Fractional Dynamics Foster Deep Learning of COPD Stage Prediction
Abstract Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. Current COPD diagnosis (i.e., spirometry) could be unreliable because the test depends on an adequate effort from the tester and testee. Moreover, the early diagnosis of COPD is challenging. The au...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-04-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202203485 |
| _version_ | 1797838937659539456 |
|---|---|
| author | Chenzhong Yin Mihai Udrescu Gaurav Gupta Mingxi Cheng Andrei Lihu Lucretia Udrescu Paul Bogdan David M. Mannino Stefan Mihaicuta |
| author_facet | Chenzhong Yin Mihai Udrescu Gaurav Gupta Mingxi Cheng Andrei Lihu Lucretia Udrescu Paul Bogdan David M. Mannino Stefan Mihaicuta |
| author_sort | Chenzhong Yin |
| collection | DOAJ |
| description | Abstract Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. Current COPD diagnosis (i.e., spirometry) could be unreliable because the test depends on an adequate effort from the tester and testee. Moreover, the early diagnosis of COPD is challenging. The authors address COPD detection by constructing two novel physiological signals datasets (4432 records from 54 patients in the WestRo COPD dataset and 13824 medical records from 534 patients in the WestRo Porti COPD dataset). The authors demonstrate their complex coupled fractal dynamical characteristics and perform a fractional‐order dynamics deep learning analysis to diagnose COPD. The authors found that the fractional‐order dynamical modeling can extract distinguishing signatures from the physiological signals across patients with all COPD stages—from stage 0 (healthy) to stage 4 (very severe). They use the fractional signatures to develop and train a deep neural network that predicts COPD stages based on the input features (such as thorax breathing effort, respiratory rate, or oxygen saturation). The authors show that the fractional dynamic deep learning model (FDDLM) achieves a COPD prediction accuracy of 98.66% and can serve as a robust alternative to spirometry. The FDDLM also has high accuracy when validated on a dataset with different physiological signals. |
| first_indexed | 2024-04-09T15:50:10Z |
| format | Article |
| id | doaj.art-cfe8694d04254234b3107e4841d548f0 |
| institution | Directory Open Access Journal |
| issn | 2198-3844 |
| language | English |
| last_indexed | 2024-04-09T15:50:10Z |
| publishDate | 2023-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj.art-cfe8694d04254234b3107e4841d548f02023-04-26T12:15:35ZengWileyAdvanced Science2198-38442023-04-011012n/an/a10.1002/advs.202203485Fractional Dynamics Foster Deep Learning of COPD Stage PredictionChenzhong Yin0Mihai Udrescu1Gaurav Gupta2Mingxi Cheng3Andrei Lihu4Lucretia Udrescu5Paul Bogdan6David M. Mannino7Stefan Mihaicuta8Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA USADepartment of Computer and Information Technology Politehnica University of Timisoara 2 Vasile Parvan Blvd. Timişoara 300223 RomaniaMing Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA USAMing Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA USADepartment of Computer and Information Technology Politehnica University of Timisoara 2 Vasile Parvan Blvd. Timişoara 300223 RomaniaDepartment I – Drug Analysis “Victor Babeş” University of Medicine and Pharmacy Timişoara 2 Eftimie Murgu Sq. Timişoara 300041 RomaniaMing Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA USACollege of Medicine University of Kentucky Lexington KY USADepartment of Pulmonology Center for Research and Innovation in Precision Medicine of Respiratory Diseases, “Victor Babes” University of Medicine and Pharmacy 2 Eftimie Murgu Sq. Timişoara 300041 RomaniaAbstract Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. Current COPD diagnosis (i.e., spirometry) could be unreliable because the test depends on an adequate effort from the tester and testee. Moreover, the early diagnosis of COPD is challenging. The authors address COPD detection by constructing two novel physiological signals datasets (4432 records from 54 patients in the WestRo COPD dataset and 13824 medical records from 534 patients in the WestRo Porti COPD dataset). The authors demonstrate their complex coupled fractal dynamical characteristics and perform a fractional‐order dynamics deep learning analysis to diagnose COPD. The authors found that the fractional‐order dynamical modeling can extract distinguishing signatures from the physiological signals across patients with all COPD stages—from stage 0 (healthy) to stage 4 (very severe). They use the fractional signatures to develop and train a deep neural network that predicts COPD stages based on the input features (such as thorax breathing effort, respiratory rate, or oxygen saturation). The authors show that the fractional dynamic deep learning model (FDDLM) achieves a COPD prediction accuracy of 98.66% and can serve as a robust alternative to spirometry. The FDDLM also has high accuracy when validated on a dataset with different physiological signals.https://doi.org/10.1002/advs.202203485chronic obstructive pulmonary disease (COPD)deep learningfractional analysis |
| spellingShingle | Chenzhong Yin Mihai Udrescu Gaurav Gupta Mingxi Cheng Andrei Lihu Lucretia Udrescu Paul Bogdan David M. Mannino Stefan Mihaicuta Fractional Dynamics Foster Deep Learning of COPD Stage Prediction Advanced Science chronic obstructive pulmonary disease (COPD) deep learning fractional analysis |
| title | Fractional Dynamics Foster Deep Learning of COPD Stage Prediction |
| title_full | Fractional Dynamics Foster Deep Learning of COPD Stage Prediction |
| title_fullStr | Fractional Dynamics Foster Deep Learning of COPD Stage Prediction |
| title_full_unstemmed | Fractional Dynamics Foster Deep Learning of COPD Stage Prediction |
| title_short | Fractional Dynamics Foster Deep Learning of COPD Stage Prediction |
| title_sort | fractional dynamics foster deep learning of copd stage prediction |
| topic | chronic obstructive pulmonary disease (COPD) deep learning fractional analysis |
| url | https://doi.org/10.1002/advs.202203485 |
| work_keys_str_mv | AT chenzhongyin fractionaldynamicsfosterdeeplearningofcopdstageprediction AT mihaiudrescu fractionaldynamicsfosterdeeplearningofcopdstageprediction AT gauravgupta fractionaldynamicsfosterdeeplearningofcopdstageprediction AT mingxicheng fractionaldynamicsfosterdeeplearningofcopdstageprediction AT andreilihu fractionaldynamicsfosterdeeplearningofcopdstageprediction AT lucretiaudrescu fractionaldynamicsfosterdeeplearningofcopdstageprediction AT paulbogdan fractionaldynamicsfosterdeeplearningofcopdstageprediction AT davidmmannino fractionaldynamicsfosterdeeplearningofcopdstageprediction AT stefanmihaicuta fractionaldynamicsfosterdeeplearningofcopdstageprediction |