The Journal of Prevention of Alzheimer's Disease最新文献

{"title":"Biofluid biomarker changes following treatment with sabirnetug (ACU193) in INTERCEPT-AD, a phase 1 trial in early Alzheimer's disease.","authors":"Erika N Cline, Daniel Antwi-Berko, Karen Sundell, Elizabeth Johnson, Maddelyn Hyland, Hao Zhang, Hugo Vanderstichele, June Kaplow, Robert A Dean, Erik Stoops, Eugeen Vanmechelen, Marleen J A Koel-Simmelink, Charlotte E Teunissen, Gopalan Sethuraman, Todd Feaster, Eric Siemers, Jasna Jerecic","doi":"10.1016/j.tjpad.2025.100082","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100082","url":null,"abstract":"<p><strong>Objective: </strong>Sabirnetug (ACU193) is a humanized monoclonal antibody selective for soluble amyloid beta oligomers (AβOs), synaptotoxins that are early and persistent triggers of Alzheimer's disease (AD). Sabirnetug pharmacodynamics were examined in the INTERCEPT-AD phase 1 study in mild cognitive impairment and mild dementia due to AD (NCT04931459) using biofluid biomarkers associated with Aβ and tau pathology, synaptic dysfunction, neuroinflammation, and neurodegeneration.</p><p><strong>Methods: </strong>INTERCEPT-AD was a randomized, first-in-human study of sabirnetug versus placebo administered as a single (SAD; 2, 10, 25, 60 mg/kg) or multiple (MAD; three doses of 10 or 60 mg/kg every 4 weeks [Q4W] or 25 mg/kg Q2W) ascending doses. Biomarkers were measured pre-/post-dose in CSF and EDTA-plasma. Correlations of biomarker changes versus dose, exposure duration, and target engagement were determined.</p><p><strong>Results: </strong>In MAD cohorts, CSF pTau181 decreased significantly (60 mg/kg Q4W, p = 0.049). VAMP2 decreased significantly at all doses (p ≤ 0.041); neurogranin decreased significantly at 60 mg/kg Q4W (p = 0.037). Aβ_1-42/Aβ_1-40 trended upward with sabirnetug dose. Aβ_1-42/Aβ_1-40 and neurogranin changes correlated with sabirnetug-AβO target engagement (p ≤ 0.01). Decreases in tTau, VAMP2, and neurogranin correlated with exposure duration (p ≤ 0.007). Plasma pTau181, pTau217, GFAP, and NfL trended lower.</p><p><strong>Discussion: </strong>Following three sabirnetug doses, changes in CSF and plasma biomarkers were observed. The CSF biomarker response increased with increasing dose and exposure duration, consistent with previous reports that sabirnetug reaches the central compartment and engages its AβO target. The ongoing phase 2 ALTITUDE-AD study (NCT06335173) will test whether sabirnetug's pharmacodynamic effects can be substantiated with a larger sample size and longer treatment duration.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100082"},"PeriodicalIF":4.3,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association of dietary diversity, genetic susceptibility, and the risk of incident dementia: A prospective cohort study.","authors":"Boyue Zhao, Bolun Cheng, Xinyang Li, Jinyu Xia, Yifan Gou, Meijuan Kang, Jingni Hui, Ye Liu, Ruixue Zhou, Chen Liu, Bingyi Wang, Panxing Shi, Feng Zhang","doi":"10.1016/j.tjpad.2025.100078","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100078","url":null,"abstract":"<p><strong>Background: </strong>Previous studies have revealed how single foods or nutrients affect dementia, but the evidence for a potential link between dietary diversity and dementia is inconsistent.</p><p><strong>Objectives: </strong>This study aimed to evaluate the association between dietary diversity and the risk of incident dementia.</p><p><strong>Design, setting and participants: </strong>This prospective study included 104,572 white participants without dementia at baseline recruited between 2006 and 2010 from the UK Biobank.</p><p><strong>Measurements: </strong>Dietary Diversity Score (DDS) was acquired through the Oxford WebQ's 24-hour dietary recall survey spanning from 2009 to 2012. Cox proportional hazards models were used to estimate the associations between DDS, diversity scores of food groups and the risk of incident dementia. Stratified analyses were subsequently conducted to assess the potential variations across different demographic, socioeconomic, and genetic risk groups.</p><p><strong>Results: </strong>Over a median follow-up period of 10.44 years, 725 participants developed incident dementia. A higher DDS was associated with a lower risk of incident dementia (HR: 0.95; 95 % CI: 0.93-0.97). Stratified analyses revealed statistical significance in this association for individuals under 65 years old (HR: 0.95; 95 % CI: 0.92-0.98), and those with higher polygenic risk scores (PRS; HR: 0.92; 95 % CI: 0.89-0.95). Among five food groups, a higher diversity score for meat and protein alternatives was associated with a lower risk of dementia (HR: 0.92; 95 % CI: 0.86-0.99).