HIV Status Concordance Study of Self-Reported and Clinical Health Data

A 9.5 KB Excel dataset compares self-reported health data with clinical estimates for 529 women, including 220 living with HIV and 309 without HIV. The dataset was created by Tovan Lew and last updated in April 2026. It originates from a study examining measurement agreement between patient-reported and clinically assessed information.

Use Cases

• Analyze concordance between self-reported (SR) and clinical estimate (CE) columns for key health indicators.
• Compare data distributions and correlations for the 'women living with HIV' (n=220) and 'women without HIV' (n=309) subgroups.
• Train classification models to predict HIV status or clinical estimate values using self-reported data features.
• Assess bias or systematic error in self-reported data by comparing it against the clinical estimate benchmark.

Strengths

• Includes data from 529 participants, providing a substantive sample for analysis.
• Clearly defines two comparison groups: 220 women with HIV and 309 women without HIV.
• Data is shared under a permissive CC-BY-4.0 license for reuse.

Limitations

• The dataset is very small at 9.5 KB, indicating limited variables or detail.
• Specific column names and health metrics measured are not provided in the metadata.
• The geographic origin and time period of the underlying study are unknown.

Provenance

Source

figshare, author Tovan Lew.

Collection Method

Comparison study collecting both self-reported data and clinical estimates from participants.

Time Range

null

Freshness

Last updated in 2026, indicating recent maintenance.

Geography

null