Objective: Physiological networks (PN) model couplings between organs in a high-dimensional parameter space. Machine learning methods, in particular artifical neural networks (ANNs), are powerful on high-dimensional classification tasks. However, lack of interpretability of the resulting models has been a drawback in research. We assess relevant PN topology changes in obstructive sleep apnea (OSA) by novel ANN interpretation techniques.
Approach: ANNs are trained to classify OSA based on the PNs of 48 patients and 48 age and gender matched healthy controls. The PNs consisting of 2812 links are derived from overnight biosignal recordings. The interpretation technique DeepLift is applied to the resulting ANN models, enabling the determination of the relevant features for classification decisions on individual subjects. The mean relevance scores of the features are compared to other machine learning methods (decision tree and random forests) and statistical tests on group differences.
Main Results: The ANN interpretation results show good agreement with the compared methods and 87% of the samples could be correctly classified. OSA patients show a significantly higher coupling (p [Formula: see text] 0.001) in light sleep (N2) between breathing rate and EEG [Formula: see text] power in all electrode locations and to chin and leg muscular tone. In deep sleep (N3), OSA leads to significantly lower coupling (p [Formula: see text] 0.01) in lateral connections of EEG [Formula: see text] and [Formula: see text] power in central and frontal positions. Misclassified OSA patients had all mild/moderate AHIs and did not show PN topology changes. Both nights of these patients have been consistently misclassified as healthy. This may indicate, that the impact of respiratory events differs in subjects, thus forming different phenotypes.
Significance: The proposed PN analysis provides a powerful and robust method to quantify a broad range of physiological interactions. Interpretability of the ANN make them a promising tool to identify new diagnostic markers in data-driven approaches.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1088/1361-6579/aaf0c9 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
State shifts in the deep Critical Zone drive landscape evolution in volcanic terrains.
Proc Natl Acad Sci U S A
January 2025
Department of Earth Sciences, University of Oregon, Eugene, OR 97403.
Volcanic provinces are among the most active but least well understood landscapes on Earth. Here, we show that the central Cascade arc, USA, exhibits systematic spatial covariation of topography and hydrology that are linked to aging volcanic bedrock, suggesting systematic controls on landscape evolution. At the Cascade crest, a locus of Quaternary volcanism, water circulates deeply through the upper [Formula: see text]1 km of crust but transitions to shallow and dominantly horizontal flow as rocks age away from the arc front.
View Article and Find Full Text PDFReviving the Lieb-Schultz-Mattis theorem in open quantum systems.
Natl Sci Rev
January 2025
Institute for Advanced Study, Tsinghua University, Beijing 100084, China.
In closed systems, the celebrated Lieb-Schultz-Mattis (LSM) theorem states that a one-dimensional locally interacting half-integer spin chain with translation and spin rotation symmetries cannot have a non-degenerate gapped ground state. However, the applicability of this theorem is diminished when the system interacts with a bath and loses its energy conservation. In this letter, we propose that the LSM theorem can be revived in the entanglement Hamiltonian when the coupling to the bath renders the system short-range correlated.
View Article and Find Full Text PDFTemperature-dependent pathways in carbon dioxide electroreduction.
Sci Bull (Beijing)
January 2025
Beijing National Laboratory for Molecular Sciences, CAS Laboratory of Colloid and Interface and Thermodynamics, CAS Research/Education Centre for Excellence in Molecular Sciences, Centre for Carbon Neutral Chemistry, Institute of Chemistry, Chinese Academy of Sciences, Beijing 100190, China; School of Chemistry, University of Chinese Academy of Sciences, Beijing 100049, China; Shanghai Key Laboratory of Green Chemistry and Chemical Processes, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai 200062, China. Electronic address:
Temperature affects both the thermodynamics of intermediate adsorption and the kinetics of elementary reactions. Despite its extensive study in thermocatalysis, temperature effect is typically overlooked in electrocatalysis. This study investigates how electrolyte temperature influences CO electroreduction over Cu catalysts.
View Article and Find Full Text PDFPhase transitions, Dirac and Weyl semimetal states in MnGeBiTe.
Sci Rep
January 2025
Saint Petersburg State University, St. Petersburg, 198504, Russia.
Using angle-resolved photoemission spectroscopy (ARPES) and density functional theory (DFT), an experimental and theoretical study of changes in the electronic structure (dispersion dependencies) and corresponding modification of the energy band gap at the Dirac point (DP) for topological insulator (TI) [Formula: see text] have been carried out with gradual replacement of magnetic Mn atoms by non-magnetic Ge atoms when concentration of the latter was varied from 10% to 75%. It was shown that when Ge concentration increases, the bulk band gap decreases and reaches zero plateau in the concentration range of 45-60% while trivial surface states (TrSS) are present and exhibit an energy splitting of 100 and 70 meV in different types of measurements. It was also shown that TSS disappear from the measured band dispersions at a Ge concentration of about 40%.
View Article and Find Full Text PDFA python approach for prediction of physicochemical properties of anti-arrhythmia drugs using topological descriptors.
Sci Rep
January 2025
Department of Mathematical Sciences, Faculty of Science, Somali National University, Mogadishu Campus, Mogadishu, Somalia.
In recent years, machine learning has gained substantial attention for its ability to predict complex chemical and biological properties, including those of pharmaceutical compounds. This study proposes a machine learning-based quantitative structure-property relationship (QSPR) model for predicting the physicochemical properties of anti-arrhythmia drugs using topological descriptors. Anti-arrhythmic drug development is challenging due to the complex relationship between chemical structure and drug efficacy.
View Article and Find Full Text PDFWant 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!