Independent Audit Says Veda’s AI Precision Exceeds 90%, Solving Ghost Networks and Payer Network Attestation Challenges
Veda is paving the way for improved data quality, transparency, and accountability in healthcare through continuous validation and testing of our AI-powered solutions. Our scientific rigor commits us to continuously testing our methodology and we believe all AI-powered data solutions should undergo an unbiased independent validation of their data. Learn about our approach to healthcare data challenges and the third-party study performed by Erdős Institute proving our data accuracy.
Provider Data Inaccuracy
Provider data management is inherently flawed. The information found in provider directories is often manually updated, the scope of required information keeps expanding and information changes often; practices move, physicians change practices, and contracts between practices and health plans expire. Multiple industry reports state between 20% and 30% of directory information changes annually.
With provider data accuracy rates of 90+%, the study highlights the potential of automation and machine learning in achieving high levels of data accuracy
Reinforcing Commitment to Accountable AI-Powered Solutions in Healthcare
Inaccurate provider directories and networks full of “ghosts” (or unavailable providers) aren’t just frustrating to patients making appointments, they’re making waves among policymakers. The bipartisan Requiring Enhanced & Accurate Lists of (REAL) Health Providers Act, introduced by U.S. Senators and Representatives calls to eradicate ghost networks that are impacting patients nationwide and states across the U.S. have followed suit with their own proposed regulations.
Vectyr Curated Dataset
To prove our products and approach to provider directory accuracy are best-in-class, the Erdős Institute conducted a blind third-party audit of Veda’s Vectyr product.
Vectyr is Veda’s curated dataset that powers all our provider data products. With Vectyr’s continuously monitored and validated data, Veda customers can quickly find correct provider information with the confidence of Veda’s optimal accuracy. Many back-office workflows—like directory management, credentialing, and claims—need access to accurate, up-to-date provider information. Our Vectyr product curates data from over 300,000 sources including NPPES, DEA, and state licensing organizations.
Why validate with impartial analysis?
As a leader in the industry, armed with proprietary solutions, we understand the key to solving complex healthcare problems lies in innovative technology. We’re taking the lead again, this time via rigorous third-party validation. By subjecting our technology to impartial analysis we’re taking a step forward in the evolution towards greater transparency.
Employing rigorous methodologies and independent sampling techniques, ensuring an unbiased assessment of provider directory accuracy? Sounds like our scientific approach to everything we do.
Additionally, having an independent institute like Erdős conduct the validation study safeguards against potential conflicts of interest and ensures the credibility and integrity of the findings.
Erdõs’ Method for Proving Accuracy
To gauge provider data accuracy, Erdős and Veda simulated a Centers for Medicare & Medicaid Services “secret shopper” audit. Callers attempted to make an appointment on behalf of a patient and collect information that would be necessary to do so: the phone number and location of the provider (which are typically major areas of inaccuracies). The audit provided a measure for the main appointment information and manual research was used to measure more detailed provider information.
To reduce bias in the CMS simulation, Erdős created a sample of NPIs for the measurement. The selection of the sample was aimed to be representative with respect to geographic categories of rural and urban and focused on stratified sampling by specialty. In the total sample, 184 NPIs were called. Of these 184 NPIs, 92 phone numbers and 118 locations could be assessed.
The call-based outcomes found phone and address accuracy are consistent at 90%. Moreover, Erdős found that additional Vectyr fields were also highly accurate. For example, the Vectyr database demonstrated accuracy levels of 99% for fields such as languages spoken. With provider data accuracy rates of 90+%, the study highlights the potential of automation and machine learning in achieving high levels of data accuracy.
Reinforcing Commitment to Accountable AI-Powered Solutions in Healthcare
With a commitment to accountable AI-powered solutions and five approved patents in the industry, we believe all healthcare data vendors need to think more rigorously about what “correct” data means. Attestation does not create quality data. Patients don’t need attested data, they need correct data. Therefore, data vendors must measure performance the same way patients do: making an appointment on the first try, with the correct information. We promise accuracy, and we deliver.
