As providers drive patient engagement initiatives, population health management programs and quality improvement projects, they're still stymied by challenges with patient identification.
In fact, many organizations have troves of electronic health records that can't avail themselves of analytics because they can't be matched with other records, according to a new report in the Journal of AHIMA.
In the article, "Applying Innovation to the Patient Identification Challenge," Lorraine Fernandes, president-elect of the International Federation of Health Information Management Associations, Jim Burke, EMPI and HIE practice lead at Himformatics and Michele O’Connor, services manager at data governance startup Collibra, spotlight "innovations that can move the healthcare industry beyond the traditional human resource-heavy, back-end retrospective approach to accurate, automated patient identification and record matching."
Those new approaches might include augmentation using data from outside healthcare – from credit bureaus and government programs, for instance – or better leveraging emerging neural network technology to sift through ambiguous patient ID information or analyze digital fingerprints or facial recognition data.
That said, "the key to innovation in patient identity goes beyond staying up to date with recent technologies – it involves a strategic data governance process,” said AHIMA interim CEO Pamela Lane.
“Once a solid plan is in place, professionals can leverage the digital assets, such as cloud-based services and other data services, to approach this issue in a complete manner," she said.
Real-time automation offered by the cloud is a central focus of the AHIMA article, and the authors see big promise for cloud technology's ability to ensure records stay up-to-date.
"The mainstream acceptance of cloud computing has opened an avenue to incorporate secure external data services into critical business processes such as patient registration, data exchange, and patient identification," they said.
"Cloud-based data services enable the infusion of referential or authoritative data that may come from large public databases outside healthcare, such as credit bureaus, loan servicing organizations, or telecommunications. These non-healthcare databases and associated business processes capture and validate identity data, update it continuously with each transaction, and retain the history of the person’s demographics."
That could help address one of the key hurdles to accurate patient matching: the fact that patients' demographics can change over time, and between encounters at different facilities.
"Real-time automation of patient matching with external data also addresses a critical latency issue associated with manual stewardship efforts, which typically don’t resolve the ambiguous linkages/tasks (those records not automatically linked by an algorithm) until days or months after a patient presents for care."