Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis

Begoña Ispizua; Diana Manjarrés; Iratxe Niño-Adan

doi:10.1109/BIBM58861.2023.10385780

Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis

Begoña Ispizua^*, Diana Manjarrés, Iratxe Niño-Adan

^*Autor correspondiente de este trabajo

IA

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

Resumen

Metabolic syndrome (MetS) is considered to be a major public health problem worldwide leading to a high risk of diabetes and cardiovascular diseases. In this paper, data collected by the Precision Medicine Initiative of the Basque Country, named the AKRIBEA project, is employed to infer via Machine Learning (ML) techniques the features that have the most influence on predicting MetS in the general case and also separately by gender. Different Feature Normalization (FN) and Feature Weighting (FW) methods are applied and an exhaustive analysis of explainability by means of Shapley Additive Explanations (SHAP) and feature relevance methods is performed. Validation results show that the Extreme Gradient Boosting (XGB) with Min-Max FN and Mutual Information FW achieves the best trade-off between precision and recall performance metrics.

Idioma original	Inglés
Título de la publicación alojada	Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023
Editores	Xingpeng Jiang, Haiying Wang, Reda Alhajj, Xiaohua Hu, Felix Engel, Mufti Mahmud, Nadia Pisanti, Xuefeng Cui, Hong Song
Editorial	Institute of Electrical and Electronics Engineers Inc.
Páginas	1989-1992
Número de páginas	4
ISBN (versión digital)	9798350337488
DOI	https://doi.org/10.1109/BIBM58861.2023.10385780
Estado	Publicada - 2023
Evento	2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023 - Istanbul, Turquía Duración: 5 dic 2023 → 8 dic 2023

Serie de la publicación

Nombre	Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

Conferencia

Conferencia	2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023
País/Territorio	Turquía
Ciudad	Istanbul
Período	5/12/23 → 8/12/23

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Acceder al documento

10.1109/BIBM58861.2023.10385780

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Ispizua, B., Manjarrés, D., & Niño-Adan, I. (2023). Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis. En X. Jiang, H. Wang, R. Alhajj, X. Hu, F. Engel, M. Mahmud, N. Pisanti, X. Cui, & H. Song (Eds.), Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023 (pp. 1989-1992). (Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM58861.2023.10385780

Ispizua, Begoña ; Manjarrés, Diana ; Niño-Adan, Iratxe. / Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis. Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023. editor / Xingpeng Jiang ; Haiying Wang ; Reda Alhajj ; Xiaohua Hu ; Felix Engel ; Mufti Mahmud ; Nadia Pisanti ; Xuefeng Cui ; Hong Song. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1989-1992 (Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023).

@inproceedings{610d5bf12ce74147bd52ea5f97499bb7,

title = "Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis",

abstract = "Metabolic syndrome (MetS) is considered to be a major public health problem worldwide leading to a high risk of diabetes and cardiovascular diseases. In this paper, data collected by the Precision Medicine Initiative of the Basque Country, named the AKRIBEA project, is employed to infer via Machine Learning (ML) techniques the features that have the most influence on predicting MetS in the general case and also separately by gender. Different Feature Normalization (FN) and Feature Weighting (FW) methods are applied and an exhaustive analysis of explainability by means of Shapley Additive Explanations (SHAP) and feature relevance methods is performed. Validation results show that the Extreme Gradient Boosting (XGB) with Min-Max FN and Mutual Information FW achieves the best trade-off between precision and recall performance metrics.",

keywords = "classification, explainability, feature relevances, machine learning, metabolic syndrome",

author = "Bego{\~n}a Ispizua and Diana Manjarr{\'e}s and Iratxe Ni{\~n}o-Adan",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023 ; Conference date: 05-12-2023 Through 08-12-2023",

