Normalized claim
Implementation_time_days: 10 days
build its desired system in just 10 days
UC San Diego Health Uses AWS to Implement AI Imaging Model in 10 Days
Use case typeClinical decision supportUpdated Jun 13, 2026
When the COVID-19 pandemic hit the United States, UC San Diego Health researchers had already developed a machine learning image recognition model to detect pneumonia in X-ray images. UC San Diego Health asked AWS for help putting the model into a clinical setting so practitioners could use the information for diagnosis and treatment. The team built a HIPAA-compliant AWS environment that connected the imaging pipeline to clinical systems and returned results directly into patient files.
- Organization
- UC San Diego Health
- Industry
- Healthcare
- Location
- United States
- Published
- May 2026
Reported outcomes
65,000 X-rays
xrays_processed_6_monthsOther quantified impact
10 daysimplementation_time_days400 X-raysfirst_day_xrays_processed3-4 minutesprocessing_time_per_xray_minutes20%clinical_decision_making_impact_percent
Strategic outcomes
Risk & complianceBuilt a HIPAA-compliant clinical environmentNew product / capabilityIntegrated model into clinical workflowsCustomer experience & trustReturned results directly into patient filesBetter decisions & insightSupported clinical decision-making
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
First_day_xrays_processed: 400 X-rays
The first day it was running on AWS, the model processed around 400 X-rays
Normalized claim
Xrays_processed_6_months: 65,000 X-rays
In the next 6 months after implementation, the model processed over 65,000 X-rays
Normalized claim
Processing_time_per_xray_minutes: 3-4 minutes
each in 3-4 minutes
Normalized claim
Clinical_decision_making_impact_percent: 20%
indicated that implementing this model has impacted clinical decision-making 20 percent of the time
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- UC San Diego Health
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Solutions Library
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 2 of 2
- 1Clinical decision support
- 2Medical imaging
Deploy a pneumonia-detection machine-learning image model into clinical workflows for COVID-19 while meeting HIPAA/security requirements and enabling fast point-of-care inference.
- Used an existing HIPAA-compliant AWS environment to build the clinical deployment in 10 days.
- Connected the model to the clinical imaging system so it could receive X-rays and output results directly into patients' files.
- Ran the implementation primarily on Amazon EC2 instances for secure, resizable compute capacity.
- Designed the setup to be maintainable and scalable for future model updates.
Technologies
- The project was implemented in 10 days.
- The first day it ran on AWS, the model processed around 400 X-rays.
- In the next 6 months, the model processed over 65,000 X-rays.
- Each X-ray took 3-4 minutes to process.
- The implementation impacted clinical decision-making 20% of the time.
- The environment allowed a single IT staff member to verify HIPAA and other compliance requirements.
Architecture
UC San Diego Health deployed its existing pneumonia-detection image model into a HIPAA-compliant AWS environment. The solution connected the clinical imaging system to AWS so incoming X-rays could be processed on Amazon EC2 and returned into patient files for clinician review. The environment was designed for secure healthcare workloads, rapid compliance verification, and elasticity for future model updates.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.