Customer Success Executive

Can ai-enabled outreach tools reshape how hospitals close care gaps? Analysis | By G Hatfield | June 01, 2026 Advocate Health's responsible approach is enabling the health system to follow up and treat patients with hypertension. Key takeaways. At the end of 2025, Advocate Health partnered with Hippocratic AI to help reach patients who were seen for elevated blood pressure in the hospital, and then didn't return for a follow up. The health system was able to reach out to 15,000 patients with hypertension care gaps to share why it is important to monitor hypertension and to walk them through how to properly check their blood pressure at home and provide that reading to their care teams. Leaders collaborated with marketing and consumer experience teams to write the script for the tool so that it complies with internal criteria and includes an introduction to the patient to tell them they are interacting with an AI agent or virtual assistant calling on behalf of the care team. As workforce shortages persist and CNOs brainstorm new ways to rework staffing models, the integration of AI into workflows shows great promise. However, it must be implemented correctly for it to live up to that promise. At Advocate Health, leaders are discovering the benefits of AI-enabled outreach tools and how to incorporate them into the broader AI strategy. According to Andy McWilliams, VP of AI clinical product development and co-chair of AI governance at Advocate Health, the health system's goal with AI is to, first and foremost, implement it responsibly. "We want to take an intentional, responsible approach to implementing AI and as we think about that from a workforce strategy standpoint, generally across the board we have a number of shortages across many different disciplines," McWilliams said. "We think of AI, when implemented appropriately and responsibly, as a force multiplier for our teams." Most recently, the health system has deployed a conversational AI tool to help reach patients suffering from hypertension. "[This tool] provides an example of where AI, when thoughtfully woven into workflows, can really offload some of the busy work [and] some of the more routine work so that our teammates can focus on more complex issues and focus on more time with the patients themselves," McWilliams said. Addressing care gaps. At the end of 2025, Advocate Health partnered with Hippocratic AI to help reach patients who were seen for elevated blood pressure in the hospital, and then didn't return for a follow up. "Elevated blood pressure [is a] very common condition," McWilliams said. "It's one of those conditions where we have very good evidence-based treatment guidelines, but across the board in the United States, untreated hypertension remains a very prevalent condition." Since the health system doesn't have the resources to be able to reach out to every patient with a care gap, they worked with nurse leaders and teams to build the AI agent that meets their criteria internally, McWilliams explained. That collaboration ensured that the tool passed the organization's criteria for safety and patient experience. The health system was able to reach out to 15,000 patients with hypertension care gaps to share why it is important to monitor hypertension and, when possible, to walk them through how to properly check their blood pressure at home and provide that reading to their care teams. The tool can also provide patients with resources for where patients can get their blood pressure checked in their communities, and then follow up with them to obtain that blood pressure reading. "As you have a conversation with a patient, oftentimes things will come up where we need to escalate that conversation or issue to our teams, and that was part of what we baked in and tested in this process," McWilliams said. "[We wanted] to make sure that as we uncovered issues we were able to get them to the right teammate at the right time so that the issue could be addressed." Both nurses and nurse informaticists were involved in building this pilot program, with nurses leading the charge as the end users incorporating the tool into their workflows. As the organization looks to scale the program, the nursing informatics team is critical for the design building process and for thinking through the workflow implications and training needs, McWilliams explained. "The important [thing] in any AI implementation is that last mile of implementation and making sure that it truly fits into the workflows and is actually a helpful aid and actually becomes that force multiplier, and isn't a barrier that sits in the workflow or creates friction," McWilliams said. Quelling skepticism. To ensure patient understanding and consent when using the AI agent, leaders collaborated with marketing and consumer experience teams to write the script for the tool so that it complies with internal criteria. The script also includes an introduction to the patient to tell them they are interacting with an AI agent or virtual assistant calling on behalf of the care team. McWilliams emphasized that the number of patients who don't want to interact with the AI agent is a smaller percentage than expected, which McWilliams attributes to transparency. "We've done a great deal of work engaging with our patients and other stakeholders across the health system to understand what it means to them for us to be transparent and accountable as we approach AI responsibly," McWilliams said. "[We're also] thinking through how [to] do more than just introduce via an AI agent that they're speaking with AI, but also provide additional content for folks and education more broadly on our approach." Gearing up for more. Initially, the pilot was meant to inform the decision to make this proactive outreach approach a standard part of care, McWilliams explained. The health system also wanted to see if it would improve care access along with the patient and teammate experience. "We were able to close care gaps for around 1,200 patients and connect with a larger number than that," McWilliams said. The pilot also helped the organization get the patients who couldn't report a blood pressure reading or those with continued hypertension to work with the centralized nursing teams to help treat them or resolve other issues that might have come up in conversations. "To us, that is very powerful, because that spoke to the improved access that comes from that force multiplier, as our teammates are able to address those more complex issues, where AI was offloading more routine tasks," McWilliams said. Patients also filled out surveys to share their feedback on the pilot, which according to McWilliams, has been positive. "The ability to ask questions and not feel like they were taking up one of our teammates' time because they could ask unlimited questions, and feeling that the experience was one that was very positive, helped them feel that they had a sense of agency around controlling their blood pressure," McWilliams said. In the future, the health system is exploring how to address other chronic conditions where proactive outreach and education are related to improving outcomes, such as heart failure, diabetes, and potentially COPD, McWilliams explained. "Those chronic conditions are highly prevalent [and] we have fairly good data to show that being on the right medications and having access points between your clinical visits improve your outcomes," McWilliams said. However, McWilliams emphasized that not every use case requires leveraging AI. "[We are] being very disciplined in selecting the right use cases," McWilliams said, "and then following that very methodical, intentional approach to make sure that we wire things up appropriately and we have the right escalation measures in place [and] the right workflows on the back end, and get to that point where, as we saw with hypertension, we get that force multiplier and improve access and experience." G Hatfield is the CNO editor for HealthLeaders.

