Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series
Chronic Obstructive Pulmonary Disease (COPD) is a chronic lung condition characterized by airflow obstruction. Current diagnostic methods primarily rely on identifying prominent features in spirometry (Volume-Flow time series) to detect COPD, but they are not adept at predicting future COPD risk bas...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Nature Research
2025
|
| _version_ | 1824459294918049792 |
|---|---|
| author | Mei, S Li, X Zhou, Y Xu, J Zhang, Y Wan, Y Cao, S Zhao, Q Geng, S Xie, J Chen, S Hong, S |
| author_facet | Mei, S Li, X Zhou, Y Xu, J Zhang, Y Wan, Y Cao, S Zhao, Q Geng, S Xie, J Chen, S Hong, S |
| author_sort | Mei, S |
| collection | OXFORD |
| description | Chronic Obstructive Pulmonary Disease (COPD) is a chronic lung condition characterized by airflow obstruction. Current diagnostic methods primarily rely on identifying prominent features in spirometry (Volume-Flow time series) to detect COPD, but they are not adept at predicting future COPD risk based on subtle data patterns. In this study, we introduce a novel deep learning-based approach, DeepSpiro, aimed at the early prediction of future COPD risk. DeepSpiro consists of four key components: SpiroSmoother for stabilizing the Volume-Flow curve, SpiroEncoder for capturing volume variability-pattern through key patches of varying lengths, SpiroExplainer for integrating heterogeneous data and explaining predictions through volume attention, and SpiroPredictor for predicting the disease risk of undiagnosed high-risk patients based on key patch concavity, with prediction horizons of 1–5 years, or even longer. Evaluated on the UK Biobank dataset, DeepSpiro achieved an AUC of 0.8328 for COPD detection and demonstrated strong predictive performance for future COPD risk (p-value < 0.001). In summary, DeepSpiro can effectively predict the long-term progression of COPD disease. |
| first_indexed | 2025-02-19T04:39:30Z |
| format | Journal article |
| id | oxford-uuid:65dc3043-9696-41c8-9ad8-21dcb4c7d14f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:39:30Z |
| publishDate | 2025 |
| publisher | Nature Research |
| record_format | dspace |
| spelling | oxford-uuid:65dc3043-9696-41c8-9ad8-21dcb4c7d14f2025-02-15T20:09:06ZDeep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time seriesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:65dc3043-9696-41c8-9ad8-21dcb4c7d14fEnglishJisc Publications RouterNature Research2025Mei, SLi, XZhou, YXu, JZhang, YWan, YCao, SZhao, QGeng, SXie, JChen, SHong, SChronic Obstructive Pulmonary Disease (COPD) is a chronic lung condition characterized by airflow obstruction. Current diagnostic methods primarily rely on identifying prominent features in spirometry (Volume-Flow time series) to detect COPD, but they are not adept at predicting future COPD risk based on subtle data patterns. In this study, we introduce a novel deep learning-based approach, DeepSpiro, aimed at the early prediction of future COPD risk. DeepSpiro consists of four key components: SpiroSmoother for stabilizing the Volume-Flow curve, SpiroEncoder for capturing volume variability-pattern through key patches of varying lengths, SpiroExplainer for integrating heterogeneous data and explaining predictions through volume attention, and SpiroPredictor for predicting the disease risk of undiagnosed high-risk patients based on key patch concavity, with prediction horizons of 1–5 years, or even longer. Evaluated on the UK Biobank dataset, DeepSpiro achieved an AUC of 0.8328 for COPD detection and demonstrated strong predictive performance for future COPD risk (p-value < 0.001). In summary, DeepSpiro can effectively predict the long-term progression of COPD disease. |
| spellingShingle | Mei, S Li, X Zhou, Y Xu, J Zhang, Y Wan, Y Cao, S Zhao, Q Geng, S Xie, J Chen, S Hong, S Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title | Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title_full | Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title_fullStr | Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title_full_unstemmed | Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title_short | Deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| title_sort | deep learning for detecting and early predicting chronic obstructive pulmonary disease from spirogram time series |
| work_keys_str_mv | AT meis deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT lix deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT zhouy deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT xuj deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT zhangy deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT wany deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT caos deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT zhaoq deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT gengs deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT xiej deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT chens deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries AT hongs deeplearningfordetectingandearlypredictingchronicobstructivepulmonarydiseasefromspirogramtimeseries |