Table of Contents
A voice-based AI voice assistant cardiac catheterization tool named Sofiya has been helping prepare patients for cardiac catheterization at a high-volume center in New York City, freeing up nurses to focus more on direct patient care.
How the AI Voice Assistant Cardiac Catheterization Pilot Performed
In a two-phase pilot study, the preprocedural call completion rate approached 90%. More than one-third of calls, which included the provision of instructions for the patient and collection of clinical information, were handled entirely by Sofiya without the need for escalation to a nurse, researchers led by Annapoorna Kini, MD, at Mount Sinai Hospital in New York, report in a paper published in npj Digital Medicine.
Estimated Time Savings
They estimate that using Sofiya instead of a nurse saved an average of 11 minutes per call, or the equivalent of 37.3 12-hour nursing shifts over the course of a year, a meaningful efficiency gain for a cath lab performing more than 16,000 procedures annually.
Why This AI Voice Assistant Cardiac Catheterization Tool Matters for Nursing Workloads
Amid shortages of healthcare workers, AI has been seen as a way to shift nurses, and in the future physicians as well, away from routine tasks like making preprocedural calls and back to the bedside working with patients, which could help improve healthcare workers’ mental health and wellbeing, Kini told TCTMD. “A lot of this mundane work can be taken care of by this conversational agent,” she said, adding that AI could eventually also take time-consuming tasks like completing charts and dictation notes off physicians’ to-do lists.
A Key Safeguard Built Into Sofiya
Sofiya was trained “with a lot of guardrails because this was first of its kind,” Kini noted, explaining that if patients ask about something not included in the AI knowledge base, they receive a call from a nurse. “Patients should not feel that AI is completely taking over their care as long as they know there’s a human in the loop and this AI agent is assisting the healthcare workers, so they are able to focus on more clinical work.”
How the AI Voice Assistant Cardiac Catheterization Study Was Designed
This study was a prospective evaluation of the initial use of Sofiya for conducting preprocedural calls at the Mount Sinai cath lab. Sofiya is based on a large language model and deployed on an agentic AI framework. The day before a procedure, Sofiya calls patients to provide instructions on diet and logistics around getting to the hospital and to collect required clinical information, including allergies and medications. If patients ask a question Sofiya can’t handle, a nurse follows up, and after the call, an AI-generated report is created and added to the patient’s electronic health record after nurse verification.
Two Rollout Phases
There were two 90-day periods involved in the rollout. The first phase was a stabilization period involving collaboration among nurses, physicians, and AI developers, while the second was led by nurses. Overall, 1,431 patients received 1,606 calls from Sofiya, 806 in phase 1 and 800 in phase 2.
Detailed Results From the AI Voice Assistant Cardiac Catheterization Trial
The overall rate of successfully completed calls was 86.4% in the first phase and 87.9% in the second. In phase 1 and phase 2 respectively, 36.6% and 42.6% of calls were completed without any human intervention, 37.6% and 33.5% required a protocol-driven callback from a nurse, and 12.2% and 11.8% were appropriately converted to a call with a human. Rates of refusal to speak with the AI assistant were 4.3% and 2.8%.
What Caused Incomplete Calls
Calls most commonly couldn’t be completed due to patients not answering or hanging up. An AI system reliability issue resulted in noncompletion in 6.0% of cases in phase 1 and 3.0% in phase 2. Most AI issues were technical in nature, with only six instances of AI hallucinations, meaning Sofiya made things up or provided incorrect information, leading to an incomplete call.
Patient Satisfaction With This AI Voice Assistant Cardiac Catheterization Tool
The researchers assessed patient satisfaction using postprocedural surveys among those who completed a preprocedural call with Sofiya. Overall satisfaction rates were high at 94.7% and 98.1% in the first and second phases, respectively. Some people “love to have a companion to chat with,” Kini said, noting Sofiya can have longer conversations with patients compared with the time nurses can dedicate to the task.
Expert Commentary on Augmentation Versus Replacement
Commenting for TCTMD, Thomas Maddox, MD, of WashU Medicine, said the study is “a good illustration” of how AI can augment current processes rather than replace the human element of care. He highlighted that the majority of calls in both study phases required some involvement from nursing staff. “It wouldn’t be correct to say, ‘Oh, this is replacing what the nurse is doing,’ but it certainly is augmenting what he or she is doing,” Maddox said, though he noted the time-savings estimates need further validation.
Implementation Challenges for This AI Voice Assistant Cardiac Catheterization Rollout
Asked about the challenges of implementing Sofiya, Kini pointed to the process of getting numerous committees within the health system, including those focused on legal and ethical implications, to sign off. The researchers also cited barriers including lack of knowledge about AI, concerns regarding reliability and accuracy, data privacy and security issues, worries about impact on patient relationships, and fears of job loss due to automation.
Cost Remains an Open Question
One issue that remains to be clarified is the cost of using AI for this purpose, Kini said, adding that once Sofiya can be streamlined into the electronic medical record, costs should come down.
What’s Next for This AI Voice Assistant Cardiac Catheterization Technology
Kini indicated that in the future, the AI assistant could likely expand into providing information to patients before discharge, making and changing appointments, conducting follow-up calls after a procedure, and guiding patients to cardiac rehabilitation. Sofiya may also be used for patients undergoing other procedures in the cath lab, such as those for peripheral or structural disease.
A Cautious but Optimistic Path Forward
“AI is here,” Kini said. “Everybody should embrace it and try to start using it where you think that it is appropriate.” She emphasized careful implementation, noting the team has already shown patients and physicians like it and is gradually expanding its use. Maddox, who serves on the FDA’s digital health advisory committee, said healthcare is “famously slow” at adopting new technologies, but AI is “definitely ready for prime time” for applications like callbacks and routine care coordination, with broader involvement in direct clinical decision-making likely to follow as rigor and safety standards continue to develop.
For more healthcare industry updates, insights and news, visit DistilINFO. Click here to subscribe to stay informed.
