NeuroVisionNet: ROC-AUC Analysis for a Multimodal Mental Health Detection Model

Sunil Kumar Sharma published this dataset on figshare in April 2026. It contains performance metrics for the NeuroHAGWO-Net AI model, which analyzes electroencephalogram (EEG) signals and behavioral text data for mental health screening. The dataset is 5.5 KB in size and is stored in an XLS file.

Use Cases

• Benchmarking multimodal AI model performance based on reported accuracy, precision, and F1-score metrics
• Analyzing feature selection techniques based on the described Hybrid Ant-Grey Wolf Optimization (HAGWO) method
• Comparing deep learning architectures for mental health detection based on the integrated EfficientNetV2 and Temporal CNNs
• Evaluating the trade-off between sensitivity and specificity in clinical AI tools based on the reported rates

Strengths

• Model performance metrics are highly specific, including an accuracy of 0.9945 and an F1-Score of 0.9909 on behavioral data
• The dataset is openly licensed under CC-BY-4.0, facilitating reuse and redistribution
• The underlying model methodology is described in detail, involving multimodal EEG and text data fusion

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The dataset is very small at 5.5 KB, indicating limited scope, likely containing only summary performance statistics

Provenance

Source

figshare

Collection Method

Likely generated from the validation of the NeuroHAGWO-Net AI model on two datasets of behavioral and EEG data.

Time Range

null

Freshness

Last updated 2026-04-13 17:44:22; freshness should be verified

Geography

null