GCPEvidence: Low40/100

MyndYou AI Virtual Care Assistant Improves Patient Outcomes with Vertex AI and Gemini

MyndYou developed 'Eleanor', an AI-powered virtual care assistant to address patient care staffing shortages and improve chronic disease management with automated patient outreach. Eleanor conducts clinical phone conversations, analyzing patient speech for clinical events and optimizing call timing using BigQuery analytics. MyndYou uses Vertex AI and Gemini, fine-tuning Gemini models for clinical accuracy and ensuring HIPAA compliance. The solution includes Speech-to-Text and Text-to-Speech APIs and uses Google Cloud Run and PaLM LLM for call data analysis and summarization. This implementation doubled successful screening appointment completions, improved patient engagement and trust, enabled regular check-ins for high-risk patients, and optimized healthcare provider workflows.

Organization
MyndYou
Industry
Healthcare

Reported outcomes

Strategic outcomes

New business modelEnabled new remote care modelCustomer experience & trustImproved patient engagement and trustNew product / capabilityCreated AI virtual care assistantRisk & complianceMaintained HIPAA-compliant patient data handling
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
MyndYou
Provider
GCP
Maturity
Unknown

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

  • 1Conversational AI for clinical patient engagement
  • 2AI model fine-tuning
  • 3Speech-to-text and text-to-speech integration
US healthcare faces a critical shortage of nurses and staff for managing chronic disease patients, impacting care quality and reach.
  • MyndYou created an AI virtual assistant that conducts real-time clinical conversations, identifies urgent clinical events, and interacts naturally with patients.
  • They fine-tune Gemini models with proprietary data to increase accuracy of clinical event detection and utilize PaLM large language model for call analysis and improvement.
  • Google Cloud BigQuery is used to analyze data and optimize calling schedules based on patient demographics and other factors.
  • HIPAA compliance is maintained to secure sensitive patient data while continuously improving the assistant's performance.
  • Integrated use of Google Cloud Run, Speech-to-Text, and Text-to-Speech enables scalable, real-time processing.
  • Doubled success rate of appointment completions compared to traditional clinician calls, improving patient outcomes.
  • Enhanced patient engagement and trust, with patients more willing to share critical health information.
  • Enabled new care models with frequent remote patient check-ins not possible with human staffing.
  • Optimized healthcare workflows for efficiency and effectiveness in chronic disease management.
Architecture

Architecture involves Gemini fine-tuned models for clinical conversation understanding, PaLM LLM for call data summarization, Google Cloud BigQuery for call timing analytics, Speech-to-Text and Text-to-Speech for interaction, and Cloud Run for scalable infrastructure.

Sources & evidence1
Evidence: Low40/100Evidence strength
  • Customer explicitly identified
  • Primary source available
  • Technical implementation details available
Type: Customer StoryPublisher: Google Cloud Customer StoriesEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.