this possible in a manner that protects patient privacy is the MDClone Adams platform’s synthetic data mode," he explained. "In response to a query, the Adams platform is capable of dynamically generating a completely synthetic data set from the original data. This synthetic data set is statistically similar to the original data, but completely synthetic – not simply de-identified.
"Because of this, we are able to use the synthetic results to identify whether a signal of interest exists, and if so, the data end user can then go through the required approvals to access the real underlying data," he continued. "This greatly accelerates initial idea validation and focuses the time resources involved in the real data approval process for those initiatives that have shown signals in the synthetic analysis."
MEETING THE CHALLENGE
Jewish General Hospital is in the initial phase of the platform going live; it launched the system two months ago. To implement the system, staff established a multi-disciplinary working group that included the MDClone team, staff from the hospital's digital health team, the IT team, and subject matter experts who knew the source systems inside and out.
This team led the technical implementation as well as the data extract and load process. Staff have focused primarily on clinical data at this point, but will soon be expanding to other sources of data.
"The Adams platform will democratize the use of data by allowing for exploration of data using basic human language to build data sets in a simple and intuitive way; knowledge of SQL or other database skills are no longer needed," Cross explained. "After receiving appropriate training and authorization, the tool is available to both our clinical teams as well as our administrative ones."
RESULTS
Jewish General Hospital is only in the initial phase of training its community on the tool and identifying pilot users for the new platform.
"We already have teams that want to look at various factors that could affect: length of stay, access delays, home and community care delivery optimization, hospital acquired infections, STEMI care, mental healthcare optimization, and more," Cross said.
ADVICE FOR OTHERS
"Embarking on a large data project such as this is not only about the technology – it's also the people and processes involved," Cross advised. "It is absolutely critical that a multi-disciplinary team be included in the planning, design and implementation of a system like this to get maximal value from the platform.
"Data needs to be validated and useful to the end users, and a feedback loop needs to exist for continuous improvement of the platform," he concluded. "Lastly, adequate support needs to be provided to clinical teams that hope to make use of a tool such as this. They will often have fantastic ideas and they need to be supported with appropriate project management support when an actionable idea materializes."
Follow Bill's HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.