Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke
Abstract Background and objectives This study aimed to employ machine learning techniques to predict the clinical efficacy of acupuncture as an intervention for patients with upper limb motor dysfunction following ischemic stroke, as well as to assess its potential utility in clinical practice. Meth...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-11-01
|
| Series: | Chinese Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13020-024-01026-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850195753924820992 |
|---|---|
| author | Yuqi Tang Sixian Hu Yipeng Xu Linjia Wang Yu Fang Pei Yu Yaning Liu Jiangwei Shi Junwen Guan Ling Zhao |
| author_facet | Yuqi Tang Sixian Hu Yipeng Xu Linjia Wang Yu Fang Pei Yu Yaning Liu Jiangwei Shi Junwen Guan Ling Zhao |
| author_sort | Yuqi Tang |
| collection | DOAJ |
| description | Abstract Background and objectives This study aimed to employ machine learning techniques to predict the clinical efficacy of acupuncture as an intervention for patients with upper limb motor dysfunction following ischemic stroke, as well as to assess its potential utility in clinical practice. Methods Medical records and digital subtraction angiography (DSA) imaging data were collected from 735 ischemic stroke patients with upper limb motor dysfunction who were treated with standardized acupuncture at two hospitals. Following the initial screening, 314 patient datasets that met the inclusion criteria were selected. We applied three deep-learning algorithms (YOLOX, FasterRCNN, and TOOD) to develop the object detection model. Object detection results pertaining to the cerebral vessels were integrated into a clinical efficacy prediction model (random forest). This model aimed to classify patient responses to acupuncture treatment. Finally, the accuracies and discriminative capabilities of the prediction models were assessed. Results The object detection model achieved an optimal recognition rate, The mean average precisions of YOLOX, TOOD, and FasterRCNN were 0.61, 0.7, and 0.68, respectively. The prediction accuracy of the clinical efficacy model reached 93.6%, with all three-treatment response classification area under the curves (AUCs) exceeding 0.95. Feature extraction using the prediction model highlighted the significant influence of various cerebral vascular stenosis sites within the internal carotid artery (ICA) on prediction outcomes. Specifically, the initial and C1 segments of the ICA had the highest predictive weights among all stenosis sites. Additionally, stenosis of the middle cerebral, anterior cerebral, and posterior cerebral arteries exerted a notable influence on the predictions. In contrast, the stenosis sites within the vertebral artery exhibited minimal impact on the model's predictive abilities. Conclusions Results underscore the substantial predictive influence of each cerebral vascular stenosis site within the ICA, with the initial and C1 segments being pivotal predictors. |
| format | Article |
| id | doaj-art-503e5e91b9f84ee98d16f052fa406036 |
| institution | OA Journals |
| issn | 1749-8546 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | BMC |
| record_format | Article |
| series | Chinese Medicine |
| spelling | doaj-art-503e5e91b9f84ee98d16f052fa4060362025-08-20T02:13:40ZengBMCChinese Medicine1749-85462024-11-0119111310.1186/s13020-024-01026-5Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic strokeYuqi Tang0Sixian Hu1Yipeng Xu2Linjia Wang3Yu Fang4Pei Yu5Yaning Liu6Jiangwei Shi7Junwen Guan8Ling Zhao9School of Acu-Mox and Tuina, Chengdu University of Traditional Chinese MedicineDepartment of Radiology, West China Hospital, Sichuan UniversitySchool of Acu-Mox and Tuina, Chengdu University of Traditional Chinese MedicineChongqing Traditional Chinese Medicine HospitalDepartment of Neurology, Hospital of Chengdu University of Traditional Chinese MedicineSchool of Acu-Mox and Tuina, Chengdu University of Traditional Chinese MedicineSchool of Acu-Mox and Tuina, Chengdu University of Traditional Chinese MedicineNational Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, First Teaching Hospital of Tianjin University of Traditional Chinese MedicineNeurosurgery Department, West China Hospital, Sichuan UniversitySchool of Acu-Mox and Tuina, Chengdu University of Traditional Chinese MedicineAbstract Background and objectives This study aimed to employ machine learning techniques to predict the clinical efficacy of acupuncture as an intervention for patients with upper limb motor dysfunction following ischemic stroke, as well as to assess its potential utility in clinical practice. Methods Medical records and digital subtraction angiography (DSA) imaging data were collected from 735 ischemic stroke patients with upper limb motor dysfunction who were treated with standardized acupuncture at two hospitals. Following the initial screening, 314 patient datasets that met the inclusion criteria were selected. We applied three deep-learning algorithms (YOLOX, FasterRCNN, and TOOD) to develop the object detection model. Object detection results pertaining to the cerebral vessels were integrated into a clinical efficacy prediction model (random forest). This model aimed to classify patient responses to acupuncture treatment. Finally, the accuracies and discriminative capabilities of the prediction models were assessed. Results The object detection model achieved an optimal recognition rate, The mean average precisions of YOLOX, TOOD, and FasterRCNN were 0.61, 0.7, and 0.68, respectively. The prediction accuracy of the clinical efficacy model reached 93.6%, with all three-treatment response classification area under the curves (AUCs) exceeding 0.95. Feature extraction using the prediction model highlighted the significant influence of various cerebral vascular stenosis sites within the internal carotid artery (ICA) on prediction outcomes. Specifically, the initial and C1 segments of the ICA had the highest predictive weights among all stenosis sites. Additionally, stenosis of the middle cerebral, anterior cerebral, and posterior cerebral arteries exerted a notable influence on the predictions. In contrast, the stenosis sites within the vertebral artery exhibited minimal impact on the model's predictive abilities. Conclusions Results underscore the substantial predictive influence of each cerebral vascular stenosis site within the ICA, with the initial and C1 segments being pivotal predictors.https://doi.org/10.1186/s13020-024-01026-5StrokeMachine learningDSAObject detectionPredictive modelUpper limb dysfunction |
| spellingShingle | Yuqi Tang Sixian Hu Yipeng Xu Linjia Wang Yu Fang Pei Yu Yaning Liu Jiangwei Shi Junwen Guan Ling Zhao Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke Chinese Medicine Stroke Machine learning DSA Object detection Predictive model Upper limb dysfunction |
| title | Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| title_full | Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| title_fullStr | Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| title_full_unstemmed | Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| title_short | Clinical efficacy of DSA-based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| title_sort | clinical efficacy of dsa based features in predicting outcomes of acupuncture intervention on upper limb dysfunction following ischemic stroke |
| topic | Stroke Machine learning DSA Object detection Predictive model Upper limb dysfunction |
| url | https://doi.org/10.1186/s13020-024-01026-5 |
| work_keys_str_mv | AT yuqitang clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT sixianhu clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT yipengxu clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT linjiawang clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT yufang clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT peiyu clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT yaningliu clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT jiangweishi clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT junwenguan clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke AT lingzhao clinicalefficacyofdsabasedfeaturesinpredictingoutcomesofacupunctureinterventiononupperlimbdysfunctionfollowingischemicstroke |