Investigating the combined effects of smoking and amyloid on brain structure in cognitively unimpaired adults using a machine learning‐based MRI marker
Bibliographic record
Abstract
Abstract Background Smoking is a well‐established risk factor for cardiovascular disease, and its association with neurodegeneration and cognitive decline is an area of ongoing research. Critically, the interplay between smoking, Alzheimer's disease (AD) pathology, and cognitive impairment remains incompletely understood. This study investigated the relationship between smoking, AD pathology as indexed by amyloid‐beta (Aβ) deposition, and cognitive performance using SPARE‐SM, a novel machine learning‐based marker that quantifies smoking‐related spatial patterns of abnormalities on individual structural magnetic resonance images (sMRI). Methods SPARE‐Smoking, derived from N = 37,098 cognitively unimpaired individuals from diverse cohorts, was evaluated in N = 222 individuals who had amyloid (Aβ) status available within +/‐ 1 year of the MRI scan in a subset of the training cohort. Amyloid deposition was determined using study‐specific cut‐offs for CSF and PET SUVR measures, categorizing participants as Aβ‐/Aβ+. Multivariable regression models were used to assess interactions between Aβ status, smoking history, and age on SPARE‐SM scores. Multivariable linear regression models, adjusted for age, sex, and years of education, examined associations between SPARE‐SM and cognitive performance. Results While the proportion of smokers was similar between Aβ+ and Aβ‐ participants (Table 1), SPARE‐SM showed a nuanced relationship with both Aβ and smoking status (Figure 1A). Specifically, SPARE‐SM was higher than SM+Aβ‐ individuals in SM+ Aβ+ individuals ( p <0.05) but lower in SM‐ Aβ+ individuals ( p <0.05). Importantly, higher SPARE‐SM was associated with worse cognitive performance, whereas simply classifying individuals as smokers or non‐smokers showed no associations with cognitive outcomes (Figure 1B). Conclusion These findings suggest a complex relationship between smoking, amyloid pathology, and cognition. The observation that SPARE‐SM differed by Aβ in smoking individuals highlights their potential synergistic effects on neurodegeneration. SPARE‐SM demonstrated associations with cognitive decline, even when clinical smoking status did not, emphasizing its potential for early risk identification. Further research is needed to disentangle the mechanisms linking smoking, brain changes, amyloid, and dementia.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".