What challenges did Kakao Healthcare face before AI implementation?

Securely share and analyze sensitive medical data across multiple hospitals without exposing patient data. Integrate and standardize disparate medical data formats and systems from various hospitals. Enable collaborative AI model training across multiple hospitals while complying with privacy and data security requirements.

What was the impact of the AI solution?

Accelerated breast cancer recurrence prediction from 2 years to 4 months with higher accuracy (Federated Learning model AUC of 0.8482). Expanded joint learning platform to 20 hospitals covering approximately 15,000 beds and 20 million people. Enabled secure and systematic joint medical research and collaboration while preserving patient privacy. Laid groundwork for digital transformation in hospital data management and drug development research.

Source

GCPEvidence: Low40/100

Kakao Healthcare Deploys Federated Learning Platform on Google Cloud for Secure Medical Data Collaboration

Use case typeFederated learningUpdated Jun 13, 2026

Kakao Healthcare developed a federated learning-based medical data platform on Google Cloud to enable secure machine learning collaboration across 16 hospitals in Korea without moving patient data outside hospital environments. The platform standardizes disparate hospital medical data and keeps sensitive information securely in each hospital's cloud environment, sharing only model insights with other participants. The federated learning system accelerated prediction of breast cancer recurrence from 2 years to 4 months with improved accuracy, and expanded to 20 hospitals covering 15,000 beds and 20 million patient records. The platform supports digital transformation in hospital data operations, joint medical research, and drug development analytics through secure, collaborative AI model training and data management.

Organization: Kakao Healthcare
Industry: Healthcare
Location: South Korea

Reported outcomes

Strategic outcomes

Risk & complianceEnabled privacy-preserving medical data collaborationMarket & geographic expansionExpanded joint learning to more hospitalsNew product / capabilityStandardized disparate hospital data formatsNew product / capabilityLaid groundwork for digital transformation

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Kakao Healthcare
Provider: GCP
Maturity: Unknown
Linked source: Google Cloud Customer Stories

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 3

1Federated Learning
2Secure Collaborative AI
3Medical Data Analytics

Securely share and analyze sensitive medical data across multiple hospitals without exposing patient data.
Integrate and standardize disparate medical data formats and systems from various hospitals.
Enable collaborative AI model training across multiple hospitals while complying with privacy and data security requirements.

Implemented a federated learning platform on Google Cloud using Vertex AI, Gemini models, and Google Kubernetes Engine (GKE) that allows each hospital to keep data within its own environment and train AI models locally.
Standardized medical data across hospitals to enable interoperability and joint learning without actual data movement.
Managed all processes within GKE for security and control, ensuring data access restrictions and participant consent in collaborative learning.
Provided hospitals with machine learning-ready data sets and access to Vertex AI for model analysis and research.

Technologies

Generative AI on Google Cloud Vertex AI Gemini Google Kubernetes Engine

Accelerated breast cancer recurrence prediction from 2 years to 4 months with higher accuracy (Federated Learning model AUC of 0.8482).
Expanded joint learning platform to 20 hospitals covering approximately 15,000 beds and 20 million people.
Enabled secure and systematic joint medical research and collaboration while preserving patient privacy.
Laid groundwork for digital transformation in hospital data management and drug development research.

Architecture

The platform uses Google Cloud Federated Learning architecture with federated ML model training distributed across 16 hospitals' local environments. It uses Vertex AI, Gemini models, and Google Kubernetes Engine (GKE) for securely managing data, training AI models locally, and sharing only learned model parameters. Data standardization and security protocols are handled to ensure privacy compliance and hospital-specific data control.

Sources & evidence1

Evidence: Low40/100Evidence strength