Eleos to Launch Polaris AI Advanced, Purpose-Built Foundational AI Model for Post-Acute Care, built with Google Cloud Technology

Polaris AI leverages Google Cloud’s Gemini family of multimodal models and Eleos’ secure and clinically validated infrastructure to reduce documentation burden, strengthen compliance and help providers focus on care.

BOSTON, Oct. 20, 2025 (GLOBE NEWSWIRE) -- Eleos, the leader in AI for post-acute care, today announced the launch of Polaris AI, built in collaboration with Google Cloud technology. Polaris AI is enabled by Google Cloud’s family of multimodal models and built on its secure, scalable infrastructure, combined with Eleos’ purpose-built dataset spanning millions of real-world behavioral health sessions. Eleos is delivering one of the most advanced foundational AI models designed for the unique demands of post-acute care, from rising clinician burnout to intensifying regulatory scrutiny across behavioral health, substance use disorder (SUD), home health and hospice care.

Built for How Post-Acute Care Actually Works
In post-acute care, conversation is treatment. Yet most AI tools weren’t built for the clinical or regulatory complexity of this environment, adding to documentation burdens and risks. Polaris AI bridges that gap by combining advanced reasoning and multimodal capabilities with deep domain expertise. The model is trained on a diverse, clinically de-identified corpus of millions of minutes of therapy transcripts, behavioral health progress notes, professionally tagged datasets and proprietary in-house content to equip clinicians with a tool that allows them to focus on what they do best: providing care.

This next evolution of Eleos’ clinically-validated models can recognize evidence-based techniques and handle sensitive disclosures with precision. Polaris AI is audio-native, which means it can interpret vocal cues that text alone strips away, bringing an additional layer of context to every interaction. 

Polaris AI is optimized to:

• Understand real-world clinical dialogue: Recognize nuance, emotional tone and implicit meaning in authentic provider-client conversations.
• Recognize evidence-based techniques: Accurately identify methods such as CBT (cognitive behavioral therapy), DBT (dialectical behavior therapy), MI (motivational interviewing) and ACT (acceptance and commitment therapy) within sessions.
• Handle and flag sensitive disclosures: Process narratives involving abuse, assault or self-harm without the hallucination or redaction of critical details typical in off-the-shelf LLMs, all while triggering mandated-reporting workflows.
• Manage long, complex sessions: Process extended, multi-participant conversations in both individual and group therapy contexts.

“In post-acute care, the meaning is in the moment: the way a question is asked, the pause before an answer, the tone that says more than the words,” said Dr. Denny Morrison, chief clinical officer at Eleos Health. “Polaris AI is built to notice those things, not just transcribe them. It’s trained to understand the conversation as care, pick up on what’s unsaid and treat sensitive moments with the care they deserve.”

Security That Matches the Sensitivity of the Work
Protecting provider and client trust means meeting the strictest security standards at every stage of the AI lifecycle, from training data to deployed models. Polaris AI is deployed on Google Cloud’s trusted infrastructure that supports HIPAA compliance and has built-in AI defenses and continuous monitoring to protect patient and provider data. This collaboration pairs post-acute care-grade compliance with AI-specific defenses to address risks like protected health information (PHI)/personally identifiable information (PII) exposure, prompt injection, system prompt leakage, model poisoning and hallucinations. Protections include continuous AI stack monitoring, secure development lifecycle practices, identity and access management, and no storage of raw audio or transcripts, all paired with a full-time CISO and dedicated security team.

“Protecting provider and client trust means meeting the strictest security standards at every stage of the AI lifecycle, from training data to deployed models,” said Aashima Gupta, global director of Healthcare Strategy & Solutions, Google Cloud. “Polaris AI, deployed on Google Cloud’s trusted infrastructure that supports HIPAA compliance, pairs post-acute care-grade compliance with AI-specific defenses to protect personally identifiable information and protected health information, and defend against prompt injection, system prompt leakage, and hallucinations.”

“As we evaluated Eleos’ security infrastructure, it was clear they left no stone unturned,” said Prasad Kodali, chief information officer at Centerstone. “They are on the leading edge of AI-specific data privacy protections, constantly evolving in line with the latest certifications and best practices.”

Building for the Long Term
Polaris AI reflects Eleos’ belief that technology should honor the human side of care.

“Our collaboration with Google Cloud brings the power of AI to the heart of post-acute care,” said Alon Joffe, CEO and Co-Founder of Eleos. “Polaris AI marks the next step in a sustained, multi-phase effort to set a new benchmark for accuracy, compliance and efficiency in some of healthcare’s most sensitive environments. At Eleos, our motto is simple: you care, we care. That’s why we design AI to work the way providers work, respecting the complexity of their world and the trust at the heart of every interaction.”

To see Polaris AI in action, request a demo of Eleos for your organization here.

About Eleos
Eleos is the leading AI platform for behavioral health, substance use disorder, home health and hospice. At Eleos, we believe the path to better care is paved with provider-focused technology. Our purpose-built AI platform streamlines documentation, simplifies revenue cycle management and surfaces deep care insights to drive better client outcomes. Created using the industry’s largest database of real-world sessions and fine-tuned by our in-house clinical experts, our AI tools are scientifically proven to reduce documentation time by more than 70%, boost client engagement by 2x and improve symptom reduction by 3-4x. With Eleos, post-acute care providers are free to focus less on administrative tasks and more on what got them into this field in the first place: caring for their clients

Contact:
Mia Nitekman
mnitekman@sloanepr.com

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.