Ultrasound and Biomarker Data for Hepatic Fat Assessment in a Chinese Cohort

A single-center Chinese health-examination cohort of 172 participants was used to evaluate models for noninvasive hepatic fat fraction categorization. The dataset includes ultrasound attenuation values and serum levels of ALT, AST, and ferritin, referenced against quantitative computed tomography categories. The study was authored by Zejun Ma and last updated in May 2026.

Use Cases

• Training a binary classifier for imaging-defined steatosis detection based on ultrasound attenuation values.
• Comparing the performance of biomarker-only models against integrated models using ALT and ferritin levels.
• Conducting subgroup analysis for model performance based on features like sex, age, and BMI mentioned in the results.

Strengths

• Dataset is associated with a specific study involving 172 participants with defined hepatic fat fraction categories.
• Model performance metrics, including AUC values with confidence intervals, are provided for validation.
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• The dataset is small at 127.5 KB, suggesting limited scope or a summary document rather than raw participant data.
• Column-level documentation is absent; field semantics must be inferred after download.
• The study concludes discrimination for the intermediate fat fraction category was weak, limiting the model's reliability for full categorization.

Provenance

Source

figshare, author Zejun Ma.

Collection Method

Collected from participants enrolled in a study, with ultrasound attenuation and serum biomarker measurements taken.

Freshness

Last updated 2026-05-29 04:53:50; freshness should be verified.

Geography

Single-center Chinese health-examination cohort.