</p><p><strong>Conclusion: </strong>Enhancing dietary diversity reduces dementia risk, and is potentially influenced by genetic predisposition. Consuming a diverse range of foods may be an effective strategy against dementia.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100078"},"PeriodicalIF":4.3,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of pre-analytical factors on plasma biomarkers for Alzheimer's disease: The ASPREE Healthy Ageing Biobank.","authors":"Zimu Wu, Michelle M Mielke, Anne M Murray, James Phung, Alice Owen, Robyn L Woods, Danni Li, Jo Wrigglesworth, Joanne Ryan","doi":"10.1016/j.tjpad.2025.100058","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100058","url":null,"abstract":"<p><strong>Background: </strong>The conditions under which samples were collected, processed, and stored in biobanks may influence Alzheimer's disease (AD) biomarker levels.</p><p><strong>Objectives: </strong>This study aims to investigate whether a range of pre-analytical factors influence plasma levels of AD biomarkers.</p><p><strong>Methods: </strong>Data were obtained from the ASPREE Healthy Ageing Biobank, a cohort of healthy community-dwelling older individuals aged 70+ years in Australia. Five biomarkers were measured using plasma from 11,868 individuals: phosphorylated-tau181 (p-tau181), neurofilament light chain (NfL), glial fibrillary acidic protein (GFAP), and amyloid-beta 42 and 40 (Aβ42/Aβ40). Linear regression examined the association between pre-analytical factors and biomarker levels.</p><p><strong>Results: </strong>Participants were aged 70-96 years, and 54 % were female. The mean storage time for samples was 10.6 years (range: 7.7-13.5). Some significant associations were identified between pre-analytical factors and biomarkers, in particular for p-tau181, but the effect sizes were small. Weak negative associations were found between p-tau181 and the time from venepuncture to laboratory (transport) (β: -0.82, p = 0.03), laboratory processing to frozen storage (β:-1.56, p < 0.001), and total years of storage (β: -0.45, p = 0.007), while a positive association was found with intermediate storage at -20 °C/-30 °C compared to -80 °C (β: 2.24, p = 0.004). Longer fasting time was associated with higher levels of both NfL (β: 0.15, p < 0.001) and GFAP (β: 1.75, p < 0.001).</p><p><strong>Conclusion: </strong>Following standard operating procedures, AD biomarkers can be measured in plasma from biobanks stored for up to 13 years, with minimal impact from long-term storage or other pre-analytical factors.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100058"},"PeriodicalIF":4.3,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143414841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic and discriminative accuracy of plasma phosphorylated tau 217 for symptomatic Alzheimer's disease in a Chinese cohort.","authors":"Li-Min Li, Ping Che, Dequan Liu, Yu Wang, Jia Li, Dian He, Tao Liu, Nan Zhang","doi":"10.1016/j.tjpad.2025.100092","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100092","url":null,"abstract":"<p><strong>Background: </strong>Plasma phosphorylated tau at threonine 217 (p-tau217) measured with an ultrasensitive immunoassay method has been demonstrated to be an optimal biomarker for Alzheimer's disease (AD).</p><p><strong>Objectives: </strong>The aim of this study was to establish the reference interval for plasma p-tau217 in Chinese individuals and evaluate its diagnostic value in symptomatic AD.</p><p><strong>Design, setting, participants: </strong>We recruited 150 cognitively unimpaired (CU) individuals, 60 patients with AD dementia, 30 patients with mild cognitive impairment (MCI) due to AD, 40 patients with frontotemporal lobar degeneration (FTLD), and 70 patients with subcortical ischaemic vascular dementia (SIVD).</p><p><strong>Measurements: </strong>The concentrations of plasma p-tau217, total tau, amyloid-beta (Aβ)42 and Aβ40 were measured with a single-molecule array.</p><p><strong>Results: </strong>Plasma p-tau217 outperformed other biomarkers in discriminating AD patients from CU controls, FTLD patients, and SIVD patients (AUC = 0.983, 0.936, 0.892) and discriminating MCI patients from CU controls (AUC = 0.943). The plasma p-tau217 level was negatively correlated with memory in patients with symptomatic AD.</p><p><strong>Conclusion: </strong>The diagnostic accuracy of plasma p-tau217 was exceptional for AD, even at early stages, in the Chinese population.