Traditionally, hospitals and health systems have experienced significant challenges in finding insights from data at scale, because their data universes are so complex. A standard health system has a huge volume of data from many different sources.
As an example, data related to a procedure such as surgery and postoperative follow-up comes from the HIS, inpatient EHR, perioperative system, genomics, lab, pathology, imaging , emergency EHR and other data. Furthermore, each source has unique formats, data types, and data elements.
If service line leaders, clinicians, and administrators want to find insights into surgical success rates, they need to navigate through data from all of those sources to find correlations and outcomes. provides analytical information.
For example, a clinician might want to know if there is a correlation between a patient taking a certain postoperative pain medication and the likelihood of readmission and/or complications, essentially asked, “Should we use this drug in these types of patients in the future? “
To get an answer to that question, the clinician needs to understand the entire data warehouse of the health system, which is of a very high standard.
“To address this challenge, the typical approach is that health systems use teams of data analysts to which clinicians send these types of questions and data analysts then having to bring that universe of data together, and that takes a lot of time and energy and expertise,” said Josh Rubel, chief commercial officer of MDClone, a provider of analytics and aggregation data technologies. data analysis, interpretation.
He continued: “And analysts are faced with an increasing number of requests, which creates a bottleneck. “In that example, if a surgeon had an interesting question about a particular pain reliever, she was forced to line up with whoever else was asking the question. The process is inherently slow and mediated, so it’s not scalable.”
To discuss potential solutions to these challenges and dive into the surrounding technologies, Healthcare IT News Rubel interview. He has a lot to say.
Q. For those who haven’t fully caught up with technology, please explain what aggregated data is and how it can be used in healthcare.
ONE. Aggregate data is non-human subject data. Well aggregated data, especially in healthcare, is data pulled from original or real data that tells the same story as real data, but doesn’t contain real subject data People.
In healthcare, with an important emphasis on patient privacy, aggregated data significantly increases the number and types of users, especially external users, who may interact with data. For example, with powerful and accurate aggregate data, health systems can grant data access to algorithm developers to train models to predict disease progression.
Q. What do healthcare CIOs and other health IT leaders need to know about aggregated data? The news here should have their attention?
ONE. Health IT leaders understand how valuable their data is, and they want to leverage that data more – internally and externally. The reason to be excited about aggregated data is the promise of a broader and more extensive use of data.
Aggregated data enables providers to drive better and faster therapeutic development through their technology or life science partners and create more quality innovations by partnering with third parties to improve performance and accelerate upcoming research from academic institutions.
Q. Please give an example of how a provider organization can use aggregated data to discover, discover, or collaborate to improve patient health.
ONE. The US Department of Veterans Affairs has developed an innovative initiative called ARCHES, in which MDClone is implemented as core infrastructure. The VA ARCHES program is using aggregated data to partner with several third-party companies on a program to help understand patient behavior and improve procedures and strategies for suicide prevention. .
Because the data is aggregated, the VA can securely and easily share it with external organizations that are developing models to predict which veterans might try to kill. their life. Without aggregate data, this kind of collaborative effort would be difficult.
We hope to see more programs like this in the VA and elsewhere, all enabled with reliable, accurate aggregate data and privacy protection.
Q. Please give one more example of how a provider organization might use aggregated data to discover, discover, or collaborate to improve patient health.
ONE. Washington University in St. Louis and the Ottawa Hospital in Canada wanted to look at the data relevant to the sepsis predictive model and sepsis care in both their settings, and they were interested in making comparisons between location.
In the old-fashioned way, they could probably come up with a clinical study agreement and start sharing data with each other over a period of several months. Instead, in two phone calls, the organizations were able to look at each other’s aggregated data.
No data sharing or data usage agreements must be signed. They did not consider human subject data, and together they built a joint study of the sepsis and sepsis care model after about two hours of interaction.
This type of collaboration is relatively unprecedented from a speed and scale standpoint for large-scale academic institutions working together. Synthesis is a game changer for this type of cross-institutional research.
Q. How does your company’s technology enable the use of aggregated data for supplier organizations?
ONE. MDClone is focused on maximizing data privacy and data utility in healthcare. With over 20 deployments worldwide, MDClone’s core service, the ADAMS platform, enables agile and high-speed data discovery to drive insights.
A distinct capability of ADAMS is to generate our aggregated data for precise cohorts, treatment areas, and populations of interest. The platform includes the ability to create and explore aggregated data for non-technical end users.
In service organizations like VA or Intermenez Health or Sheba in Israel, our fusion engine is used hundreds of times a day to help find opportunities to improve quality, performance and overall health. body.
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email the writer: [email protected]
Healthcare IT News is a publication of HIMSS Media.
