AI-Ready Data Platform Accelerating Surgical Innovation
Overview
Carlsmed, a newly public health tech company, needed a unified, AI-ready data platform to strengthen surgical planning and clinical decision support. They sought help integrating diverse data sources, implementing secure de-identification, and enabling scalable ML workflows. ImagineX designed a modern Medallion Architecture on AWS, using Claude to accelerate front-end development, data cleansing, and pipeline optimization, paired with a custom UI for labeling and analytics.
Problem
Disconnected data sources limited AI model development and clinical insights.
Lacked secure, compliant de-identification and PHI removal workflows.
Manual labeling slowed dataset readiness for ML and LLM use cases.
No platform for centralized enrichment, analytics, or clinical review.
Needed a fast path to MVP to support executive timelines.
Solution
ImagineX built a secure AWS-based Medallion Architecture with automated ingestion from databases and image repositories. Claude accelerated development of the custom Next.js UI for human-in-the-loop pathology labeling, and powered ETL pipelines that cleaned, deduped, and de-identified data while driving ongoing pipeline management and optimization. Refined Gold-layer datasets support analytics, AI use cases, and MS Teams chat ingestion for case summarization. Terraform IaC, documentation, and Agile delivery ensured rapid, scalable deployment aligned with clinical workflows.
Outcome
Delivered an MVP aligned with executive speed-to-market goals.
Enabled scalable AI, ML, and LLM development with cleaned, consolidated datasets.
Unified data foundation improves surgical planning and business insights.
Custom Claude-built clinical UI streamlined labeling, enrichment, and data exploration workflows.
Services
Technology Delivery
Technical Management
Agile Delivery
Data & Software Engineering
Technologies Used
AWS Glue
AWS S3 (Delta Lake)
AWS Step Functions
AWS Bedrock
Terraform
Next.js UI
Claude
