NOVEL PLASMA PROTEIN BIOMARKERS: A TIME-DEPENDENT PREDICTIVE MODEL FOR ALZHEIMER’S DISEASE
2024

Predicting Alzheimer's Disease with Plasma Protein Biomarkers

Sample size: 440 publication Evidence: moderate

Author Information

Author(s): Zhuang Tianchi, Xu Ting, Qiu Xichenhui, Yang Yingqi, Qi Xiang, Xu Qin, Ji Minghui

Primary Institution: Nanjing Medical University

Hypothesis

Can novel plasma protein biomarkers be used to predict the onset of Alzheimer's disease?

Conclusion

The study found that specific plasma protein signatures can effectively predict the risk of Alzheimer's disease onset.

Supporting Evidence

  • Seven protein signatures were identified as predictive of Alzheimer's disease risk.
  • The Cox model showed robust predictive performance with AUC values of 0.77 at 4, 6, and 8 years.
  • Low-risk individuals had significantly delayed Alzheimer's onset compared to high-risk individuals.

Takeaway

Scientists found that certain proteins in the blood can help tell if someone might get Alzheimer's disease in the future.

Methodology

The study used Cox regression, LASSO regression, and cross-validation to analyze data from participants.

Limitations

Weak correlations were observed between plasma and CSF protein levels.

Participant Demographics

Participants were aged 60 and above from the Alzheimer’s Disease Neuroimaging Initiative cohort.

Statistical Information

P-Value

p<0.001

Statistical Significance

p<0.001

Digital Object Identifier (DOI)

10.1093/geroni/igae098.3678

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication