On building machine learning models for medical dataset with correlated features
This work builds machine learning models for the dataset generated using a numerical model developed on an idealized human artery. The model has been constructed accounting for varying blood characteristics as it flows through arteries with variable vascular properties, and it is applied to simulate...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2024-03-01
|
Series: | Computational and Mathematical Biophysics |
Subjects: | |
Online Access: | https://doi.org/10.1515/cmb-2023-0124 |
_version_ | 1797258371693281280 |
---|---|
author | Nayak Debismita Tantravahi Sai Lakshmi Radhika |
author_facet | Nayak Debismita Tantravahi Sai Lakshmi Radhika |
author_sort | Nayak Debismita |
collection | DOAJ |
description | This work builds machine learning models for the dataset generated using a numerical model developed on an idealized human artery. The model has been constructed accounting for varying blood characteristics as it flows through arteries with variable vascular properties, and it is applied to simulate blood flow in the femoral and its continued artery. For this purpose, we designed a pipeline model consisting of three components to include the major segments of the femoral artery: CFA, the common femoral artery and SFA, the superficial artery, and its continued one, the popliteal artery (PA). A notable point of this study is that the features and target variables of the former component pipe form the set of features of the latter, thus resulting in multicollinearity among the features in the third component pipe. Thus, we worked on understanding the effect of these correlated features on the target variables using regularized linear regression models, ensemble, and boosting algorithms. This study highlighted the blood velocity in CFA as the primary influential factor for wall shear stress in both CFA and SFA. Additionally, it established the blood rheology in PA as a significant factor for the same in it. Nevertheless, because the study relies on idealized conditions, these discoveries necessitate thorough clinical validation. |
first_indexed | 2024-04-24T22:52:29Z |
format | Article |
id | doaj.art-514eecb191e64c1bbe171e1fdf012d2b |
institution | Directory Open Access Journal |
issn | 2544-7297 |
language | English |
last_indexed | 2024-04-24T22:52:29Z |
publishDate | 2024-03-01 |
publisher | De Gruyter |
record_format | Article |
series | Computational and Mathematical Biophysics |
spelling | doaj.art-514eecb191e64c1bbe171e1fdf012d2b2024-03-18T10:27:23ZengDe GruyterComputational and Mathematical Biophysics2544-72972024-03-0112112860012310.1515/cmb-2023-0124On building machine learning models for medical dataset with correlated featuresNayak Debismita0Tantravahi Sai Lakshmi Radhika1Department of Mathematics, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad-500078, IndiaDepartment of Mathematics, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad-500078, IndiaThis work builds machine learning models for the dataset generated using a numerical model developed on an idealized human artery. The model has been constructed accounting for varying blood characteristics as it flows through arteries with variable vascular properties, and it is applied to simulate blood flow in the femoral and its continued artery. For this purpose, we designed a pipeline model consisting of three components to include the major segments of the femoral artery: CFA, the common femoral artery and SFA, the superficial artery, and its continued one, the popliteal artery (PA). A notable point of this study is that the features and target variables of the former component pipe form the set of features of the latter, thus resulting in multicollinearity among the features in the third component pipe. Thus, we worked on understanding the effect of these correlated features on the target variables using regularized linear regression models, ensemble, and boosting algorithms. This study highlighted the blood velocity in CFA as the primary influential factor for wall shear stress in both CFA and SFA. Additionally, it established the blood rheology in PA as a significant factor for the same in it. Nevertheless, because the study relies on idealized conditions, these discoveries necessitate thorough clinical validation.https://doi.org/10.1515/cmb-2023-0124machine learning modelsfemoral arterynumerical modelcorrelated featuresquantile loss function76a0592-1092c1076z9997r40 |
spellingShingle | Nayak Debismita Tantravahi Sai Lakshmi Radhika On building machine learning models for medical dataset with correlated features Computational and Mathematical Biophysics machine learning models femoral artery numerical model correlated features quantile loss function 76a05 92-10 92c10 76z99 97r40 |
title | On building machine learning models for medical dataset with correlated features |
title_full | On building machine learning models for medical dataset with correlated features |
title_fullStr | On building machine learning models for medical dataset with correlated features |
title_full_unstemmed | On building machine learning models for medical dataset with correlated features |
title_short | On building machine learning models for medical dataset with correlated features |
title_sort | on building machine learning models for medical dataset with correlated features |
topic | machine learning models femoral artery numerical model correlated features quantile loss function 76a05 92-10 92c10 76z99 97r40 |
url | https://doi.org/10.1515/cmb-2023-0124 |
work_keys_str_mv | AT nayakdebismita onbuildingmachinelearningmodelsformedicaldatasetwithcorrelatedfeatures AT tantravahisailakshmiradhika onbuildingmachinelearningmodelsformedicaldatasetwithcorrelatedfeatures |