A dataset containing slide-level diagnostic performance metrics with Wilson 95% confidence intervals, calculated on an independent test set. The data, authored by Nisreen Osman E. Ahmed and last updated in March 2026, is stored in a 5.5 KB XLS file. It relates to a framework for automated amastigote detection and includes calibration metrics.
Use Cases
- Evaluating diagnostic model performance based on slide-level metrics and confidence intervals.
- Comparing calibration techniques like temperature scaling and isotonic regression based on reported metrics.
- Assessing the reliability of automated amastigote detection systems based on diagnostic probabilities.
Strengths
- Data includes Wilson 95% confidence intervals for performance metrics.
- File is small (5.5 KB) and easily accessible in XLS format.
- Released under a permissive CC-BY-4.0 license.
Limitations
- Row count and specific column definitions are unknown, requiring manual inspection.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- figshare, authored by Nisreen Osman E. Ahmed.
- Collection Method
- Likely generated from statistical analyses of a diagnostic model's performance on an independent test set.
- Time Range
- null
- Freshness
- Last updated 2026-03-17 17:37:47; freshness should be verified.
- Geography
- null