12-Lead ECG Dataset for Cognitive Stress Detection Using HRV and ECG Morphology Features

This repository contains the ECG_Stress_Dataset, a de-identified 12-lead electrocardiographic (ECG) dataset acquired from healthy young adult participants under baseline and cognitive stress conditions. The recordings were obtained using a TLC 6000 Holter system and are provided as raw ECG files as exported from the device. The signals have not been filtered, centered, cropped, segmented, or preprocessed. Therefore, this repository contains the original acquisition-stage ECG recordings before the signal processing procedures described in the associated manuscript. The dataset includes 12-lead ECG recordings corresponding to leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6. The associated study used these recordings for the extraction of heart rate variability (HRV) and ECG morphology features for cognitive stress detection using adaptive genetic feature selection and multi-classifier evaluation. Cognitive stress was induced using a structured task based on the Factor R subtest of the PMA-R battery. The experimental protocol included a pre-rest adaptation phase, a baseline relaxation phase, an instruction phase, a cognitive stress phase with ECG recording, and a recovery period. All files were de-identified before publication. Participant names and direct personal identifiers were removed and replaced with coded identifiers such as ID-001, ID-002, ID-003, etc. The private correspondence table linking coded IDs with participant names is not included in this repository. No informed consent forms or direct personal identifiers are included. The study was conducted in accordance with the Declaration of Helsinki and was approved by the Ethics Committee of the Faculty of Engineering of the Autonomous University of Querétaro under approval number CEAIFI-183-2021-PI. Written informed consent was obtained from all participants before data acquisition. This dataset is intended to support transparency, reproducibility, and further research in ECG-based cognitive stress detection, heart rate variability analysis, ECG morphology analysis, biomedical signal processing, feature selection, and machine learning classification. DOI: https://doi.org/10.5281/zenodo.19864426