Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data

Abstract Purpose Accurately detecting Acute bilirubin encephalopathy (ABE) from non-ABE neonates with hyperbilirubinemia (HB) condition remains a challenge in clinical practice. In this study, an automatic ABE diagnosing system based on multi-modal MRI images and non-image clinical metadata is propo...

Full description

Saved in:
Bibliographic Details
Main Authors: Miao Wu, Qian Liu, Can Lai
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Pediatrics
Subjects:
Online Access:https://doi.org/10.1186/s12887-025-05411-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704145458561024
author Miao Wu
Qian Liu
Can Lai
author_facet Miao Wu
Qian Liu
Can Lai
author_sort Miao Wu
collection DOAJ
description Abstract Purpose Accurately detecting Acute bilirubin encephalopathy (ABE) from non-ABE neonates with hyperbilirubinemia (HB) condition remains a challenge in clinical practice. In this study, an automatic ABE diagnosing system based on multi-modal MRI images and non-image clinical metadata is proposed to address the issue. Methods A total of 75 ABE neonates and 75 non-ABE neonates with HB are included in the study. Each patient has 3 multi-modal magnetic resonance images and 8 non-image clinical features. To investigate the diagnosing model’s performance, 3 different feature sets, namely deep features from multi-modal MRI images, non-image clinical features, and fusion features, are extracted, respectively, and then further classified by a support vector machine (SVM), respectively. Results The results indicated the SVM classifier built on the fusion features achieved the best classification performance with an accuracy of 93.24 ± 2.35, specificity of 91.38 ± 4.45%, sensitivity of 95.11 ± 2.97%, precision of 91.87 ± 3.88%, area-under-the-curve (AUC) of 98.08 ± 1.16%, F1_score of 93.38 ± 2.23%. The performance of the SVM classifier built on the deep features was better than that built on the non-image clinical features. Conclusion Our study demonstrated that ABE diagnostic performance based on deep features from multi-modal MRI images could be significantly improved by incorporating clinical features. The proposed strategy may potentially be applicable to clinical practice to facilitate clinical management.
format Article
id doaj-art-e97b90d4e41e4f6c859946dc3e825a5d
institution DOAJ
issn 1471-2431
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Pediatrics
spelling doaj-art-e97b90d4e41e4f6c859946dc3e825a5d2025-08-20T03:16:51ZengBMCBMC Pediatrics1471-24312025-05-012511810.1186/s12887-025-05411-3Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical dataMiao Wu0Qian Liu1Can Lai2College of Medical Engineering and Technology, Xinjiang Medical UniversityBasic Medical College, Xinjiang Medical UniversityDepartment of Radiology, Children’s Hospital, Zhejiang University School of MedicineAbstract Purpose Accurately detecting Acute bilirubin encephalopathy (ABE) from non-ABE neonates with hyperbilirubinemia (HB) condition remains a challenge in clinical practice. In this study, an automatic ABE diagnosing system based on multi-modal MRI images and non-image clinical metadata is proposed to address the issue. Methods A total of 75 ABE neonates and 75 non-ABE neonates with HB are included in the study. Each patient has 3 multi-modal magnetic resonance images and 8 non-image clinical features. To investigate the diagnosing model’s performance, 3 different feature sets, namely deep features from multi-modal MRI images, non-image clinical features, and fusion features, are extracted, respectively, and then further classified by a support vector machine (SVM), respectively. Results The results indicated the SVM classifier built on the fusion features achieved the best classification performance with an accuracy of 93.24 ± 2.35, specificity of 91.38 ± 4.45%, sensitivity of 95.11 ± 2.97%, precision of 91.87 ± 3.88%, area-under-the-curve (AUC) of 98.08 ± 1.16%, F1_score of 93.38 ± 2.23%. The performance of the SVM classifier built on the deep features was better than that built on the non-image clinical features. Conclusion Our study demonstrated that ABE diagnostic performance based on deep features from multi-modal MRI images could be significantly improved by incorporating clinical features. The proposed strategy may potentially be applicable to clinical practice to facilitate clinical management.https://doi.org/10.1186/s12887-025-05411-3DetectingAcute bilirubin encephalopathyHyperbilirubinemiaNeonatesMultimodal MRI imagesNon-image clinical data
spellingShingle Miao Wu
Qian Liu
Can Lai
Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
BMC Pediatrics
Detecting
Acute bilirubin encephalopathy
Hyperbilirubinemia
Neonates
Multimodal MRI images
Non-image clinical data
title Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
title_full Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
title_fullStr Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
title_full_unstemmed Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
title_short Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI images and non-image clinical data
title_sort detecting acute bilirubin encephalopathy in neonates based on multimodal mri images and non image clinical data
topic Detecting
Acute bilirubin encephalopathy
Hyperbilirubinemia
Neonates
Multimodal MRI images
Non-image clinical data
url https://doi.org/10.1186/s12887-025-05411-3
work_keys_str_mv AT miaowu detectingacutebilirubinencephalopathyinneonatesbasedonmultimodalmriimagesandnonimageclinicaldata
AT qianliu detectingacutebilirubinencephalopathyinneonatesbasedonmultimodalmriimagesandnonimageclinicaldata
AT canlai detectingacutebilirubinencephalopathyinneonatesbasedonmultimodalmriimagesandnonimageclinicaldata