Predicting early Alzheimer’s with blood biomarkers and clinical features
Abstract Alzheimer’s disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer’s Disease Neuroim...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-56489-1 |
| _version_ | 1827130289531387904 |
|---|---|
| author | Muaath Ebrahim AlMansoori Sherlyn Jemimah Ferial Abuhantash Aamna AlShehhi |
| author_facet | Muaath Ebrahim AlMansoori Sherlyn Jemimah Ferial Abuhantash Aamna AlShehhi |
| author_sort | Muaath Ebrahim AlMansoori |
| collection | DOAJ |
| description | Abstract Alzheimer’s disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer’s Disease Neuroimaging Initiative (ADNI). Analyzing 623 ADNI participants, we found that the Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieved exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, we achieved very good performance (AUC = 0.65, AUC = 0.63, respectively). Using SHapley Additive exPlanations (SHAP), we identified significant features, potentially serving as AD biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. In summary, this genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods. |
| first_indexed | 2024-04-24T23:08:12Z |
| format | Article |
| id | doaj.art-7d13e93a6a0049f5bca060963b0e7c71 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2025-03-20T16:13:49Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-7d13e93a6a0049f5bca060963b0e7c712024-09-01T11:16:01ZengNature PortfolioScientific Reports2045-23222024-03-0114111510.1038/s41598-024-56489-1Predicting early Alzheimer’s with blood biomarkers and clinical featuresMuaath Ebrahim AlMansoori0Sherlyn Jemimah1Ferial Abuhantash2Aamna AlShehhi3Department of Biomedical Engineering, Khalifa UniversityDepartment of Biomedical Engineering, Khalifa UniversityDepartment of Biomedical Engineering, Khalifa UniversityDepartment of Biomedical Engineering, Khalifa UniversityAbstract Alzheimer’s disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer’s Disease Neuroimaging Initiative (ADNI). Analyzing 623 ADNI participants, we found that the Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieved exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, we achieved very good performance (AUC = 0.65, AUC = 0.63, respectively). Using SHapley Additive exPlanations (SHAP), we identified significant features, potentially serving as AD biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. In summary, this genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.https://doi.org/10.1038/s41598-024-56489-1Alzheimer’s diseaseMachine learningBlood biomarkersClinical features |
| spellingShingle | Muaath Ebrahim AlMansoori Sherlyn Jemimah Ferial Abuhantash Aamna AlShehhi Predicting early Alzheimer’s with blood biomarkers and clinical features Scientific Reports Alzheimer’s disease Machine learning Blood biomarkers Clinical features |
| title | Predicting early Alzheimer’s with blood biomarkers and clinical features |
| title_full | Predicting early Alzheimer’s with blood biomarkers and clinical features |
| title_fullStr | Predicting early Alzheimer’s with blood biomarkers and clinical features |
| title_full_unstemmed | Predicting early Alzheimer’s with blood biomarkers and clinical features |
| title_short | Predicting early Alzheimer’s with blood biomarkers and clinical features |
| title_sort | predicting early alzheimer s with blood biomarkers and clinical features |
| topic | Alzheimer’s disease Machine learning Blood biomarkers Clinical features |
| url | https://doi.org/10.1038/s41598-024-56489-1 |
| work_keys_str_mv | AT muaathebrahimalmansoori predictingearlyalzheimerswithbloodbiomarkersandclinicalfeatures AT sherlynjemimah predictingearlyalzheimerswithbloodbiomarkersandclinicalfeatures AT ferialabuhantash predictingearlyalzheimerswithbloodbiomarkersandclinicalfeatures AT aamnaalshehhi predictingearlyalzheimerswithbloodbiomarkersandclinicalfeatures |