Association between acoustic features and brain volumes: the Framingham Heart Study
IntroductionAlthough brain magnetic resonance imaging (MRI) is a valuable tool for investigating structural changes in the brain associated with neurodegeneration, the development of non-invasive and cost-effective alternative methods for detecting early cognitive impairment is crucial. The human vo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Dementia |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frdem.2023.1214940/full |
| _version_ | 1797492690015748096 |
|---|---|
| author | Huitong Ding Huitong Ding Alexander P. Hamel Cody Karjadi Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Sophia Lu Robert J. Thomas Rhoda Au Rhoda Au Rhoda Au Rhoda Au Rhoda Au Honghuang Lin |
| author_facet | Huitong Ding Huitong Ding Alexander P. Hamel Cody Karjadi Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Sophia Lu Robert J. Thomas Rhoda Au Rhoda Au Rhoda Au Rhoda Au Rhoda Au Honghuang Lin |
| author_sort | Huitong Ding |
| collection | DOAJ |
| description | IntroductionAlthough brain magnetic resonance imaging (MRI) is a valuable tool for investigating structural changes in the brain associated with neurodegeneration, the development of non-invasive and cost-effective alternative methods for detecting early cognitive impairment is crucial. The human voice has been increasingly used as an indicator for effectively detecting cognitive disorders, but it remains unclear whether acoustic features are associated with structural neuroimaging.MethodsThis study aims to investigate the association between acoustic features and brain volume and compare the predictive power of each for mild cognitive impairment (MCI) in a large community-based population. The study included participants from the Framingham Heart Study (FHS) who had at least one voice recording and an MRI scan. Sixty-five acoustic features were extracted with the OpenSMILE software (v2.1.3) from each voice recording. Nine MRI measures were derived according to the FHS MRI protocol. We examined the associations between acoustic features and MRI measures using linear regression models adjusted for age, sex, and education. Acoustic composite scores were generated by combining acoustic features significantly associated with MRI measures. The MCI prediction ability of acoustic composite scores and MRI measures were compared by building random forest models and calculating the mean area under the receiver operating characteristic curve (AUC) of 10-fold cross-validation.ResultsThe study included 4,293 participants (age 57 ± 13 years, 53.9% women). During 9.3 ± 3.7 years follow-up, 106 participants were diagnosed with MCI. Seven MRI measures were significantly associated with more than 20 acoustic features after adjusting for multiple testing. The acoustic composite scores can improve the AUC for MCI prediction to 0.794, compared to 0.759 achieved by MRI measures.DiscussionWe found multiple acoustic features were associated with MRI measures, suggesting the potential for using acoustic features as easily accessible digital biomarkers for the early diagnosis of MCI. |
| first_indexed | 2024-03-10T01:07:19Z |
| format | Article |
| id | doaj.art-5389832006cd441b95a48c70145cbc1f |
| institution | Directory Open Access Journal |
| issn | 2813-3919 |
| language | English |
| last_indexed | 2024-03-10T01:07:19Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Dementia |
| spelling | doaj.art-5389832006cd441b95a48c70145cbc1f2023-11-23T14:23:53ZengFrontiers Media S.A.Frontiers in Dementia2813-39192023-11-01210.3389/frdem.2023.12149401214940Association between acoustic features and brain volumes: the Framingham Heart StudyHuitong Ding0Huitong Ding1Alexander P. Hamel2Cody Karjadi3Ting F. A. Ang4Ting F. A. Ang5Ting F. A. Ang6Ting F. A. Ang7Sophia Lu8Robert J. Thomas9Rhoda Au10Rhoda Au11Rhoda Au12Rhoda Au13Rhoda Au14Honghuang Lin15Department of Anatomy and Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesThe Framingham Heart Study, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartment of Medicine, University of Massachusetts Chan Medical School, Worcester, MA, United StatesThe Framingham Heart Study, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartment of Anatomy and Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesThe Framingham Heart Study, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartment of Epidemiology, Boston University School of Public Health, Boston, MA, United StatesSlone Epidemiology Center, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesSlone Epidemiology Center, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDivision of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA, United StatesDepartment of Anatomy and Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesThe Framingham Heart Study, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartment of Epidemiology, Boston University