Goal And Aims: Performance evaluation of automatic sleep staging on two-channel subcutaneous electroencephalography.

Focus Technology: UNEEG medical's 24/7 electroencephalography SubQ (the SubQ device) with deep learning model U-SleepSQ.

Reference Method/technology: Manually scored hypnograms from polysomnographic recordings.

Sample: Twenty-two healthy adults with 1-6 recordings per participant. The clinical study was registered at ClinicalTrials.gov with the identifier NCT04513743.

Design: Fine-tuning of U-Sleep in 11-fold cross-participant validation on 22 healthy adults. The resultant model was called U-SleepSQ.

Core Analytics: Bland-Altman analysis of sleep parameters. Advanced multiclass model performance metrics: stage-specific accuracy, specificity, sensitivity, kappa (κ), and F1 score. Additionally, Cohen's κ coefficient and macro F1 score. Longitudinal and participant-level performance evaluation.

Additional Analytics And Exploratory Analyses: Exploration of model confidence quantification. Performance vs. age, sex, body mass index, SubQ implantation hemisphere, normalized entropy, transition index, and scores from the following three questionnaires: Morningness-Eveningness Questionnaire, World Health Organization's 5-item Well-being Index, and Major Depression Inventory.

Core Outcomes: There was a strong agreement between the focus and reference method/technology.

Important Supplemental Outcomes: The confidence score was a promising metric for estimating the reliability of each hypnogram classified by the system.

Core Conclusion: The U-SleepSQ model classified hypnograms for healthy participants soon after implantation and longitudinally with a strong agreement with the gold standard of manually scored polysomnographics, exhibiting negligible temporal variation.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.sleh.2024.08.007DOI Listing

Publication Analysis

Top Keywords

strong agreement
12
healthy adults
12
automatic sleep
8
sleep staging
8
manually scored
8
model
5
staging based
4
based 24/7
4
24/7 eeg
4
subq
4

Similar Publications

MicroRNAs (miRNAs) have been recognised as potential biomarkers due to their specific expression patterns in different biological tissues and their changes in expression under pathological conditions. MicroRNA-122 (miR-122) is a vertebrate-specific miRNA that is predominantly expressed in the liver and plays an important role in liver metabolism and development. Dysregulation of miR-122 expression is associated with several liver-related diseases, including hepatocellular carcinoma and drug-induced liver injury (DILI).

View Article and Find Full Text PDF

Background: Effective vector control interventions, notably insecticide-treated nets (ITNs) and indoor residual spraying (IRS) are indispensable for malaria control in Tanzania and elsewhere. However, the emergence of widespread insecticide resistance threatens the efficacy of these interventions. Monitoring of insecticide resistance is, therefore, critical for the selection and assessment of the programmatic impact of insecticide-based interventions.

View Article and Find Full Text PDF

Anal squamous cell carcinoma (SCC) incidence has increased, and treatment has shifted from surgery to chemoradiotherapy (CRT), with salvage abdominoperineal resection (APR) being reserved for persistent/recurrent cases. This study evaluates the utility of different Tumor Regression Scoring Systems (TRSS) in predicting survival in anal SCC patients, using pathologists' observations and digital pathology. Cases managed surgically from 2005 to 2019 were collected.

View Article and Find Full Text PDF

Practical, low-cost integrity testing of diesel particle filters using remote sensing measurement at the campus entrance gate.

Sci Total Environ

December 2024

ASEM (Czech Association of Emissions Technicians), Boleslavská 902, 293 06 Kosmonosy, Czech Republic.

This work investigates the detection of defunct or absent diesel particle filters by drive-through remote sensing measurement at the Czech University of Life Sciences main vehicular entrance gate. An exhaust sample was collected by a line attached to the road surface in the center of the travel lane. A non-volatile particle number (nvPN) counter and electric mobility particle size classifier were used to measure particle number concentrations, and an FTIR analyzer was used to measure CO, CO, and NO concentrations.

View Article and Find Full Text PDF

Fit for purpose? Evaluating benthic invertebrate DNA metabarcoding for ecological status class assessment in streams under the Water Framework Directive.

Water Res

December 2024

University of Duisburg-Essen, Aquatic Ecosystem Research, Universitaetsstr. 5, 45141, Essen, Germany; University of Duisburg-Essen, Centre for Water and Environmental Research (ZWU), Universitaetsstr. 3, 45141, Essen, Germany. Electronic address:

The ecological state of aquatic ecosystems is systematically monitored using various bioindicators in many countries worldwide. In the European Union, freshwater biomonitoring is the central component of the EU Water Framework Directive (WFD, 2000/60/EC) and currently based on morpho-taxonomic methods. DNA metabarcoding is a novel approach to assess the ecological state fast and efficiently based on organismal DNA signatures and thereby support and upscale biomonitoring.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!