Research on noise-induced hearing loss based on functional and structural MRI using machine learning methods DOI Creative Commons

Minghui Lv,

Liping Wang, Ranran Huang

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 26, 2025

Noise-induced hearing loss (NIHL) is a common occupational condition. The aim of this study was to develop classification model for NIHL on the basis both functional magnetic resonance imaging (fMRI) and structural (sMRI) by applying machine learning methods. fMRI indices such as amplitude low-frequency fluctuation (ALFF), fractional (fALFF), regional homogeneity (ReHo), degree centrality (DC), sMRI gray matter volume (GMV), white (WMV), cortical thickness were extracted from each brain region. least absolute shrinkage selection operator used reduce select optimal features. support vector (SVM), random forest (RF) logistic regression (LR) algorithms, establish NIHL. Finally, SVM based combined indices, achieved best performance, with area under receiver operating characteristic curve 0.97 an accuracy 95%. that integrates indicators has greatest potential identifying patients healthy people, revealing complementary role in indicating it necessary include multiple when establishing model.

Language: Английский

Research on noise-induced hearing loss based on functional and structural MRI using machine learning methods DOI Creative Commons

Minghui Lv,

Liping Wang, Ranran Huang

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 26, 2025

Noise-induced hearing loss (NIHL) is a common occupational condition. The aim of this study was to develop classification model for NIHL on the basis both functional magnetic resonance imaging (fMRI) and structural (sMRI) by applying machine learning methods. fMRI indices such as amplitude low-frequency fluctuation (ALFF), fractional (fALFF), regional homogeneity (ReHo), degree centrality (DC), sMRI gray matter volume (GMV), white (WMV), cortical thickness were extracted from each brain region. least absolute shrinkage selection operator used reduce select optimal features. support vector (SVM), random forest (RF) logistic regression (LR) algorithms, establish NIHL. Finally, SVM based combined indices, achieved best performance, with area under receiver operating characteristic curve 0.97 an accuracy 95%. that integrates indicators has greatest potential identifying patients healthy people, revealing complementary role in indicating it necessary include multiple when establishing model.

Language: Английский

Citations

0