Multimodal Model for Predicting Hepatic Encephalopathy Risk Post-TIPS

A multimodal dataset was used to develop a predictive model for overt hepatic encephalopathy (OHE) within one year after a transjugular intrahepatic portosystemic shunt (TIPS) procedure. The study by Lin-Feng Zhou, last updated in May 2026, integrated manual CT imaging features, radiomics, and clinical data from 338 patients treated between November 2015 and January 2022. The combined model (Model MRC) demonstrated superior predictive performance with an AUC of 0.902.

Use Cases

• Training predictive models for post-TIPS complications based on integrated clinical and imaging data.
• Comparing the performance of manual imaging features versus radiomics for medical risk prediction.
• Benchmarking multimodal fusion models against single-modality models in a clinical setting.

Strengths

• Dataset includes 338 patient records with a clear temporal range from November 2015 to January 2022.
• Model performance is quantitatively reported, with the combined model achieving an AUC of 0.902 and an F1 score of 0.891.
• The study design includes a training and validation split (7:3) and uses multiple established feature selection methods.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data is unknown, which may limit suitability assessment.
• The dataset is very small at 18.7 KB, indicating limited scope, likely containing only model results or summary statistics.

Provenance

Source

figshare

Collection Method

Retrospective study of patients who underwent TIPS.

Time Range

November 2015 to January 2022

Freshness

Last updated 2026-05-12 04:19:07; freshness should be verified.