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100092"},"PeriodicalIF":4.3,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143414835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"White matter hyperintensity severity modifies gut metabolite association with cognitive outcomes.","authors":"Naruchorn Kijpaisalratana, Chia-Ling Phuah, Zsuzsanna Ament, Varun M Bhave, Ana-Lucia Garcia-Guarniz, Jonathan Duskin, Catharine A Couch, M Ryan Irvin, W Taylor Kimberly","doi":"10.1016/j.tjpad.2025.100086","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100086","url":null,"abstract":"<p><strong>Background: </strong>Gut microbiome-associated metabolites and white matter hyperintensities (WMH) are independently associated with cognitive impairment. However, it is unclear if gut metabolites and WMH interact to influence dementia.</p><p><strong>Objectives: </strong>To examine the association between gut microbial metabolites and cognitive outcomes and assess whether the severity of baseline WMH would impact associations between gut microbial metabolites and cognitive outcomes.</p><p><strong>Design: </strong>Cross-sectional design.</p><p><strong>Setting: </strong>Cohort of individuals who are clinically normal, mild cognitive impairment, or Alzheimer's Disease in the Alzheimer's Disease Neuroimaging Initiative (ADNI).</p><p><strong>Participants: </strong>A total of 578 participants with available baseline 3.0T 2D-Fluid Attenuation Inversion Recovery (FLAIR) Magnetic Resonance Imaging (MRI) scans and baseline gut microbial metabolite measurement were included in the analysis.</p><p><strong>Measurements: </strong>Gut metabolite measurements and automated WMH volume estimations were obtained from FLAIR MRI and were used to assess the association and interaction with cognitive impairment.</p><p><strong>Results: </strong>Of 104 metabolites studied, glycodeoxycholic acid (GDCA) surpassed the false discovery rate and was associated the Alzheimer's Disease Assessment Scale-Cognitive Subscale version 13 (ADAS-Cog13) score (β = 0.12, 95 % CI = 0.05-0.20, p = 0.001) and cognitive impairment determined by mini-mental status exam (MMSE) (OR = 2.11, 95 % CI = 1.41-3.15, p < 0.001). GDCA was associated with higher ADAS-Cog13 in participants with low WMH burden (β = 0.21, 95% CI = 0.10-0.32, p < 0.001) but not in participants with high WMH burden (β = 0.04, 95 % CI = -0.07 to 0.14, p = 0.48; interaction p = 0.02).</p><p><strong>Conclusion: </strong>An elevated level of GDCA was associated with worse cognition. WMH severity modified the association between GDCA and cognitive outcomes.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100086"},"PeriodicalIF":4.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143410750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reevaluating the sleep-dementia link: Methodological gaps and future directions.","authors":"Julián Benito-León, Carla María Benito-Rodríguez","doi":"10.1016/j.tjpad.2025.100085","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100085","url":null,"abstract":"","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100085"},"PeriodicalIF":4.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143410673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The interaction between circadian syndrome and genetic susceptibility in the risk of incident dementia: A longitudinal cohort study.","authors":"Linling Yu, Wei Liu, Chenqi Liao, Na Shen, Anding Liu, Liming Cheng, Xiong Wang","doi":"10.1016/j.tjpad.2025.100089","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100089","url":null,"abstract":"<p><strong>Background: </strong>Despite growing interest in circadian disturbances as potential triggers for dementia, the specific impact of circadian syndrome (CircS) on dementia incidence remains poorly understood. Moreover, the role of genetic susceptibility modulating these effects remains to be explored.</p><p><strong>Methods: </strong>Dementia-free participants from the UK Biobank cohort were included in the analysis. To evaluate the association between CircS and the incidence of dementia, as well as the modifying influence of genetic susceptibility on this relationship, Cox proportional hazards models were utilized.</p><p><strong>Results: </strong>During a median follow-up period of 14.55 years, 3,965 incident dementia cases were documented. CircS was found to significantly increased the risk of incident dementia, with a hazard ratio (HR) of 1.401 (95 % confidence interval [CI]: 1.296, 1.516). Compared to a CircS score of ≤3, mild CircS (HR: 1.259, 95 % CI: 1.146-1.383), moderate CircS (HR: 1.667, 95 % CI: 1.461-1.903), and severe CircS (HR: 2.028, 95 % CI: 1.397-2.944) were all significantly associated with an elevated risk of dementia. There were significant multiplicative interactions between CircS and genetic susceptibility (P_interaction<0.001). Participants with both a high polygenic risk score (PRS) and CircS had the highest risk of incident dementia (HR: 2.551, 95 % CI: 2.169, 3.001), compared to those with a low PRS and no CircS.