For many, precision medicine calls to mind cutting-edge technologies like genomic sequencing, machine learning, and artificial intelligence: ultra-high tech for ultra-keen diagnoses. These aspirational technologies are poised to play a crucial role in modern healthcare, but their impact is precluded by logistical problems around data generation, storage, and transmission.
The Precision Medicine Initiative (PMI) calls attention to such information roadblocks hampering the healthcare system. Its mission — “to enable a new era of medicine through research, technology, and policies that empower patients, researchers, and providers to work together toward development of individualized care” — boils down to two things: better data and better data distribution.
Take genomic data, for instance. Geisinger assistant professor of genomic medicine Nephi Walton, MD, told Healthcare IT News that there’s already lots of valuable genomic data available — just not where medical practitioners can access it. “You have tons of data that tells you how [patients are] going to react to medications, what things they’re going to have to look out for in the future,” he explains, “and it just doesn’t go anywhere right now.”
Vendors in the healthcare sector are integrating with embedded business intelligence (BI) solutions to turn their products into highly connective data hubs.
This means that SaaS companies don’t have to be at the leading edge of medical research to support the PMI. Vendors in the healthcare sector are integrating with embedded business intelligence (BI) solutions to turn their products into highly connective data hubs. BI facilitates data sharing between systems, fosters better medical insights, and can even be leveraged to improve data quality, all of which culminates in better care. Here’s how BI is already helping to make medicine more precise.
One of the virtues of business intelligence software is its ability to connect to a myriad of data source types. Exago BI, for example, connects to more than a dozen different types of databases (structured and unstructured) as well as more than a half-dozen different object types, including tables, views, stored procedures, database functions, parameterized SQL statements, web service methods, and .NET assembly methods. This kind of connective flexibility makes it possible to pull data from a wide breadth of systems into one central hub, such as a SaaS application.
Newport Credentialing Solutions, producers of a cloud-based credentialing and provider enrollment application, found that introducing BI to their product enabled their customers to combine data from a variety of sources, including billing, HR, privileging, and central verification office systems. These systems do not interface with each other directly, resulting in lots of manual data entry and increased risk of human error. Bridging this connectivity gap not only improved organizations’ overall efficiencies but also paved the way for data quality improvements.
Organizations are often surprised to discover business intelligence’s role in data quality control. BI software, by granting wider access to the data in question, passively surfaces quality issues to stakeholders, who are often quick to correct the issue at its source.
George Firican, Data Governance and Business Intelligence Director at the University of British Columbia, is a major proponent of capitalizing on this benefit. “[BI solutions] really help to raise awareness and build consensus and help create that stakeholder sponsorship,” he says. “They put front and center the data quality issue in your report. You notice it, you don’t like it, you want to do something about it.”
This is exactly the trend Newport Credentialing began to see among its customers. Stakeholders would spot inconsistencies and mistakes in their BI-enabled product, CARE, and then use CARE’s data-writing capabilities to correct records in connected systems.
David Meier, VP Technology at Newport, says he and his team realized they had a role to play in provider data management. “Organizations need to centralize this data somewhere,” he rationalizes. “It can’t be in a hundred different systems throughout the organization, and you can’t filter on a location if you have fifty different ways of spelling it.” As medical systems grow more interconnected and stakeholders work to reconcile conflicting records, data quality will improve as a natural result.
Unmitigated access to clean, authoritative data paves the way for BI’s primary contribution to precision medicine: data analysis. As Walton reveals of genomic data, mere access to the right information does not guarantee positive outcomes. “We have results that would have been classified differently, depending [on] which lab they went to,” he says. Even well-studied genes like BRCA1 and BRCA2 have hundreds of variants. BI could, in this case, be used to distinguish the 22% of variants that might affect medical management from the 44% which should not, helping doctors interpret clinical test results.
Clinical decision support hinges on timely access to the right information. Alerts, dashboards, and reports embedded within healthcare applications can all help improve the quality and precision of care. Regularly scheduled reports can help medical providers stay synchronized in their practices and policies. And, perhaps most crucially, BI can unearth trends and correlations contributing to medical research and patient care.
BI is an asset to those medical applications seeking to support the PMI and empower its customers to garner data insights across diverse systems. If interoperability and individualized care is the future of modern medicine, BI is a stepping stone on the path to that goal. Medical SaaS providers can help accelerate the movement by connecting healthcare providers and equipping them with the data they need, when they need it.