Hippocratic AI launches Polaris 5.0 to outperform major frontier models on medical safety. Published. May 21, 2026 Hippocratic AI is taking aim at general-purpose frontier models with Polaris 5.0, a healthcare-specific voice AI system designed for clinical safety and real-time patient conversations. The company says the 5-trillion-parameter constellation model outperformed models from OpenAI, Google, and Anthropic across more than 50 healthcare benchmarks, including 99.95% accuracy in drug safety and 99.75% in clinical escalation across seven body systems. Polaris 5.0 was trained on more than 180 million real-world patient interactions and validated by 7,500 licensed clinicians. By focusing on a purpose-built voice stack, the system achieves a time-to-first-audio latency of 1.5 seconds, which Hippocratic AI says supports live patient care workflows. The architecture features a 700-billion-parameter core and specialized agents capable of Interdependent Document Intelligence. This allows the AI to cross-reference benefits policies with formularies to provide accurate co-pay quotes in a single conversational turn. Polaris 5.0 also introduces acoustic biomarkers that detect coughs or throat-clearing mid-sentence to assist in respiratory assessments. CEO Munjal Shah noted that healthcare requires an "experienced AI model" capable of navigating complex conversations at voice speed. Beyond clinical tasks, the model scored 100% on anti-bribery compliance for pharma and 99.1% on HIPAA-compliant authentication, significantly outperforming general-purpose realtime models. Current deployment data shows the system manages multi-lingual patient care with mid-call language switching between English, Spanish, and Mandarin without context loss. Its clinical escalation protocols now cover musculoskeletal, cardiovascular, and mental health presentations, routing urgent cases to human clinicians in seconds. Hippocratic AI Chief Science Officer Subhabrata Mukherjee stated that frontier models fail most core clinical voice workflows because they lack the rebuilt stack necessary for medical precision. Related insights. The Healthcare Technology Report is your comprehensive source for business news, investment activity and corporate actions related to the healthcare technology industry.

Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversations. Modular Team Discover what Modular can do for you Build the future of AI with Modular * Sign up today Signup to its Cloud Platform today to get started easily. Sign Up * Browse open models Browse its model catalog, or deploy your own custom model Browse models