Baseline Characteristics for Pediatric Moyamoya Disease Surgical Outcomes Study

A retrospective study of 181 pediatric patients (≤18 years) with Moyamoya disease who underwent revascularization surgery, with an independent validation cohort of 79 patients. The dataset contains baseline characteristics used to develop an explainable deep learning model for predicting postoperative cerebrovascular events from intraoperative arterial blood pressure waveforms. It was authored by Jung-Bin Park and last updated in June 2026.

Use Cases

• Training classification models to predict postoperative cerebrovascular events based on patient baseline characteristics.
• Conducting exploratory statistical analysis of waveform-derived physiologic features associated with surgical outcomes.
• Benchmarking convolutional neural network (CNN) models against Vision Transformer (ViT) architectures for medical time-series classification.
• Investigating the clinical relevance of diastolic runoff phase dynamics in arterial blood pressure signals.

Strengths

• Includes data from 181 pediatric patients with a separate temporal validation cohort of 79 patients.
• Dataset is associated with a study achieving an internal classification AUROC of 0.772 and a validation AUROC of 0.738.
• Released under a permissive CC-BY-4.0 license, allowing for reuse and modification.

Limitations

• Row count and column-level documentation are unknown, which limits suitability assessment and requires manual inspection after download.
• The study's findings are described as exploratory and require prospective multi-center validation before clinical application.

Provenance

Source

figshare, author Jung-Bin Park

Collection Method

Retrospective study of pediatric patients undergoing revascularization surgery for Moyamoya disease.

Freshness

Last updated 2026-06-04 17:34:19