{ "abstract": "Maternal family history (FHm) increases the risk for Alzheimer’s disease (AD) compared to paternal. However, family history information is often unknown, complicating identification of higher-risk patients. Parent-of-origin effects on brain atrophy and matrilineally inherited mitochondrial genomic variation have been reported, but their utility for risk stratification is unclear. Machine learning approaches show promise for identifying traits associated with FHm, potentially improving FHm prediction in patients with unknown family history. We assessed whether structural Magnetic Resonance Imaging variables and/or mitochondrial haplogroups could accurately predict self-reported FHm as a proxy for individuals with high AD risk. Datasets were divided into 80% training and 20% testing using stratified sampling, with 4-fold cross-validation for hyperparameter tuning and model optimization. Models were compared based on accuracy and AUC. Feature importance was evaluated to identify the most informative variables. Neuroimaging data were available for 1,129 participants with known family history (mean age 69 years; 61% female; 44% FHm-positive; 71% normal cognition; 20% without normal cognition). For neuroimaging only models, XGBoost (Accuracy = 0.59, AUC = 0.59) and naïve Bayes (Accuracy = 0.58, AUC = 0.58) performed best, with precuneus volume being the most important feature correlated with reported FHm. Inclusion of mitochondrial haplogroups reduced the sample size (n = 717) but had minimal impact on model performance using XGBoost (Accuracy = 0.62, AUC = 0.62). The R0 intermediate clade was the most important mitochondrial haplogroup, with the precuneus remaining the most important overall feature. This study is among the first to integrate neuroimaging and mitochondrial data to identify patients with self-reported FHm of AD. Our findings reinforce the precuneus as an AD-vulnerable region linked to FHm. The addition of mitochondrial haplogroups maintained accuracy similar to imaging alone, despite a reduced sample size. This highlights the potential of combining neuroimaging and mitochondrial genetics for identifying traits associated with reported FHm of AD when family history is unknown. Author summary: Having a mother with Alzheimer’s disease (AD) increases a person’s risk more than having a father with AD. Many individuals do not know their family history, complicating the identification of those at higher risk due to maternal family history. Prior research suggests brain changes and inherited mitochondrial DNA, may play a role. Analyzing data from large AD research datasets, we used machine learning to test whether brain MRI measurements and/or mitochondrial DNA could predict a maternal family history of AD. We compared models by accuracy and AUC and examined which features were most important. While accuracy was modest, the most significant MRI measure was the volume of the precuneus, a brain region vulnerable in AD. Prediction accuracy was similar when mitochondrial data were included, and the precuneus volume remained the most important model feature overall. This work is among the first to combine MRI and mitochondrial data to predict self-reported maternal family history of AD. The results emphasize the precuneus as a key region connected with a reported maternal family history of AD and suggest that integrating brain imaging and mitochondrial genetics may offer complementary information for identifying potential risk in the absence of family history, despite limited prediction performance.", "abstract_shown": true, "affiliations": [ "Center for Genomic Medicine, Children’s Mercy Research Institute, Kansas City, Missouri, United States of America", "Alzheimer’s Disease Research Center Neuroimaging Core, University of Kansas Medical Center, Fairway, Kansas, United States of America", "Department of Cell Biology and Physiology, University of Kansas Medical Center, Kansas City, Kansas, United States of America", "Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, Kansas, United States of America", "Department of Internal Medicine, Division of Medical Informatics, Division of Pulmonary Critical Care and Sleep Medicine, University of Kansas Medical Center, Kansas City, Kansas, United States of America", "Department of Neurology, University of Kansas Medical Center, Kansas City, Kansas, United States of America" ], "article_type": "Research Article", "arxiv": null, "author_total": 6, "authors": [ { "affs": [ 0 ], "name": "Olivia J. Veatch" }, { "affs": [ 1 ], "name": "Sreejata Dutta" }, { "affs": [ 2 ], "name": "Clayton O. Mansel" }, { "affs": [ 3 ], "name": "Ryan Townley" }, { "affs": [ 4 ], "name": "Mihaela E. Sardiu" }, { "affs": [ 5 ], "name": "Robyn A. Honea" } ], "bibtex": "https://research.draconitic.com/paper/71by10p3wx1j1.bib", "cited_by": 0, "doi": "10.1371/journal.page.0000045", "fulltext_url": null, "id": "71by10p3wx1j1", "issns": [ "3070-801X" ], "landing_url": "https://doi.org/10.1371/journal.page.0000045", "language": null, "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "journal", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "openalex", "2738|Dementia and Cognitive Impairment Research" ], [ "plos", "/Biology and life sciences/Biochemistry/Bioenergetics/Energy-producing organelles/Mitochondria" ], [ "plos", "/Biology and life sciences/Cell biology/Cellular structures and organelles/Energy-producing organelles/Mitochondria" ], [ "plos", "/Biology and life sciences/Evolutionary biology/Population genetics/Haplogroups" ], [ "plos", "/Biology and life sciences/Genetics/Mitochondrial genetics" ], [ "plos", "/Biology and life sciences/Genetics/Population genetics/Haplogroups" ], [ "plos", "/Biology and life sciences/Neuroscience/Neuroimaging" ], [ "plos", "/Biology and life sciences/Population biology/Population genetics/Haplogroups" ], [ "plos", "/Computer and information sciences/Artificial intelligence/Machine learning" ], [ "plos", "/Medicine and health sciences/Diagnostic medicine/Diagnostic radiology/Magnetic resonance imaging" ], [ "plos", "/Medicine and health sciences/Epidemiology/Medical risk factors" ], [ "plos", "/Medicine and health sciences/Medical conditions/Neurodegenerative diseases/Alzheimer's disease" ], [ "plos", "/Medicine and health sciences/Mental health and psychiatry/Dementia/Alzheimer's disease" ], [ "plos", "/Medicine and health sciences/Neurology/Dementia/Alzheimer's disease" ], [ "plos", "/Medicine and health sciences/Neurology/Neurodegenerative diseases/Alzheimer's disease" ], [ "plos", "/Medicine and health sciences/Radiology and imaging/Diagnostic radiology/Magnetic resonance imaging" ], [ "plos", "/Research and analysis methods/Imaging techniques/Diagnostic radiology/Magnetic resonance imaging" ], [ "plos", "/Research and analysis methods/Imaging techniques/Neuroimaging" ] ], "openalex": "W7214096804", "pdf_url": "https://journals.plos.org/agingandhealth/article/file?id=10.1371/journal.page.0000045&type=printable", "pmcid": null, "pmid": null, "published": "2026-09-23", "publisher": "Public Library of Science", "ris": "https://research.draconitic.com/paper/71by10p3wx1j1.ris", "sources": [ { "first_seen": "2026-10-30T12:17:43Z", "native_id": "10.1371/journal.page.0000045", "source": "plos", "url": "https://doi.org/10.1371/journal.page.0000045" } ], "subjects": [ { "field": "biology", "origin": "plos:genetics", "subfield": "genetics-genomics" }, { "field": "medicine", "origin": "plos:diagnostic radiology", "subfield": "imaging" }, { "field": "medicine", "origin": "plos:neurology", "subfield": "neurology" } ], "title": "Using machine learning of neuroimaging and mitochondrial haplogroups to predict maternal family history of Alzheimer’s disease", "title_text": "Using machine learning of neuroimaging and mitochondrial haplogroups to predict maternal family history of Alzheimer’s disease", "type": "peer-reviewed", "updated_at": "2026-10-30T12:17:43Z", "url": "https://research.draconitic.com/paper/71by10p3wx1j1", "venue": "PLOS Aging and Health", "versions": [] }