Physically Meaningful Surrogate Data for COPD
The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intelligence (AI) into respiratory healthcare. Deep learning techniques are “data hungry” whilst patient...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10417113/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583243270979584 |
|---|---|
| author | Harry J. Davies Ghena Hammour Hongjian Xiao Patrik Bachtiger Alexander Larionov Philip L. Molyneaux Nicholas S. Peters Danilo P. Mandic |
| author_facet | Harry J. Davies Ghena Hammour Hongjian Xiao Patrik Bachtiger Alexander Larionov Philip L. Molyneaux Nicholas S. Peters Danilo P. Mandic |
| author_sort | Harry J. Davies |
| collection | DOAJ |
| description | The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intelligence (AI) into respiratory healthcare. Deep learning techniques are “data hungry” whilst patient-based data is invariably expensive and time consuming to record. To this end, we introduce a novel COPD-simulator, a physical apparatus with an easy to replicate design which enables rapid and effective generation of a wide range of COPD-like data from healthy subjects, for enhanced training of deep learning frameworks. To ensure the faithfulness of our domain-aware COPD surrogates, the generated waveforms are examined through both flow waveforms and photoplethysmography (PPG) waveforms (as a proxy for intrathoracic pressure) in terms of duty cycle, sample entropy, FEV<sub>1</sub>/FVC ratios and flow-volume loops. The proposed simulator operates on healthy subjects and is able to generate FEV<sub>1</sub>/FVC obstruction ratios ranging from greater than 0.8 to less than 0.2, mirroring values that can observed in the full spectrum of real-world COPD. As a final stage of verification, a simple convolutional neural network is trained on surrogate data alone, and is used to accurately detect COPD in real-world patients. When training solely on surrogate data, and testing on real-world data, a comparison of true positive rate against false positive rate yields an area under the curve of 0.75, compared with 0.63 when training solely on real-world data. |
| format | Article |
| id | doaj-art-9614f87448ae4814921b8b144b44fc52 |
| institution | Kabale University |
| issn | 2644-1276 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-9614f87448ae4814921b8b144b44fc522025-01-29T00:01:26ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762024-01-01514815610.1109/OJEMB.2024.336068810417113Physically Meaningful Surrogate Data for COPDHarry J. Davies0https://orcid.org/0000-0001-7506-2300Ghena Hammour1https://orcid.org/0000-0003-3891-4783Hongjian Xiao2https://orcid.org/0000-0002-1615-8174Patrik Bachtiger3https://orcid.org/0000-0002-3502-8869Alexander Larionov4https://orcid.org/0009-0007-4261-5336Philip L. Molyneaux5https://orcid.org/0000-0003-1301-8800Nicholas S. Peters6https://orcid.org/0000-0002-3581-8078Danilo P. Mandic7https://orcid.org/0000-0001-8432-3963Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.National Heart and Lung Institute, Imperial College London, London, U.K.Department of Computing, Imperial College London, London, U.K.National Heart and Lung Institute, Imperial College London, London, U.K.National Heart and Lung Institute, Imperial College London, London, U.K.Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intelligence (AI) into respiratory healthcare. Deep learning techniques are “data hungry” whilst patient-based data is invariably expensive and time consuming to record. To this end, we introduce a novel COPD-simulator, a physical apparatus with an easy to replicate design which enables rapid and effective generation of a wide range of COPD-like data from healthy subjects, for enhanced training of deep learning frameworks. To ensure the faithfulness of our domain-aware COPD surrogates, the generated waveforms are examined through both flow waveforms and photoplethysmography (PPG) waveforms (as a proxy for intrathoracic pressure) in terms of duty cycle, sample entropy, FEV<sub>1</sub>/FVC ratios and flow-volume loops. The proposed simulator operates on healthy subjects and is able to generate FEV<sub>1</sub>/FVC obstruction ratios ranging from greater than 0.8 to less than 0.2, mirroring values that can observed in the full spectrum of real-world COPD. As a final stage of verification, a simple convolutional neural network is trained on surrogate data alone, and is used to accurately detect COPD in real-world patients. When training solely on surrogate data, and testing on real-world data, a comparison of true positive rate against false positive rate yields an area under the curve of 0.75, compared with 0.63 when training solely on real-world data.https://ieeexplore.ieee.org/document/10417113/COPDdeep learningphotoplethysmographysurrogate datawearable health |
| spellingShingle | Harry J. Davies Ghena Hammour Hongjian Xiao Patrik Bachtiger Alexander Larionov Philip L. Molyneaux Nicholas S. Peters Danilo P. Mandic Physically Meaningful Surrogate Data for COPD IEEE Open Journal of Engineering in Medicine and Biology COPD deep learning photoplethysmography surrogate data wearable health |
| title | Physically Meaningful Surrogate Data for COPD |
| title_full | Physically Meaningful Surrogate Data for COPD |
| title_fullStr | Physically Meaningful Surrogate Data for COPD |
| title_full_unstemmed | Physically Meaningful Surrogate Data for COPD |
| title_short | Physically Meaningful Surrogate Data for COPD |
| title_sort | physically meaningful surrogate data for copd |
| topic | COPD deep learning photoplethysmography surrogate data wearable health |
| url | https://ieeexplore.ieee.org/document/10417113/ |
| work_keys_str_mv | AT harryjdavies physicallymeaningfulsurrogatedataforcopd AT ghenahammour physicallymeaningfulsurrogatedataforcopd AT hongjianxiao physicallymeaningfulsurrogatedataforcopd AT patrikbachtiger physicallymeaningfulsurrogatedataforcopd AT alexanderlarionov physicallymeaningfulsurrogatedataforcopd AT philiplmolyneaux physicallymeaningfulsurrogatedataforcopd AT nicholasspeters physicallymeaningfulsurrogatedataforcopd AT danilopmandic physicallymeaningfulsurrogatedataforcopd |