Health-Specific Evaluation for AI Systems

Learn how to evaluate AI systems in healthcare using specialized metrics and frameworks that address clinical validity, FDA regulatory requirements, bias detection, safety assessment, and practical implementation strategies. This comprehensive guide provides insights into designing robust evaluation pipelines for health AI applications.

Statistical Analysis for Evaluation

Learn how to apply statistical methods for robust evaluation of models, including power analysis, mixed-effects models, bootstrap confidence intervals, multiple comparison corrections, and effect size calculations. This guide provides practical algorithms and Python code snippets to help researchers ensure their evaluations are statistically sound and meaningful.

LLM Evaluation Methods

Learn about various methods for evaluating large language models (LLMs), including automatic metrics like BLEU and ROUGE, the LLM-as-judge paradigm, human-in-the-loop strategies, and specialized approaches for health-related applications. This comprehensive guide also covers best practices for benchmark design, red teaming, and scaling evaluations.

Human Evaluation & Psychometrics for AI Systems

This post provides a detailed overview of human evaluation and psychometrics in the context of AI systems, covering key concepts, reliability metrics, scale design, and practical implementation strategies. It includes algorithms and code snippets to help practitioners design robust evaluation frameworks.

NEMAR Dataset Citations Analysis Dashboard

NEMAR Dataset Citations Analysis Dashboard

This dashboard provides comprehensive analysis of dataset citations within the NEMAR ecosystem, revealing collaboration patterns, research trends, and the impact of open neuroscience data sharing on the research community.

Creating Interactive Dashboards in Hugo: A Complete Guide

Learn how to transform your Hugo static site into an interactive dashboard powerhouse using Chart.js, structured JSON data, and modern web development practices.

HBN Data Insights Dashboard

HBN Dataset Insights Dashboard

This is a data visualization dashboard for exploring the Healthy Brain Network EEG dataset. Features age and sex distributions, task availability metrics, mental health correlations, and per-release analysis across 11 dataset releases with over 3,600 participants.

Hyser experimental setup showing 256-channel HD-sEMG electrode arrays

Hyser: High-Density Surface EMG Dataset for Neural Interface Research

The Hyser dataset provides 256-channel HD-sEMG recordings from 20 subjects across five distinct tasks, including gesture recognition and force control paradigms, making it ideal for developing advanced neural interfaces and prosthetic control algorithms.

Topographic maps showing how μECoG at Motor Cortex projects across the scalp

Simulating Scalp EEG from Ultrahigh-Density ECoG Data Illustrates Cortex to Scalp Projection Patterns

Using 1024-electrode ultrahigh-density electrocorticography (μECoG) data as ground truth, this study demonstrates that cortical activity from a small 3×3 cm patch projects broadly across the entire scalp surface, not just to nearby EEG electrodes. By applying ICA decomposition and forward-projecting through a high-definition head model, we show that scalp EEG channels reflect complex mixtures of distributed cortical sources rather than primarily local activity. These findings challenge conventional channel-level EEG interpretation approaches and underscore the critical importance of source-level analysis methods for accurate understanding of brain electrical activity.

Standardized sensor placement framework with anatomical landmarks

A Standardized Framework for Sensor Placement in Human Motion Capture and Wearable Applications

We present a comprehensive framework that standardizes sensor placement in human movement and physiological monitoring applications. Through precise definitions of anatomical landmarks, coordinate systems, and placement protocols, our framework enables reproducible sensor positioning across different applications and laboratories. The system provides quantifiable levels of placement precision and is compatible with existing data-sharing standards like BIDS and HED. This standardization addresses the critical need for consistent sensor placement across applications ranging from clinical biomechanics to consumer wearables, enhancing data quality, reproducibility, and interoperability in human biosensing research.