Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring最新文献

{"title":"Variation in depression's impact on dementia risk by age in adults aged ≥75 years.","authors":"Yoo Jin Jang, Ju-Yeong Park, Se Yun Kim, Jin-Hyung Jung, Kyungdo Han, Se Chang Yoon, Hong Jin Jeon","doi":"10.1002/dad2.70185","DOIUrl":"10.1002/dad2.70185","url":null,"abstract":"<p><strong>Introduction: </strong>Late-life depression is linked to an increased dementia risk; however, whether this relationship varies with age remains unclear.</p><p><strong>Methods: </strong>We analyzed data from 1,127,331 individuals aged ≥75 years without dementia from the Korean National Health Insurance database who had undergone health screening between 2012 and 2015. Participants were followed up for ≤10 years. Cox proportional hazards and Fine-Gray subdistribution models were used to estimate dementia risk.</p><p><strong>Results: </strong>Depression was associated with increased dementia risk in both the old-old (75 to 84 years; hazard ratio [HR]: 1.338, 95% confidence interval [CI]: 1.325 to 1.351) and the oldest-old (≥85 years; HR: 1.111, 95% CI: 1.071 to 1.152), with attenuated effects at older ages. Cerebrovascular disease modified this association in the old-old, but no interaction was observed in the oldest-old.</p><p><strong>Discussion: </strong>Depression's impact on dementia risk decreases with age. Cerebrovascular diseases may influence depression-associated neurodegenerative pathways, although this interaction diminishes in the oldest-old.</p><p><strong>Highlights: </strong>Depression increased dementia risk in adults aged 75 years and older.The strength of the association declined with advancing age.Effect modification by cerebrovascular disease was observed only in the 75 to 84 old group.Findings support age-related decline in depression's impact on dementia risk.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 4","pages":"e70185"},"PeriodicalIF":4.4,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12477493/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bayesian analysis of diagnostic timelines across Alzheimer's disease, frontotemporal dementia, and other neurodegenerative conditions.","authors":"Ananthan Ambikairajah, David Foxe, Ann-Marie G de Lange, James Carrick, Sau Chi Cheung, Velandai K Srikanth, Yun Tae Hwang, Rebekah M Ahmed, James R Burrell, Olivier Piguet","doi":"10.1002/dad2.70184","DOIUrl":"10.1002/dad2.70184","url":null,"abstract":"<p><strong>Introduction: </strong>Timely diagnosis is crucial for managing neurodegenerative conditions. This study investigated whether time from symptom onset to diagnosis differs by clinical syndrome and sex.</p><p><strong>Methods: </strong>This retrospective, cross-sectional study included 591 participants with Alzheimer's disease (AD), frontotemporal dementia (FTD) subtypes (behavioral variant FTD [bvFTD], semantic dementia [SD], and progressive non-fluent aphasia), logopenic progressive aphasia (LPA), and syndromes associated with movement disorders (corticobasal syndrome, FTD with motor neuron disease [FTD-MND], and progressive supranuclear palsy). Bayesian regression models were used to compute diagnostic timelines.</p><p><strong>Results: </strong>Compared to AD (3.35 years; 95% credible interval [CrI]: 3.03-3.72), SD and bvFTD had additional delays of 9.7 (95% CrI: 1.96-20.64) and 14.82 months (95% CrI: 6.94-25.42), respectively, while FTD-MND was shorter by 11.62 months (95% CrI: -15.7 to -4.68). Men with bvFTD had 23.64 month longer delays than women (95% CrI: 10.35-44.33).</p><p><strong>Discussion: </strong>Diagnostic delays may reflect syndrome-specific clinical features, diagnostic complexity, and sociocultural factors. Findings highlight the need for improved diagnostic pathways and pre-clinical biomarkers to facilitate earlier identification.</p><p><strong>Highlights: </strong>Bayesian analyses revealed that diagnostic delays differ by syndrome and sex.Alzheimer's disease (AD) was diagnosed on average 3.35 years after symptom onset.Diagnoses were delayed in semantic and behavioral variant frontotemporal dementia (bvFTD) compared to AD.Men with bvFTD had longer delays than women.Findings support need for improved diagnostic pathways and pre-clinical biomarkers.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70184"},"PeriodicalIF":4.4,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12477622/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can auditory processing dysfunction indicate early cognitive decline?","authors":"Xinrong Ma, Jiayu Li, Ying Wang, Shiyuan Li, Junjie Guo, Wenxin Shen, Xiao Yu, Hongyu Dong, Shujian Huang, Linpeng Li, Jian Wang, Shankai Yin, Hui Wang","doi":"10.1002/dad2.70189","DOIUrl":"10.1002/dad2.70189","url":null,"abstract":"<p><strong>Introduction: </strong>Central auditory processing (CAP) is crucial for speech perception and is also fundamental for cognitive function. This study investigated whether gap detection threshold (GDT) could serve as an early marker for identifying individuals with cognitive impairment (CI) at high risk of dementia.</p><p><strong>Methods: </strong>Sixty-four older adults underwent peripheral auditory, cognitive, and CAP assessments. Machine learning and resting state electroencephalography (EEG)/event-related potential (ERP) analyses explored predictors and neural correlates of CI.