year = "2023",

doi = "10.1109/BIBM58861.2023.10385780",

language = "English",

series = "Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1989--1992",

editor = "Xingpeng Jiang and Haiying Wang and Reda Alhajj and Xiaohua Hu and Felix Engel and Mufti Mahmud and Nadia Pisanti and Xuefeng Cui and Hong Song",

booktitle = "Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023",

address = "United States",

}

Ispizua, B , Manjarrés, D & Niño-Adan, I 2023, Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis. En X Jiang, H Wang, R Alhajj, X Hu, F Engel, M Mahmud, N Pisanti, X Cui & H Song (eds.), Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023. Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1989-1992, 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023, Istanbul, Turquía, 5/12/23. https://doi.org/10.1109/BIBM58861.2023.10385780

Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis. / Ispizua, Begoña ; Manjarrés, Diana; Niño-Adan, Iratxe.
Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023. ed. / Xingpeng Jiang; Haiying Wang; Reda Alhajj; Xiaohua Hu; Felix Engel; Mufti Mahmud; Nadia Pisanti; Xuefeng Cui; Hong Song. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1989-1992 (Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis

AU - Ispizua, Begoña

AU - Manjarrés, Diana

AU - Niño-Adan, Iratxe

PY - 2023

Y1 - 2023

N2 - Metabolic syndrome (MetS) is considered to be a major public health problem worldwide leading to a high risk of diabetes and cardiovascular diseases. In this paper, data collected by the Precision Medicine Initiative of the Basque Country, named the AKRIBEA project, is employed to infer via Machine Learning (ML) techniques the features that have the most influence on predicting MetS in the general case and also separately by gender. Different Feature Normalization (FN) and Feature Weighting (FW) methods are applied and an exhaustive analysis of explainability by means of Shapley Additive Explanations (SHAP) and feature relevance methods is performed. Validation results show that the Extreme Gradient Boosting (XGB) with Min-Max FN and Mutual Information FW achieves the best trade-off between precision and recall performance metrics.

AB - Metabolic syndrome (MetS) is considered to be a major public health problem worldwide leading to a high risk of diabetes and cardiovascular diseases. In this paper, data collected by the Precision Medicine Initiative of the Basque Country, named the AKRIBEA project, is employed to infer via Machine Learning (ML) techniques the features that have the most influence on predicting MetS in the general case and also separately by gender. Different Feature Normalization (FN) and Feature Weighting (FW) methods are applied and an exhaustive analysis of explainability by means of Shapley Additive Explanations (SHAP) and feature relevance methods is performed. Validation results show that the Extreme Gradient Boosting (XGB) with Min-Max FN and Mutual Information FW achieves the best trade-off between precision and recall performance metrics.

KW - classification

KW - explainability

KW - feature relevances

KW - machine learning

KW - metabolic syndrome

UR - http://www.scopus.com/inward/record.url?scp=85184906046&partnerID=8YFLogxK

U2 - 10.1109/BIBM58861.2023.10385780

DO - 10.1109/BIBM58861.2023.10385780

M3 - Conference contribution

AN - SCOPUS:85184906046

T3 - Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

SP - 1989

EP - 1992

BT - Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

A2 - Jiang, Xingpeng

A2 - Wang, Haiying

A2 - Alhajj, Reda

A2 - Hu, Xiaohua

A2 - Engel, Felix

A2 - Mahmud, Mufti

A2 - Pisanti, Nadia

A2 - Cui, Xuefeng

A2 - Song, Hong

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

Y2 - 5 December 2023 through 8 December 2023

ER -

Ispizua B , Manjarrés D, Niño-Adan I. Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis. En Jiang X, Wang H, Alhajj R, Hu X, Engel F, Mahmud M, Pisanti N, Cui X, Song H, editores, Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1989-1992. (Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023). doi: 10.1109/BIBM58861.2023.10385780

Prediction of Metabolic Syndrome Based on Machine Learning Techniques with Emphasis on Feature Relevances and Explainability Analysis

Resumen

Serie de la publicación

Conferencia

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto