Danville, California — RecovryAI has completed patient participation and clinical data collection in a pivotal study evaluating its artificial intelligence-powered virtual care assistant for patients recovering from hip and knee replacement surgery.
The milestone, known as last patient out, concludes the patient phase of a 15-month prospective study conducted at three U.S. orthopedic centers.
The trial enrolled 525 patients and generated more than 43,200 conversations between patients and the company’s clinical AI system. The data will support RecovryAI’s planned De Novo submission to the U.S. Food and Drug Administration later this year.
“Last patient out is not the finish line, but it is a significant milestone in a rigorous, multi-site pivotal trial,” RecovryAI Co-Founder and Chief Executive Officer Scott Walchek said.
“It reflects an extraordinary effort by our clinical partners, patients and team, and gives us the evidence base to begin the final adjudication and statistical work supporting our planned FDA De Novo submission,” Walchek added.
The study was conducted under institutional review board oversight at OrthoArizona in Scottsdale, Arizona; Kansas Joint & Spine in Wichita, Kansas; and Mercy Medical Center in Baltimore.
RecovryAI’s patient-facing virtual care assistant evaluates whether a patient’s reported recovery is consistent with the expected postoperative course.
The system can provide guidance when recovery appears normal or alert the patient’s care team when it identifies a potential deviation, along with relevant clinical context.
The study’s primary endpoint measures the agreement between the AI system’s classifications and recommendations and assessments made by experienced orthopedic surgeons.
Each eligible conversation is reviewed independently by three physicians in a blinded format, resulting in more than 129,000 individual physician assessments.
RecovryAI said the results will provide a direct measure of concordance between the virtual care assistant and independent physician evaluations.
Following completion of patient participation, the company will conduct final physician adjudication, lock the study database and complete its prespecified statistical analysis.
“We participated in the pivotal trial because postoperative demand is outpacing available clinical capacity,” said Dr. Ken Schmidt, an orthopedic surgeon at OrthoArizona and principal investigator in the study.
“We’re confident that AI can safely carry a meaningful share of that workload, but without rigorous evaluation and FDA authorization, it cannot earn our trust as part of patient care,” Schmidt added.
The prospective trial is paired with a retrospective analysis involving 579 additional patients, bringing the total number evaluated under the protocol to 1,104.
The retrospective component examines the potential effect of the virtual care assistant on clinical workflows and downstream healthcare use.
The study also includes a stress-testing dataset of about 1,500 conversations designed to assess the system’s performance in uncommon and clinically complex situations that may not occur frequently enough in a prospective trial.
The simulated conversations incorporate different clinical conditions, underlying health problems, communication styles and levels of health literacy. Each is based on a real physician-reviewed interaction and independently assessed for clinical plausibility.
RecovryAI received FDA Breakthrough Device Designation for the virtual care assistant earlier this year and is seeking De Novo authorization as a Class II medical device.
The study design, primary endpoint and physician-review process were informed by an earlier pilot study and discussions with the FDA that began in 2024.
The pivotal trial was conducted as a non-significant-risk study, with the investigational technology operating under physician oversight.
“There is a meaningful difference between AI that supports a clinician and AI that engages a patient with clinical guidance,” said Dr. Benjamin Ma, Chair of the Department of Orthopaedic Surgery at the University of California, San Francisco.
“The latter must be evaluated as a medical device, with evidence sufficient to establish that it performs safely and reliably,” Ma added.
RecovryAI said its virtual care assistant is designed to manage routine postoperative conversations while escalating potential complications or unexpected recovery patterns to healthcare professionals.
If authorized, the technology could help reduce postoperative workloads while retaining physician oversight and allowing care teams to focus on patients requiring more direct clinical attention.