</p><p><strong>Results: </strong>GDT was significantly higher in those with CI (mean ± standard deviation: 8.25 ± 6.14 versus 5.98 ± 3.44 ms, respectively, <i>p</i> = 0.034), and negatively correlated with cognitive test scores (e.g., Addenbrooke's Cognitive Examination III: <i>r</i> = -0.40, <i>p</i> = 0.001). GDT emerged as a key predictor. EEG showed altered auditory connectivity and ERP revealed reduced N1/N2 amplitudes in high-GDT individuals (false discovery rate corrected <i>p</i> < 0.05).</p><p><strong>Discussion: </strong>GDT may reflect early neurophysiological changes in individuals with CI and has potential as a non-invasive biomarker.</p><p><strong>Highlights: </strong>Central auditory processing (CAP) test scores were found to be significantly correlated with cognitive tests.By machine learning, the best variable gap detection threshold (GDT) for predicting cognitive impairment was screened out.GDT subgroup analysis was performed within the normal control (NC) group. Compared to the low GDT subgroup, the high GDT subgroup had lower amplitudes of the cognitive components of the event-related potential and many differences in functional connectivity, indicating that GDT has predictive value for changes in cognitive function.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 4","pages":"e70189"},"PeriodicalIF":4.4,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12464561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A vision transformer approach for fully automated and scalable dementia screening using clock drawing test images.","authors":"Michael B Bone, Morris Freedman, Sandra E Black, Daniel Felsky, Sanjeev Kumar, Bradley Pugh, Stephen C Strother, David F Tang-Wai, Maria Carmela Tartaglia, Bradley R Buchsbaum","doi":"10.1002/dad2.70171","DOIUrl":"10.1002/dad2.70171","url":null,"abstract":"<p><strong>Introduction: </strong>The clock drawing test (CDT) screens for dementia but requires trained scorers and lacks standardized criteria. Thus, we developed an automated vision transformer (ViT)-based diagnostic system with convolutional neural network preprocessing for analyzing hand-drawn CDT images.</p><p><strong>Methods: </strong>The architecture implements fine-tuned ViT feature extraction with linear classification for dementia prediction. Training used the National Health and Aging Trends Study (NHATS) dataset (<i>n</i> = 54,027), with testing on an independent clinical cohort from the Toronto Dementia Research Alliance (TDRA; <i>n</i> = 862; 522 dementia, 340 normal cognition).</p><p><strong>Results: </strong>The ViT approach predicted dementia with 76.5% balanced accuracy, outperforming human-scored features (74.3%) and existing deep learning models (MiniVGG = 73.3%, MobileNetV2 = 72.3%, relevance factor variational autoencoder = 69.1%) on the TDRA dataset.</p><p><strong>Discussion: </strong>This pen-and-paper compatible diagnostic system enables scalable remote cognitive screening through automated CDT image analysis that is competitive with human-scored features, potentially increasing diagnostic accessibility for diverse populations across varied socioeconomic contexts.</p><p><strong>Highlights: </strong>The vision transformer model achieves 76.5% accuracy in dementia detection from clock drawing tests, outperforming human scoring and existing deep learning methods.Novel convolutional neural network-based preprocessing automatically handles challenging image quality issues like shadows, irrelevant markings, and improper cropping.The system requires only a photo of a hand-drawn clock test, enabling scalable remote screening accessible across socioeconomic contexts.A feature-extraction model trained on 54,027 samples demonstrates robust generalization to an independent clinical dataset of 862 patients.This fully automated approach eliminates the need for trained scorers while maintaining diagnostic accuracy above manual methods.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70171"},"PeriodicalIF":4.4,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12457074/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145151855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optical coherence tomography as a potential biomarker for the logopenic variant of primary progressive aphasia: A cross-sectional prospective study.","authors":"Fei Wu, Monica Lavoie, Mélanie Hébert, Ali Dirani, Robert Laforce","doi":"10.1002/dad2.70188","DOIUrl":"10.1002/dad2.70188","url":null,"abstract":"<p><strong>Background: </strong>Optical coherence tomography (OCT) and OCT angiography (OCT-A) have been studied as biomarkers for Alzheimer's disease (AD), with promising results. Nevertheless, their potential in the logopenic variant of primary progressive aphasia (lvPPA), which shares the same amyloid pathology, has not yet been explored. This work aimed to characterize retinal changes in lvPPA compared to healthy controls.</p><p><strong>Methods: </strong>Ten participants with lvPPA and eleven controls underwent OCT and OCT-A imaging. Amyloid pathology in lvPPA was confirmed by lumbar puncture. Retinal parameters included retinal nerve fiber layer (RNFL) thickness and foveal avascular zone (FAZ).