Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data
Objective: To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data. Methods: Clinical indicators, echocardiographic data, traditional Chinese medicine (TCM) tongue manifestations, and...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-06-01
|
| Series: | Digital Chinese Medicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589377725000655 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839604039364378624 |
|---|---|
| author | Jiyu ZHANG Jiatuo XU Liping TU Hongyuan FU |
| author_facet | Jiyu ZHANG Jiatuo XU Liping TU Hongyuan FU |
| author_sort | Jiyu ZHANG |
| collection | DOAJ |
| description | Objective: To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data. Methods: Clinical indicators, echocardiographic data, traditional Chinese medicine (TCM) tongue manifestations, and facial features were collected from patients who underwent coronary computed tomography angiography (CTA) in the Cardiac Care Unit (CCU) of Shanghai Tenth People's Hospital between May 1, 2023 and May 1, 2024. An adaptive weighted multi-modal data fusion (AWMDF) model based on deep learning was constructed to predict the severity of coronary artery stenosis. The model was evaluated using metrics including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic (ROC) curve (AUC). Further performance assessment was conducted through comparisons with six ensemble machine learning methods, data ablation, model component ablation, and various decision-level fusion strategies. Results: A total of 158 patients were included in the study. The AWMDF model achieved excellent predictive performance (AUC = 0.973, accuracy = 0.937, precision = 0.937, recall = 0.929, and F1 score = 0.933). Compared with model ablation, data ablation experiments, and various traditional machine learning models, the AWMDF model demonstrated superior performance. Moreover, the adaptive weighting strategy outperformed alternative approaches, including simple weighting, averaging, voting, and fixed-weight schemes. Conclusion: The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support. |
| format | Article |
| id | doaj-art-c060ddc42d444bf9b50de4890b64fdbd |
| institution | Matheson Library |
| issn | 2589-3777 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Digital Chinese Medicine |
| spelling | doaj-art-c060ddc42d444bf9b50de4890b64fdbd2025-08-02T04:47:36ZengKeAi Communications Co., Ltd.Digital Chinese Medicine2589-37772025-06-0182163173Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine dataJiyu ZHANG0Jiatuo XU1Liping TU2Hongyuan FU3College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200120, ChinaCorresponding author.; College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200120, ChinaCollege of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200120, ChinaCollege of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai 200120, ChinaObjective: To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data. Methods: Clinical indicators, echocardiographic data, traditional Chinese medicine (TCM) tongue manifestations, and facial features were collected from patients who underwent coronary computed tomography angiography (CTA) in the Cardiac Care Unit (CCU) of Shanghai Tenth People's Hospital between May 1, 2023 and May 1, 2024. An adaptive weighted multi-modal data fusion (AWMDF) model based on deep learning was constructed to predict the severity of coronary artery stenosis. The model was evaluated using metrics including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic (ROC) curve (AUC). Further performance assessment was conducted through comparisons with six ensemble machine learning methods, data ablation, model component ablation, and various decision-level fusion strategies. Results: A total of 158 patients were included in the study. The AWMDF model achieved excellent predictive performance (AUC = 0.973, accuracy = 0.937, precision = 0.937, recall = 0.929, and F1 score = 0.933). Compared with model ablation, data ablation experiments, and various traditional machine learning models, the AWMDF model demonstrated superior performance. Moreover, the adaptive weighting strategy outperformed alternative approaches, including simple weighting, averaging, voting, and fixed-weight schemes. Conclusion: The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.http://www.sciencedirect.com/science/article/pii/S2589377725000655Coronary artery diseaseDeep learningMulti-modalClinical predictionTraditional Chinese medicine diagnosis |
| spellingShingle | Jiyu ZHANG Jiatuo XU Liping TU Hongyuan FU Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data Digital Chinese Medicine Coronary artery disease Deep learning Multi-modal Clinical prediction Traditional Chinese medicine diagnosis |
| title | Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data |
| title_full | Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data |
| title_fullStr | Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data |
| title_full_unstemmed | Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data |
| title_short | Construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi-modal fusion of traditional Chinese and western medicine data |
| title_sort | construction and evaluation of a predictive model for the degree of coronary artery occlusion based on adaptive weighted multi modal fusion of traditional chinese and western medicine data |
| topic | Coronary artery disease Deep learning Multi-modal Clinical prediction Traditional Chinese medicine diagnosis |
| url | http://www.sciencedirect.com/science/article/pii/S2589377725000655 |
| work_keys_str_mv | AT jiyuzhang constructionandevaluationofapredictivemodelforthedegreeofcoronaryarteryocclusionbasedonadaptiveweightedmultimodalfusionoftraditionalchineseandwesternmedicinedata AT jiatuoxu constructionandevaluationofapredictivemodelforthedegreeofcoronaryarteryocclusionbasedonadaptiveweightedmultimodalfusionoftraditionalchineseandwesternmedicinedata AT lipingtu constructionandevaluationofapredictivemodelforthedegreeofcoronaryarteryocclusionbasedonadaptiveweightedmultimodalfusionoftraditionalchineseandwesternmedicinedata AT hongyuanfu constructionandevaluationofapredictivemodelforthedegreeofcoronaryarteryocclusionbasedonadaptiveweightedmultimodalfusionoftraditionalchineseandwesternmedicinedata |