The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders
Abstract Background The increasing prevalence of neurocognitive disorders (NCDs) in the aging population worldwide has become a significant concern due to subjectivity of evaluations and the lack of precise diagnostic methods and specific indicators. Developing personalized diagnostic strategies for...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2024-01-01
|
Series: | Microbiome |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40168-023-01717-5 |
_version_ | 1797349762941321216 |
---|---|
author | Yan Han Xinglin Zeng Lin Hua Xingping Quan Ying Chen Manfei Zhou Yaochen Chuang Yang Li Shengpeng Wang Xu Shen Lai Wei Zhen Yuan Yonghua Zhao |
author_facet | Yan Han Xinglin Zeng Lin Hua Xingping Quan Ying Chen Manfei Zhou Yaochen Chuang Yang Li Shengpeng Wang Xu Shen Lai Wei Zhen Yuan Yonghua Zhao |
author_sort | Yan Han |
collection | DOAJ |
description | Abstract Background The increasing prevalence of neurocognitive disorders (NCDs) in the aging population worldwide has become a significant concern due to subjectivity of evaluations and the lack of precise diagnostic methods and specific indicators. Developing personalized diagnostic strategies for NCDs has therefore become a priority. Results Multimodal electroencephalography (EEG) data of a matched cohort of normal aging (NA) and NCDs seniors were recorded, and their faecal samples and urine exosomes were collected to identify multi-omics signatures and metabolic pathways in NCDs by integrating metagenomics, proteomics, and metabolomics analysis. Additionally, experimental verification of multi-omics signatures was carried out in aged mice using faecal microbiota transplantation (FMT). We found that NCDs seniors had low EEG power spectral density and identified specific microbiota, including Ruminococcus gnavus, Enterocloster bolteae, Lachnoclostridium sp. YL 32, and metabolites, including L-tryptophan, L-glutamic acid, gamma-aminobutyric acid (GABA), and fatty acid esters of hydroxy fatty acids (FAHFAs), as well as disturbed biosynthesis of aromatic amino acids and TCA cycle dysfunction, validated in aged mice. Finally, we employed a support vector machine (SVM) algorithm to construct a machine learning model to classify NA and NCDs groups based on the fusion of EEG data and multi-omics profiles and the model demonstrated 92.69% accuracy in classifying NA and NCDs groups. Conclusions Our study highlights the potential of multi-omics profiling and EEG data fusion in personalized diagnosis of NCDs, with the potential to improve diagnostic precision and provide insights into the underlying mechanisms of NCDs. Video Abstract |
first_indexed | 2024-03-08T12:35:07Z |
format | Article |
id | doaj.art-19eb83b39aba45ed81b4ad7473f3d214 |
institution | Directory Open Access Journal |
issn | 2049-2618 |
language | English |
last_indexed | 2024-03-08T12:35:07Z |
publishDate | 2024-01-01 |
publisher | BMC |
record_format | Article |
series | Microbiome |
spelling | doaj.art-19eb83b39aba45ed81b4ad7473f3d2142024-01-21T12:27:54ZengBMCMicrobiome2049-26182024-01-0112112410.1186/s40168-023-01717-5The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disordersYan Han0Xinglin Zeng1Lin Hua2Xingping Quan3Ying Chen4Manfei Zhou5Yaochen Chuang6Yang Li7Shengpeng Wang8Xu Shen9Lai Wei10Zhen Yuan11Yonghua Zhao12State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Avenida da UniversidadeCentre for Cognitive and Brain Sciences, University of Macau, Avenida da UniversidadeCentre for Cognitive and Brain Sciences, University of Macau, Avenida da UniversidadeState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Avenida da UniversidadeSchool of Health Economics and Management, Nanjing University of Chinese MedicineState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Avenida da UniversidadeKiang Wu Nursing College of MacauDepartment of Gastrointestinal Surgery, Second Clinical Medical College of Jinan University, Shenzhen People’s HospitalState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Avenida da UniversidadeJiangsu Key Laboratory of Drug Target and Drug for Degenerative Diseases, Nanjing University of Chinese MedicineSchool of Pharmaceutical Science, Southern Medical UniversityCentre for Cognitive and Brain Sciences, University of Macau, Avenida da UniversidadeState Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Avenida da UniversidadeAbstract Background The increasing prevalence of neurocognitive disorders (NCDs) in the aging population worldwide has become a significant concern due to subjectivity of evaluations and the lack of precise diagnostic methods and specific indicators. Developing personalized diagnostic strategies for NCDs has therefore become a priority. Results Multimodal electroencephalography (EEG) data of a matched cohort of normal aging (NA) and NCDs seniors were recorded, and their faecal samples and urine exosomes were collected to identify multi-omics signatures and metabolic pathways in NCDs by integrating metagenomics, proteomics, and metabolomics analysis. Additionally, experimental verification of multi-omics signatures was carried out in aged mice using faecal microbiota transplantation (FMT). We found that NCDs seniors had low EEG power spectral density and identified specific microbiota, including Ruminococcus gnavus, Enterocloster bolteae, Lachnoclostridium sp. YL 32, and metabolites, including L-tryptophan, L-glutamic acid, gamma-aminobutyric acid (GABA), and fatty acid esters of hydroxy fatty acids (FAHFAs), as well as disturbed biosynthesis of aromatic amino acids and TCA cycle dysfunction, validated in aged mice. Finally, we employed a support vector machine (SVM) algorithm to construct a machine learning model to classify NA and NCDs groups based on the fusion of EEG data and multi-omics profiles and the model demonstrated 92.69% accuracy in classifying NA and NCDs groups. Conclusions Our study highlights the potential of multi-omics profiling and EEG data fusion in personalized diagnosis of NCDs, with the potential to improve diagnostic precision and provide insights into the underlying mechanisms of NCDs. Video Abstracthttps://doi.org/10.1186/s40168-023-01717-5Neurocognitive disordersElectroencephalographyMetagenomicsProteomicsMetabolomicsSupport vector machine |
spellingShingle | Yan Han Xinglin Zeng Lin Hua Xingping Quan Ying Chen Manfei Zhou Yaochen Chuang Yang Li Shengpeng Wang Xu Shen Lai Wei Zhen Yuan Yonghua Zhao The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders Microbiome Neurocognitive disorders Electroencephalography Metagenomics Proteomics Metabolomics Support vector machine |
title | The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders |
title_full | The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders |
title_fullStr | The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders |
title_full_unstemmed | The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders |
title_short | The fusion of multi-omics profile and multimodal EEG data contributes to the personalized diagnostic strategy for neurocognitive disorders |
title_sort | fusion of multi omics profile and multimodal eeg data contributes to the personalized diagnostic strategy for neurocognitive disorders |
topic | Neurocognitive disorders Electroencephalography Metagenomics Proteomics Metabolomics Support vector machine |
url | https://doi.org/10.1186/s40168-023-01717-5 |
work_keys_str_mv | AT yanhan thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xinglinzeng thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT linhua thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xingpingquan thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yingchen thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT manfeizhou thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yaochenchuang thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yangli thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT shengpengwang thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xushen thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT laiwei thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT zhenyuan thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yonghuazhao thefusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yanhan fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xinglinzeng fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT linhua fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xingpingquan fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yingchen fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT manfeizhou fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yaochenchuang fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yangli fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT shengpengwang fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT xushen fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT laiwei fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT zhenyuan fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders AT yonghuazhao fusionofmultiomicsprofileandmultimodaleegdatacontributestothepersonalizeddiagnosticstrategyforneurocognitivedisorders |