</p><p><strong>Results: </strong>Compared to controls, lvPPA participants exhibited reduced RNFL thickness in the temporal sector (<i>p</i> = 0.013) and significantly decreased FAZ circularity (<i>p</i> = 0.002).</p><p><strong>Discussion: </strong>RNFL thinning may reflect trans-synaptic degeneration from cortical atrophy, while reduced FAZ circularity suggests early microvascular changes related to amyloid burden. Our findings support OCT and OCT-A as potential biomarkers for lvPPA.</p><p><strong>Highlights: </strong>For the first time, OCT and OCT-A are studied as potential biomarkers for lvPPA.Compared to healthy controls, retinal nerve thickness is decreased in lvPPA patients.Retinal vasculature exhibits structural alterations in lvPPA patients.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70188"},"PeriodicalIF":4.4,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12455141/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145138972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to \"Gender differences in Cognitive Reserve: An impact on progression in Subjective Cognitive Decline?\"","authors":"","doi":"10.1002/dad2.70191","DOIUrl":"https://doi.org/10.1002/dad2.70191","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1002/dad2.70174.].</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70191"},"PeriodicalIF":4.4,"publicationDate":"2025-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12450579/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145131785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting cognitive status in stroke survivors from driving performance.","authors":"Stefan Delmas, Anjali Tiwari, Sharon N Poisson, Manfred Diehl, Neha Lodha","doi":"10.1002/dad2.70183","DOIUrl":"10.1002/dad2.70183","url":null,"abstract":"<p><strong>Introduction: </strong>This study aimed to determine whether simulated driving performance can reliably predict cognitive impairment in stroke survivors.</p><p><strong>Methods: </strong>Cognitively impaired (<i>n</i> = 35) and normal (<i>n</i> = 54) stroke survivors completed a simulated driving course with reactive, distracted, and route-planning sections. Performance was assessed using lane departures, average speed, brake reaction time, task completion time, and route accuracy.</p><p><strong>Results: </strong>Logistic regression models correctly distinguished cognitive status in 77.5% of cases for reactive and distracted driving, and 80.9% for route planning. Notably, the route planning task also achieved the highest classification rate of cognitively impaired participants (∼70%). Receiver operating characteristic (ROC) analyses on the strongest predictors from each driving section revealed significant areas under the curve (AUCs), with optimal cutoffs identifying cognitively impaired participants at 70%-80% accuracy.</p><p><strong>Discussion: </strong>These findings provide a critical foundation for developing simulator-based assessments as practical, functionally relevant screening tools for identifying cognitive impairment and determining driving readiness post-stroke.</p><p><strong>Highlights: </strong>Stroke survivors were tested on simulated driving tasks.Driving metrics were lane departures, speed, reaction time, and route accuracy.Cognitive status was predicted with greater than 75% accuracy.Simulators may be a clinical tool for assessing post-stroke driving readiness.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70183"},"PeriodicalIF":4.4,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12441590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145088281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sex differences in life expectancy in dementia, mild cognitive impairment (MCI), and subjective cognitive decline (SCD).","authors":"Rachel Amland, Geir Selbæk, Anne Brækhus, Hanneke F M Rhodius-Meester, Bjørn H Strand","doi":"10.1002/dad2.70177","DOIUrl":"10.1002/dad2.70177","url":null,"abstract":"<p><strong>Introduction: </strong>It is unclear how dementia affects loss in life expectancy (LE). In this registry-based study, we aimed to study sex differences in LE and loss in LE in dementia, mild cognitive impairment (MCI), and subjective cognitive decline (SCD).</p><p><strong>Methods: </strong>A total of 16,358 patients diagnosed with dementia, MCI, or SCD from the Norwegian Registry of Persons Assessed for Cognitive Symptoms (NorCog) during 2009-2022 were included and followed up for mortality. Sex differences in LE and loss in LE were predicted using flexible parametric survival models and sex-specific mortality in the general population as reference.</p><p><strong>Results: </strong>Among dementia patients, women with dementia had the largest loss in LE: 17 years loss at 60 years; correspondingly, men lost 13.5 years. Similar patterns were observed for MCI and dementia subtypes.</p><p><strong>Discussion: </strong>Women with dementia or MCI had a larger loss in LE compared to men with these diagnoses.