The Combination of Neuropsychiatric Symptoms and Blood-Based Biomarkers Enhances Early Detection of Mild Cognitive Impairment
Bibliographic record
Abstract
Abstract Background Combing behavioral assessments with blood-based biomarkers (BBM) may improve detection of Mild Cognitive Impairment (MCI) linked to early-stage neurodegenerative disease. Neuropsychiatric symptoms (NPS) often precede or accompany cognitive decline and provide observable behavioral signals, while BBM reflect underlying neuropathological changes. We investigated if integrating biological (plasma biomarkers) and behavioral (NPS) measures improves differentiation of MCI from cognitively normal (CN) individuals in a multi-ethnic Southeast Asian cohort— an underrepresented population in dementia research. Methods This cross-sectional analysis included 678 community-dwelling adults (mean age 59.2±11.0, 60.5% female) from the Biomarkers and Cognition Study, Singapore (BIOCIS), comprising participants recruited from the community, at Dementia Research Centre (Singapore) from February 2022 to March 2024. Participants underwent behavioral assessments using the Mild Behavioral Impairment Checklist (MBI-C) and the Depression, Anxiety, and Stress Scales (DASS). Plasma biomarkers measured were amyloid-beta (Aβ40, Aβ42), phosphorylated tau (p-tau181), neurofilament light (NfL), and glial fibrillary acidic protein (GFAP). Logistic regression and receiver operating characteristic (ROC) analyses evaluated the discriminative power of NPS, BBM, and their combination for identifying MCI risk. Results MBI-C total scores and subdomains (Mood, Interest, Control) and plasma biomarkers (Aβ40, NfL, GFAP) were significantly elevated in MCI compared to CN participants. Multivariate analysis showed elevated plasma GFAP (OR=3.64, 95% CI:1.96–6.75, p<0.001) and higher MBI-C Mood scores (OR=2.61, 95% CI:1.54–4.44, p<0.001) as the variables most associated with MCI. The combined model integrating NPS and BBM achieved a higher discriminative ability (AUC = 0.786) for MCI than models using NPS (AUC = 0.593) or BBM (AUC = 0.697) alone. The integrated model yielded 64.7% sensitivity and 84.9% specificity for distinguishing MCI from CN, outperforming single-domain approaches. Conclusions Integrating biological and behavioral markers improves identification of individuals with early cognitive impairment. Notably, GFAP-driven neuroinflammation and mood disturbances emerged as key features of prodromal dementia, highlighting astrocytic activation and affective changes as promising biomarkers and early intervention targets. This dual-domain, multimodal framework offers translational potential for earlier detection, risk stratification, and timely intervention for Alzheimer’s disease and other dementias.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".