What was the impact of the AI solution?

App adoption grew to 35,000 active users within a year, aiding personal health monitoring and enhancing medical research engagement. Accelerated research trial timelines, reducing experimentation from weeks to days using Google Cloud infrastructure. Improved developer experience and operational scalability through container orchestration and cloud AI services. Established a privacy-first approach leveraging blockchain to ensure integrity and compliance in clinical data trials.

Source

GCP

doc.ai leverages Google Cloud AI and Kubernetes for mobile health insights and research acceleration

Use case typeAI development platformUpdated Jun 13, 2026

doc.ai developed an AI platform enabling machine learning computations on real-world health data to deliver personal health insights and accelerate medical research through data trials. The mobile app integrates on-device AI with cloud-hosted ML training and inference on Google Cloud using Google Kubernetes Engine (GKE) for scalable deployment and Google Compute Engine with GPUs for efficient model tuning. doc.ai implemented an Ethereum private blockchain on GKE to ensure data privacy and transparency in research trials. The solution reached over 35,000 active users within a year and enables accelerated research trials for allergies, Crohn's disease, colitis, and epilepsy with higher user engagement. The platform offers APIs for licensed partners to conduct trials, leveraging Google Cloud for operational scalability and accelerated experimentation.

Organization: doc.ai
Industry: Healthcare
Location: United States

Reported outcomes

Strategic outcomes

New product / capabilityBuilt a secure AI health insights platformScale & capacityEnabled scalable ML service deliveryRisk & complianceEstablished privacy-first clinical trial transparencyEcosystem & partnershipsExposed research APIs for licensed partners

Primary read

Use case focus

Showing 3 of 3

1Health Insights
2AI for Medical Research
3Privacy-Preserving AI Platforms

doc.ai aimed to create a secure AI platform facilitating machine learning on diverse personal and medical health data to provide insights and accelerate research while ensuring data privacy and compliance.

Developed a mobile health monitoring app integrated with Google Cloud AI services.
Hosted ML training and inference on Google Kubernetes Engine clusters for scalable service delivery.
Used Google Compute Engine with GPUs for hyperparameter tuning and model training.
Utilized an Ethereum private blockchain running on GKE for data privacy, research trial transparency, and compliance.
Exposed ML models via APIs for licensed partners to conduct and manage research trials.

Technologies

Google Kubernetes Engine Google Compute Engine TensorFlow NVIDIA GPUs Ethereum private blockchain GKE

App adoption grew to 35,000 active users within a year, aiding personal health monitoring and enhancing medical research engagement.
Accelerated research trial timelines, reducing experimentation from weeks to days using Google Cloud infrastructure.
Improved developer experience and operational scalability through container orchestration and cloud AI services.
Established a privacy-first approach leveraging blockchain to ensure integrity and compliance in clinical data trials.

Architecture

The architecture combines a mobile app with cloud-hosted ML model training and inference on Google Kubernetes Engine and Compute Engine leveraging GPUs. An Ethereum private blockchain on GKE supports data privacy and trial transparency. APIs expose ML models to partners.

Sources & evidence1

Groundedness: 5/5

Primary source

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

Explore related AI use cases

Customer evidence