Bibliographic Details
| Title: |
Yoga practices effect on VCSS-based classification of patients with chronic venous insufficiency based on hybrid machine learning algorithms |
| Authors: |
Changhong Pan, Lu Qi, Lili Zhao, Yijun Wei |
| Source: |
International Journal of Cognitive Computing in Engineering, Vol 6, Iss, Pp 255-266 (2025) |
| Publisher Information: |
Elsevier BV, 2025. |
| Publication Year: |
2025 |
| Subject Terms: |
Yoga practices, Venous clinical severity score, Decision Tree classifier, Electronic computers. Computer science, Science, Chronic venous insufficiency, QA75.5-76.95, Hybrid Machine Learning Algorithm |
| Description: |
Advancements in technology have increased work demands, neglecting individual well-being and causing mental pressure and decreased fitness. The COVID-19 pandemic has worsened this, leading to a surge in psychological stress. Non-pharmacological approaches like yoga are gaining popularity for stress management, showing positive effects on the autonomic nervous system and offering benefits such as improved cardio-respiratory health and metabolic efficiency, as well as positive effects on conditions like Type-2 diabetes, Chronic Venous Disease (CVD), and obesity. This investigation aims to introduce proficiently functioning machine learning classifiers, such as single and hybrid forms of Decision Trees (DT), into the domain of studies within this particular category. The study utilized 2 optimization algorithms, namely the Honey Badger Algorithm (HBA) and the Arithmetic Optimization Algorithm (AOA), to develop hybrid models. Venous Clinical Severity Score (VCSS) levels prior to and one month following yoga sessions were among the variables in the questionnaire that were considered as inputs: effective influences on CVD. The developed prediction models were trained, and their operational capability was tested. The extracted results classified the samples into 4 classes: Absent, Mild, Moderate, and Severe Chronic Venous Insufficiency (CVI). Comparative analysis revealed that DTHB (Decision Tree optimized with Honey Badger Algorithm) with maximum Accuracy and Precision of higher than 90 % was the optimal model, especially for classifying patients with Moderate and Severe levels of CVI needing emergency medical action. |
| Document Type: |
Article |
| Language: |
English |
| ISSN: |
2666-3074 |
| DOI: |
10.1016/j.ijcce.2025.01.003 |
| Access URL: |
https://doaj.org/article/094f4d3829df4bb496d23b86d20d4fbe |
| Rights: |
CC BY |
| Accession Number: |
edsair.doi.dedup.....070338d2fb199f84173f48efcd31525e |
| Database: |
OpenAIRE |