Neural network analysis of heart rhythm variability for diagnosis of immobilization syndrome and objectivization of effectiveness of early rehabilitation
| Dublin Core | PKP Metadata Items | Metadata for this Document | |
| 1. | Title | Title of document | Neural network analysis of heart rhythm variability for diagnosis of immobilization syndrome and objectivization of effectiveness of early rehabilitation |
| 2. | Creator | Author's name, affiliation, country | Julia Yu. Nekrasova; Federal Research and Clinical Center of Intensive Care and Rehabilitology; Moscow Aviation Institute (National Research University); Russian Federation |
| 2. | Creator | Author's name, affiliation, country | D. S. Yankevich; Federal Research and Clinical Center of Intensive Care and Rehabilitology; Russian Federation |
| 2. | Creator | Author's name, affiliation, country | М. М. Kanarsky; Federal Research and Clinical Center of Intensive Care and Rehabilitology; Russian Federation |
| 2. | Creator | Author's name, affiliation, country | A. S. Markov; Moscow Aviation Institute (National Research University); Russian Federation |
| 3. | Subject | Discipline(s) | |
| 3. | Subject | Keyword(s) | heart rate variability; immobilization syndrome; post-intensive care syndrome (PICS); impaired consciousness; neural networks; rehabilitation |
| 4. | Description | Abstract | The article discusses the use of a neural network analysis of heart rate variability for the diagnosis of immobilization syndrome and post-intensive care syndrome (PICS) in patients with disorders of consciousness for monitoring the quality of the rehabilitation process. It is shown that there are statistical differences between the curves characterizing the heart rate variability of healthy patients and patients with impaired consciousness. The use of a neural network allows to automatically evaluate the severity of the immobilization syndrome and Post Intensive Care Syndrome, as well as the effectiveness of measures for their prevention and the overall quality of the work of medical personnel. |
| 5. | Publisher | Organizing agency, location | Eco-Vector |
| 6. | Contributor | Sponsor(s) | |
| 7. | Date | (DD-MM-YYYY) | 15.08.2020 |
| 8. | Type | Status & genre | Peer-reviewed Article |
| 8. | Type | Type | Research Article |
| 9. | Format | File format | |
| 10. | Identifier | Uniform Resource Identifier | https://rjmseer.com/1560-9537/article/view/34233 |
| 10. | Identifier | Digital Object Identifier (DOI) | 10.17816/MSER34233 |
| 10. | Identifier | Digital Object Identifier (DOI) (PDF (Rus)) | 10.17816/MSER34233-23311 |
| 11. | Source | Title; vol., no. (year) | Medical and Social Expert Evaluation and Rehabilitation; Vol 23, No 1 (2020) |
| 12. | Language | English=en | ru |
| 13. | Relation | Supp. Files |
Figure: 1. Increments of the amplitudes of R-peaks, intervals between R-peaks and angle α (198KB) doi: 10.17816/MSER34233-24457 Figure: 2. Statistical characteristics of the main group of patients (156KB) doi: 10.17816/MSER34233-24458 Figure: 3. Dependences of dR (marked in red), dT (blue) and dα (green) on the interval number: a - for a healthy person, b - for a patient in a vegetative state due to anoxic brain damage, c - for a patient in a vegetative state condition due to traumatic brain injury, d - for a patient in a state of minimal consciousness due to traumatic brain injury, e - for a patient who regained consciousness after severe brain contusion (891KB) doi: 10.17816/MSER34233-24459 Figure: 4. Diagrams of the amplitude range of R-peaks: a - for healthy subjects, b - for patients of the main group (146KB) doi: 10.17816/MSER34233-24460 Figure: 5. Values of the dispersion of the amplitude of the R wave for different categories of patients (59KB) doi: 10.17816/MSER34233-24461 Figure: 6. Diagrams of the range of values of the coefficients of asymmetry (a) and kurtosis (b) for patients of the main group and healthy subjects (107KB) doi: 10.17816/MSER34233-24462 Figure: 7. The structure of the neural network (247KB) doi: 10.17816/MSER34233-24463 Figure: 8. Dependence of the classification accuracy of the neural network on the number of training epochs for training (blue) and test (orange) data (60KB) doi: 10.17816/MSER34233-24464 |
| 14. | Coverage | Geo-spatial location, chronological period, research sample (gender, age, etc.) | |
| 15. | Rights | Copyright and permissions |
Copyright (c) 2020 Eco-Vector |