Newsbytes

Create PDF

—Renee Caruthers

Regenstrief Institute develops framework for assessing patient-matching algorithms

The Regenstrief Institute recently announced that a team of research scientists has developed an eight-point framework to assess the validity and accuracy of algorithms for linking patients’ medical records from disparate sources within and between health systems, known as patient matching.

“We recognize that the need for patient matching is not going away and that we need standardized methods to uniquely identify patients,” said Shaun Grannis, MD, MS, who led the project as Regenstrief’s vice president for data and analytics, in a press release. “Current patient-matching algorithms come in many different flavors, shapes, and sizes. To be able to compare how one performs against the other, or even to understand how they might interact together, we have to have a standard way of assessment. We have produced a novel, robust framework for consistent and reproducible evaluation. Simply put, the framework we’ve developed at Regenstrief provides a ‘measuring stick’ for the effectiveness of patient-matching tools.”

The framework’s eight-point approach, detailed in the Journal of the American Medical Informatics Association (Gupta AK, et al. 2022;​29​[12]:2105–2109), is a set of guidelines for creating and evaluating gold-standard data sets for measuring the performance of patient-matching algorithms. Steps one through four address recommended manual-review reporting elements for preparing a gold-standard data set and record pairs. These steps focus on data set descriptions, data preprocessing, record pair grouping, and procedures for sampling and matching record pairs. Steps five through eight address the training of human reviewers, inter-rater reliability measures, adjudication processes, and descriptions of reviewer characteristics.

“Patient identity is the last gaping hole in our health infrastructure,” said Dr. Grannis, noting that unlike many other industrialized countries, the United States does not have a national patient identifier, instead leaving the creation of unique patient identifier tools to researchers and commercial entities.

Ibex prostate cancer solution gets CE mark under IVDR

Ibex Analytics has reported that Galen Prostate is now CE-marked under the European In Vitro Diagnostic Medical Devices Regulation for supporting pathologists in the primary diagnosis of prostate biopsies.

Galen Prostate uses artificial intelligence to analyze biopsies prior to pathologist review, providing pathologists with diagnostic insights to guide diagnoses. The product’s algorithms were trained on large data sets, enriched with rare prostatic malignancies, from multiple pathology institutes worldwide.

“Galen helps pathologists diagnose cancer, provides additional insights, including a Gleason score, tumor size, and associated morphologies for each cancer slide, and offers decision-support tools to help accelerate diagnostic turnaround and reduce subjectivity,” according to a company press statement.

Galen Prostate is available for research use only in the United States.

HHS names first organizations approved to implement TEFCA

The U.S. Department of Health and Human Services has released the names of the first six organizations expected to be designated as qualified health information networks under the voluntary Trusted Exchange Framework and Common Agreement. TEFCA is an outgrowth of the 21st Century Cures Act, which required that HHS establish an infrastructure model and governing approach for nationwide health information exchange.

The organizations—Epic Systems, CommonWell Health Alliance, eHealth Exchange, Health Gorilla, Konza, and Kno2—will officially be designated as QHINS once they are fully onboarded, according to an HHS HealthITbuzz blog post.

The organizations were recognized at an HHS event last month “for their willingness to voluntarily step up and meet the rigorous TEFCA eligibility requirements, terms and conditions of TEFCA participation, and commitment to a 12-month go-live timeline,” according to the blog post. The QHIN applicants have networks that collectively cover most U.S. hospitals and tens of thousands of providers, and they process billions of transactions annually across all states, HHS reported.

The six QHINs have committed to begin exchanging data by the end of this year, Micky Tripathi, PhD, ONC national coordinator for health information technology, said at the HHS event.

The nonprofit Sequoia Project, which serves as the Office of the National Coordinator for Health Information Technology’s recognized coordinating entity for TEFCA, approved the six QHIN applications.

Dr. Aller practices clinical informatics in Southern California. He can be reached at raller@usc.edu. Dennis Winsten is founder of Dennis Winsten & Associates, Healthcare Systems Consultants. He can be reached at dwinsten.az@gmail.com.