School of Public Health, Boston, MA, United StatesSlone Epidemiology Center, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartments of Neurology and Medicine, Boston University Chobanian and Avedisian School of Medicine, Boston, MA, United StatesDepartment of Medicine, University of Massachusetts Chan Medical School, Worcester, MA, United StatesIntroductionAlthough brain magnetic resonance imaging (MRI) is a valuable tool for investigating structural changes in the brain associated with neurodegeneration, the development of non-invasive and cost-effective alternative methods for detecting early cognitive impairment is crucial. The human voice has been increasingly used as an indicator for effectively detecting cognitive disorders, but it remains unclear whether acoustic features are associated with structural neuroimaging.MethodsThis study aims to investigate the association between acoustic features and brain volume and compare the predictive power of each for mild cognitive impairment (MCI) in a large community-based population. The study included participants from the Framingham Heart Study (FHS) who had at least one voice recording and an MRI scan. Sixty-five acoustic features were extracted with the OpenSMILE software (v2.1.3) from each voice recording. Nine MRI measures were derived according to the FHS MRI protocol. We examined the associations between acoustic features and MRI measures using linear regression models adjusted for age, sex, and education. Acoustic composite scores were generated by combining acoustic features significantly associated with MRI measures. The MCI prediction ability of acoustic composite scores and MRI measures were compared by building random forest models and calculating the mean area under the receiver operating characteristic curve (AUC) of 10-fold cross-validation.ResultsThe study included 4,293 participants (age 57 ± 13 years, 53.9% women). During 9.3 ± 3.7 years follow-up, 106 participants were diagnosed with MCI. Seven MRI measures were significantly associated with more than 20 acoustic features after adjusting for multiple testing. The acoustic composite scores can improve the AUC for MCI prediction to 0.794, compared to 0.759 achieved by MRI measures.DiscussionWe found multiple acoustic features were associated with MRI measures, suggesting the potential for using acoustic features as easily accessible digital biomarkers for the early diagnosis of MCI.https://www.frontiersin.org/articles/10.3389/frdem.2023.1214940/fullmild cognitive impairmentdigital voicebrain volumeassociationprediction |
| spellingShingle | Huitong Ding Huitong Ding Alexander P. Hamel Cody Karjadi Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Ting F. A. Ang Sophia Lu Robert J. Thomas Rhoda Au Rhoda Au Rhoda Au Rhoda Au Rhoda Au Honghuang Lin Association between acoustic features and brain volumes: the Framingham Heart Study Frontiers in Dementia mild cognitive impairment digital voice brain volume association prediction |
| title | Association between acoustic features and brain volumes: the Framingham Heart Study |
| title_full | Association between acoustic features and brain volumes: the Framingham Heart Study |
| title_fullStr | Association between acoustic features and brain volumes: the Framingham Heart Study |
| title_full_unstemmed | Association between acoustic features and brain volumes: the Framingham Heart Study |
| title_short | Association between acoustic features and brain volumes: the Framingham Heart Study |
| title_sort | association between acoustic features and brain volumes the framingham heart study |
| topic | mild cognitive impairment digital voice brain volume association prediction |
| url | https://www.frontiersin.org/articles/10.3389/frdem.2023.1214940/full |
| work_keys_str_mv | AT huitongding associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT huitongding associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT alexanderphamel associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT codykarjadi associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT tingfaang associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT tingfaang associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT tingfaang associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT tingfaang associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT sophialu associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT robertjthomas associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT rhodaau associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT rhodaau associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT rhodaau associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT rhodaau associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT rhodaau associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy AT honghuanglin associationbetweenacousticfeaturesandbrainvolumestheframinghamheartstudy |