# Federated Cancer Prediction

Enabled privacy-preserving cancer risk prediction using federated machine learning.

## Key Takeaways:

### Data privacy limited collaborative modeling

Sensitive patient data prevented institutions from training shared predictive models.

### We enabled privacy-preserving collaboration

Federated learning allowed joint model training without sharing raw patient data.

### Federated ML with NVIDIA FLARE

Models were trained using PyTorch across structured, time-series, and unstructured clinical data within a federated setup.

### Promising early cancer risk prediction performance

Initial results demonstrated strong predictive potential while preserving patient privacy.

### Continue Reading

### [Governed Metrics for AI](/content/case-studies/semantic-layer-enterprise-metrics/index.html)

Single logic across every interface

### [Compliance Reporting](/content/case-studies/compliance-reporting/index.html)

Reporting automated

### [Audience Segmentation](/content/case-studies/audience-segmentation/index.html)

Targeting efficiency improved.