</p><p><strong>Conclusions: </strong>CircS was associated with an increased risk of dementia, which might be aggravated by genetic susceptibility.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100089"},"PeriodicalIF":4.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143374193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness of digital screening tools in detecting cognitive impairment among community-dwelling elderly in Northern China: A large cohort study.","authors":"Xiaonan Zhang, Feifei Zhang, Sijia Hou, Chenxi Hao, Xiangmin Fan, Yarong Zhao, Wenjing Bao, Junpin An, Shuning Du, Guowen Min, Qiuyan Wang, Wencheng Zhu, Yang Li, Hui Zhang","doi":"10.1016/j.tjpad.2025.100080","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100080","url":null,"abstract":"<p><strong>Introduction: </strong>This study assessed the effectiveness of three digital screening tools in detecting cognitive impairment (CI) in a large cohort of community-dwelling elderly individuals and investigated the relationship between key digital features and plasma p-tau217 levels.</p><p><strong>Methods: </strong>This community-based cohort study included 1,083 participants aged 65 years or older, with 337 diagnosed with CI and 746 classified as normal controls (NC). We utilized two screening approaches: traditional methods (AD8, MMSE scale, and APOE genotyping) and digital tools (drawing, gait, and eye tracking). LightGBM-based machine learning models were developed for each digital screening tool and their combination, and their performance was evaluated. The correlation between key digital features and plasma p-tau217 levels was analyzed as well.</p><p><strong>Results: </strong>A total of 21 drawing, 71 gait, and 35 eye-tracking parameters showed significant differences between the two groups (all p < 0.05). The area under the curve (AUC) values for the drawing, gait, and eye-tracking models in distinguishing CI from NC were 0.860, 0.848, and 0.895, respectively. The combination of eye-tracking and drawing achieved the highest classification effectiveness, with an AUC of 0.958, and accuracy, sensitivity, and specificity all exceeded 85%. The fusion model achieved an AUC of 0.928 in distinguishing mild cognitive impairment (MCI) from NC. Additionally, several digital features (including two drawing, ten gait, and one eye-tracking parameters) were significantly correlated with plasma p-tau217 levels (all |r| > 0.3, p < 0.001).</p><p><strong>Discussion: </strong>Digital screening tools offer objective, accurate, and efficient alternatives for detecting CI in community settings, with the fusion of drawing and eye-tracking providing the best performance (AUC = 0.958).</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100080"},"PeriodicalIF":4.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143374941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LMTK2 and CRB1 are two novel risk genes for Alzheimer's disease in Han Chinese.","authors":"Xuewen Xiao, Hui Liu, Rui Yao, Yunni Li, Xinxin Liao, Yingzi Liu, Yafang Zhou, Junling Wang, Beisha Tang, Bin Jiao, Jinchen Li, Lu Shen, Shilin Luo","doi":"10.1016/j.tjpad.2025.100087","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100087","url":null,"abstract":"<p><strong>Background: </strong>Alzheimer's disease (AD) is the most prevalent neurodegenerative disease with a substantial genetic background. However, its underlying genetic architecture remains to be elucidated.</p><p><strong>Methods: </strong>In this study, we performed whole-exome sequencing in 282 familial and/or early-onset AD patients and 1086 cognitively normal controls in the Han Chinse populations. According to minor allele frequency, variants were divided into common variants (MAF ≥ 0.01) and rare variants (MAF < 0.01). Common variant-based association analysis and gene-based association test aggregating rare variants were performed by PLINK 1.9 and Sequence Kernel Association Test-Optimal, respectively. We replicated the significant results by using the same AD samples and controls from whole genome sequencing (n = 1879). Furthermore, we determined the functions of the novel AD risk genes in vitro.