A leading US nonprofit academic health system deployed Harrison.ai's Comprehensive Care platform, an AI triage tool for obstructive hydrocephalus (OHCP) on non-contrast CT head studies, and captured more than $100,000 in Medicare New Technology Add-on Payment (NTAP) reimbursement across its six-hospital network in roughly four months.
The deployment centers on Harrison.ai Comprehensive Care (formerly marketed as Annalise.ai), which analyzes every NCCT head and raises both passive and active alerts when OHCP is suspected. The device received FDA 510(k) clearance in September 2023 and holds Breakthrough Device designation, making it the first AI OHCP triage solution. That Breakthrough status qualified the device for Medicare's NTAP pathway, paying an add-on of up to 65% of the technology's cost on top of the standard DRG for admissions through September 30, 2027.
The customer is an integrated, nonprofit academic health system serving communities across the United States. Spanning six hospitals, more than 1,000 acute-care beds, and over 250 outpatient sites, it runs on Epic EHR and reads roughly 23,000 CT brain studies each year. OHCP is comparatively low-frequency but competes for attention on busy worklists, exactly where an AI triage and notification add value: for a network reading thousands of NCCT head studies a year, moving these studies to the top of the worklist quickly and consistently is both a patient-safety priority and an operational one.
Once the solution was live, reimbursement accrued quickly. One network site alone captured over $12,000 across 50 confirmed inpatient encounters, with each qualifying patient receiving the full $241.39 reimbursement. Network-wide, the total passed $100,000 in about four months, all routed automatically through Epic EHR. Because every dollar is an add-on to the DRG, it closes the gap on reimbursement the network was already generating from scans performed, with near-zero added radiologist effort.
The network built an Epic-native pipeline to operationalize capture. A cross-functional working group — radiology informatics, IT and PMO, HIM coding, revenue cycle, compliance, and the billing office — stood up a workflow that carries a case from the scan to payment largely on its own, with a safeguard at each step. Cases are captured automatically based on eligibility criteria and order, confirmed by a coder, and protected by checks that make it hard for revenue to leak, yielding up to $241.39 of net-new payment per eligible case on scans already being performed.
Beyond the dollars, faster triage of critical findings helps care teams reach the right patients sooner, easing pressure on radiology as imaging volumes continue to climb. Because the whole workflow lives inside Epic, the model does not get stuck at one site; it repeats across every eligible hospital in the network, strengthening the case for clinical AI each time. The next step is closing out the remaining manual gap to help streamline the process further.
This case study has been anonymized at the customer's request; the health system is not named. Harrison.ai Radiology solutions were previously marketed as Annalise.ai solutions. Reimbursement figures reflect amounts realized over the stated period and are not a projection of future results.