Multimodal Neurobiological Data for Binge-Type Eating Disorder Classification

A 2026 study by Lena Rommerskirchen applied machine learning to multimodal data from 110 participants with bulimia nervosa, binge eating disorder, and matched controls. The dataset integrates task-based fMRI, intrinsic connectivity, voxel-based morphometry, neuropsychological assessments, and peripheral blood biomarkers. It was used to classify diagnostic groups and predict individual symptom variation.

Use Cases

• Training diagnostic classifiers based on functional brain connectivity patterns.
• Distinguishing between bulimia nervosa and binge eating disorder using task-based fMRI with disorder-specific stimuli.
• Predicting individual symptom expression using multimodal neurobiological and behavioral data.
• Comparing the predictive utility of unimodal versus multimodal machine learning frameworks for psychiatric conditions.

Strengths

• Multimodal integration of five distinct data types: fMRI, connectivity, morphometry, assessments, and biomarkers.
• Includes 110 participants across three diagnostic groups (BN, BED, controls) with age and weight matching.
• Reported classification accuracies, such as 87% mean balanced accuracy for distinguishing BN from BED.

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The dataset is small in file size (864.3 KB), indicating limited raw data scope, likely a summary or processed results.
• Data may reflect bias inherent to the specific participant cohort and study design.

Provenance

Source

Lena Rommerskirchen via figshare.

Collection Method

Collected from a study of 110 participants, integrating multiple neurobiological and behavioral assessments.

Time Range

The study was published in 2026; specific data collection dates are not provided.

Freshness

Last updated 2026-04-13 05:49:02.

Geography

Geographic coverage of the participant cohort is not specified.