EEG Data for Patients Receiving Intravenous Antibiotic Medication

Citation Author(s):
Alaa Awad
Abdellatif
Qatar University
Zina
Chkirbene
Qatar University
Abeer
Al-Marridi
Qatar University
Amr
Mohamed
Qatar University
Aiman
Erbad
Qatar University
Mark Dennis
O’Connor
Hamad Medical Corporation
James
Laughton
Hamad Medical Corporation
Anthony
Villacorte
Hamad Medical Corporation
Johansen
Menez
Hamad Medical Corporation
Submitted by:
Alaa Abdellatif
Last updated:
Thu, 04/30/2020 - 11:04
DOI:
10.21227/qcg5-yd65
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

This dataset has been collected in the Patient Recovery Center (a  24-hour,  7-day  nurse  staffed  facility)  with  medical  consultant   from  the  Mobile  Healthcare  Service of Hamad Medical Corporation. The collection of the raw EEG data is made possible by the use of a non-invasive head-cap type device (i.e., EMOTIV EPOC+ with 14 EEG channels). Using this dataset, we conduct a biological data collection and analysis study for patients undergoing routine planned treatment. The primary objective of our study is the safe collection of EEG data from patients receiving antibiotic therapy, in addition to analyzing the acquired data for detecting the medication side effects, i.e., that might indicate risk of seizure. This study aims to collect and monitor the EEG activity of patients receiving intravenous medication. The acquired EEG data in this study has been collected from 30 patients: before, during, and after receiving the medication. We remark that each column in our dataset files is mapping a particular channel of EMOTIV EPOC+, in addition to a class label column (the first column), i.e., refers to the data collection phase, and a patient identification column (the second column). Number of rows in our dataset represents time instance of the recording channels. 

 

Instructions: 

The acquired EEG data has been collected under the Abhath project. The Abhath project is MRC 01-17-091 investigation of the utility of employing techniques of deep learning algorithmic analysis to raw EEG, vital signs and observational data from patients receiving Intravenous antibiotic medication, with respect to using the output data to better predict the risk of seizure events. 

Comments

hi

Submitted by Ionela Riciu on Sat, 05/02/2020 - 11:13

Hi Lonela 

Submitted by Alaa Abdellatif on Sun, 05/03/2020 - 18:19