De-identified Study Dataset for Forensic Evidence Recovery Analysis

Case-level variables from a study on detecting acute physical findings in sexual assault cases. The dataset is 24.7 KB in size and was authored by Erhan Kartal. It was last updated on March 18, 2026, and is shared under a CC-BY-4.0 license.

Use Cases

• Train a Random Forest classifier for detecting acute physical findings based on case-level variables.
• Reproduce the statistical results and prespecified sensitivity analysis from the original study.
• Analyze the relationship between parallel genital injuries and other forensic evidence.
• Validate model performance metrics like ROC AUC for reporting on injury detection.

Strengths

• Dataset is small (24.7 KB), facilitating quick download and exploration.
• Shared under a permissive CC-BY-4.0 license, allowing for reuse and modification.
• Includes variables necessary to reproduce the study's statistical results, supporting reproducibility.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Erhan Kartal, potentially associated with a university forensic clinic.

Collection Method

Likely contains case-level variables collected for a clinical study.

Freshness

Last updated 2026-03-18 17:29:33; freshness should be verified.