oscar-test-data-generation

This Skill generates synthetic CPAP test data using internal builders to create realistic sleep therapy sessions for validation. It produces fake patient datasets with patterns like high-AHI cases and zero-usage nights, ensuring no real patient information is used.

Synthetic sleep therapy data is used to validate charts, analytics, and export functions in OSCAR CSV workflows. By generating fake CPAP sessions and Fitbit-like datasets, developers can test end-to-end pipelines and edge cases without exposing real patient information.

You can create a 30-night CPAP dataset by running pattern-driven builders that produce specific test scenarios. These internal utilities generate time-series trends, high-AHI cases, and zero-usage nights to validate analytics and export functions robustly.

Yes, this synthetic data generation approach works for Fitbit-like datasets and edge cases. The builders generate comprehensive test scenarios including high-AHI, zero-usage nights, and time-series patterns to ensure robust validation of sleep therapy applications.

Yes, you can use these test data builders entirely without real patient information. The internal utilities are specifically designed to generate synthetic CPAP and sleep therapy data, creating patterns like high-AHI cases and zero-usage nights for safe validation.

The synthetic CPAP data generated is limited to testing, examples, and validation scenarios for OSCAR workflows. It uses internal test utilities to create patterns like high-AHI and zero-usage nights, but the data is synthetic and not intended for clinical or real-world medical applications.