</p><p><strong>Results: </strong>Common variants association analysis revealed that APOE rs429358 reached statistical whole-exome significance. Gene-level aggregation testing identified that rare damaging variants in LMTK2 and CRB1 conferred risk to AD. All variants are located in highly conserved amino acid regions and are predicted to be damaging. Furthermore, functional studies showed that LMTK2 rare damaging variants (R234P and S974G) enhanced tau phosphorylation levels, tau aggregates formation, and Aβ generation. Meanwhile, the CRB1 Y556X variant caused incomplete translation of CRB1 protein and increased the Aβ42 level and Aβ42/Aβ40 ratio.</p><p><strong>Conclusion: </strong>Our findings indicated that LMTK2 and CRB1 are two novel AD risk genes in Han Chinese, which may provide promising targets for diagnosis and intervention.</p>","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100087"},"PeriodicalIF":4.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143373992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting cognitive decline: Deep-learning reveals subtle brain changes in pre-MCI stage.","authors":"Ling Yue, Yongsheng Pan, Wei Li, Junyan Mao, Bo Hong, Zhen Gu, Mingxia Liu, Dinggang Shen, Shifu Xiao","doi":"10.1016/j.tjpad.2025.100079","DOIUrl":"https://doi.org/10.1016/j.tjpad.2025.100079","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Mild cognitive impairment (MCI) and preclinical MCI (e.g., subjective cognitive decline, SCD) are considered risk states of dementia, such as Alzheimer's Disease (AD). However, it is challenging to accurately predict conversion from normal cognition (NC) to MCI, which is important for early detection and intervention. Since neuropathological changes may have occurred in the brain many years before clinical AD, we sought to detect the subtle brain changes in the pre-MCI stage using a deep-learning method based on structural Magnetic Resonance Imaging (MRI).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objectives: &lt;/strong&gt;To discover early structural neuroimaging changes that differentiate between stable and progressive cognitive status, and to establish a predictive model for MCI conversion.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Design, setting and participants: &lt;/strong&gt;We first created a unique deep-learning framework for pre-AD conversion prediction through the Alzheimer's Disease Neuroimaging Initiative-1 (ADNI-1) database (n = 845). Then, we tested the model on ADNI-2 (n = 321, followed 3 years) and our private study (n = 109), the China Longitudinal Aging Study (CLAS), to validate the rationality for pre-MCI conversion prediction. The CLAS is a 7-year community-based cohort study in Shanghai. Our framework consisted of two steps: 1) a single-ROI-based network (SRNet) for identifying informative regions in the brain, and 2) a multi-ROI-based network (MRNet) for pre-AD conversion prediction. We then utilized these \"ROI-based deep learning\" neural networks to create a composite score using advanced algorithm-building. We coined this score as the Progressive Index (PI), which serves as a metric for assessing the propensity of AD conversion. Ultimately, we employed the PI to gauge its predictive capability for MCI conversion in both ADNI-2 and CLAS datasets.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Measurements: &lt;/strong&gt;We primarily utilized baseline T1-weighted MRI scans to identify the most discriminative brain regions and subsequently developed the PI in both training and validation datasets. We compared the PI across different cognitive groups and conducted logistic regression models along with their AUCs, adjusting for education level, gender, neuropsychological test scores, and the presence of comorbid conditions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We trained the SRNet and MRNet using 845 subjects from ADNI-1 with baseline MRI data, in which AD and progressive MCI (converting to AD within 3 years) patients were considered as positive samples, while NC and stable MCI (remaining stable for 3 years) subjects were considered as negative samples. The convolutional neural networks identified the top 10 regions of interest (ROIs) for distinguishing progressive from stable cases. These key brain regions included the hippocampus, amygdala, temporal lobe, insula, and anterior cerebellum. A total of 321 subjects from ADNI-2, including 209 NC (18 progressive NC (pNC), 113 stable NC (sNC), and 78 remain","PeriodicalId":22711,"journal":{"name":"The Journal of Prevention of Alzheimer's Disease","volume":" ","pages":"100079"},"PeriodicalIF":4.3,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143371171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}