</p><p><strong>Highlights: </strong>Women with dementia had the largest loss in life expectancy compared to the general population.The excess female loss in life expectancy was also evident for all the dementia subtypes and for mild cognitive impairment.The loss in life expectancy was more pronounced in younger patients with dementia, with a loss of 17 years in women at 60 years of age. Men, in comparison, lost 13.5 years at the same age.Subjective cognitive decline was associated with a minor loss in life expectancy in both sexes.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70177"},"PeriodicalIF":4.4,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12434703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145076522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Longitudinal changes in the brain-age gap in mild cognitive impairment and their relationships with neuropsychological functions and Alzheimer's disease biomarkers.","authors":"Rachel R Jin, Yue Gu, Tatia M C Lee","doi":"10.1002/dad2.70180","DOIUrl":"10.1002/dad2.70180","url":null,"abstract":"<p><strong>Introduction: </strong>The discrepancy between biological and modeled brain ages-the brain-age gap (BAG)-could indicate potential neuropsychological changes. This study verified if and how longitudinal BAG changes were associated with neuropsychological functions and Alzheimer's disease-related biomarkers in individuals with mild cognitive impairment (MCI).</p><p><strong>Methods: </strong>One hundred thirty-eight individuals with MCI and 103 healthy controls (HCs) with three rounds of magnetic resonance imaging scanning were selected from the Alzheimer's Disease Neuroimaging Initiative. We applied support vector regression on functional connectivity for modeling the brain age and further calculated the BAG.</p><p><strong>Results: </strong>Longitudinal BAG changes were higher in participants with MCI compared to HCs. Larger BAG fluctuations were correlated with poorer cognitive performance and more severe depressive symptoms in patients with MCI. Neurofilament light chain and phosphorylated tau levels were associated with the longitudinal BAG changes.</p><p><strong>Discussion: </strong>Present findings demonstrated the necessity of incorporating longitudinal BAG in monitoring the neuropsychological status among cognitively vulnerable populations.</p><p><strong>Highlights: </strong>Brain-age gap (BAG) changes are sensitive indicators of cognitive vulnerability in aging.BAG changes were larger in patients with mild cognitive impairment than in the controls.Longitudinal BAG changes were associated with worse cognitive-affective states.The plasma neurofilament light chain and cerebrospinal fluid phosphorylated tau levels were associated with the BAG changes.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70180"},"PeriodicalIF":4.4,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12434607/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145076507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning diagnosis of mild cognitive impairment using advanced diffusion MRI and CSF biomarkers.","authors":"Alexander Y Guo, John P Laporte, Kavita Singh, Jonghyun Bae, Keagan Bergeron, Angelique de Rouen, Noam Y Fox, Nathan Zhang, Isabel Carino-Bazan, Mary E Faulkner, Rafael de Cabo, Dan Benjamini, Zhaoyuan Gong, Mustapha Bouhrara","doi":"10.1002/dad2.70182","DOIUrl":"10.1002/dad2.70182","url":null,"abstract":"<p><strong>Introduction: </strong>Machine learning applied to neuroimaging can help with medical diagnosis and early detection by identifying biomarkers of subtle changes in brain structure and function. The effectiveness of advanced diffusion MRI (dMRI) methods for pre-dementia classification remains largely unexplored, particularly when combined with CSF biomarkers.</p><p><strong>Methods: </strong>We implemented XGBoost machine learning models to evaluate the classification potential of dMRI parameters (derived using NODDI, C-NODDI, MAP, or SMI), CSF biomarkers of Alzheimer's pathology (Tau, pTau, Aβ42, Aβ40), and pairwise dMRI + CSF combinations in distinguishing cognitive normality from mild cognitive impairment.</p><p><strong>Results: </strong>MAP-RTAP (AUC = 0.78) and pTau/Aβ42 (AUC = 0.76) were the best performing individual biomarkers. Combining C-NDI derived using C-NODDI and Aβ42/Aβ40 achieved the highest performance (AUC = 0.84) and accuracy (0.84), while other combinations optimized either sensitivity (0.93) or specificity (0.88).</p><p><strong>Discussion: </strong>dMRI biomarkers demonstrate comparable performance to CSF biomarkers, with notable improvements achieved when combined. This study highlights dMRI's effectiveness for enhancing early AD detection.</p><p><strong>Highlights: </strong>Advanced multishell diffusion MRI provides equivalent performance as CSF biomarkers in classifying MCICombining diffusion MRI and CSF biomarkers improves classification performanceStatistical diffusion MRI models perform best when used individually to classify MCIThe pTau/Aβ42 ratio outperforms other individual CSF biomarkers in MCI diagnosisBiophysical diffusion MRI models achieve the best performance when combined with CSF data.</p>","PeriodicalId":53226,"journal":{"name":"Alzheimer''s and Dementia: Diagnosis, Assessment and Disease Monitoring","volume":"17 3","pages":"e70182"},"PeriodicalIF":4.4,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12426029/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}