A data-driven framework for biomarker discovery applied to optimizing modern clinical and preclinical trials on Alzheimer’s disease
2024

New Framework for Discovering Alzheimer’s Disease Biomarkers

Sample size: 240 publication 10 minutes Evidence: high

Author Information

Author(s): Llorente-Saguer Isaac, Oxtoby Neil P

Primary Institution: University College London

Hypothesis

Can a data-driven framework improve the discovery of biomarkers for Alzheimer’s disease?

Conclusion

The BioDisCVR framework discovered superior tau PET biomarkers that significantly reduce sample size estimates for clinical trials.

Supporting Evidence

  • The BioDisCVR framework reduced sample size estimates by approximately 80%.
  • Results showed improved biomarker performance compared to existing methods.
  • Longitudinal precision of the new biomarkers was significantly higher.

Takeaway

Researchers created a new tool to find better ways to measure Alzheimer’s disease, which could help make drug trials faster and safer.

Methodology

The study used a machine learning framework called BioDisCVR to analyze tau PET data and discover new biomarkers.

Potential Biases

Potential biases may arise from the selection of reference regions in the biomarker analysis.

Limitations

The study's findings may not generalize to all populations due to the predominance of white participants.

Participant Demographics

198 individuals from the ADNI database, with 48.7% females; 42 individuals from Mayo Clinic, with 33.3% females.

Statistical Information

P-Value

p<0.001

Confidence Interval

(195, 321)

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1093/braincomms/fcae438

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication