The application value of Rs-fMRI-based machine learning models for differentiating mild cognitive impairment from Alzheimer's disease: a systematic review and meta-analysis
2024

Using Machine Learning with Rs-fMRI to Differentiate Mild Cognitive Impairment from Alzheimer's Disease

Sample size: 5554 publication 10 minutes Evidence: high

Author Information

Author(s): Wang Chentong, Zhou Li, Zhou Feng, Fu Tingting

Primary Institution: Ningbo Medical Center Lihuili Hospital, Ningbo, Zhejiang, China

Hypothesis

The study aims to explore the diagnostic accuracy of Rs-fMRI-based machine learning models in differentiating mild cognitive impairment from Alzheimer's disease.

Conclusion

The Rs-fMRI-based machine learning model shows high diagnostic accuracy for differentiating mild cognitive impairment from Alzheimer's disease.

Supporting Evidence

  • The study included 23 studies with a total of 5,554 participants.
  • The diagnostic accuracy for Alzheimer's disease in binary classification tasks was found to be 0.99.
  • The sensitivity and specificity of the machine learning model were 0.94 and 0.98, respectively.
  • Multi-class classification tasks showed high accuracy for differentiating between normal controls, early mild cognitive impairment, late mild cognitive impairment, and Alzheimer's disease.

Takeaway

Researchers used brain scans to teach computers how to tell the difference between people with mild memory problems and those with Alzheimer's disease, and they found it works really well.

Methodology

A systematic review and meta-analysis were conducted using data from various databases, focusing on the diagnostic accuracy of Rs-fMRI-based machine learning models.

Potential Biases

There is a risk of publication bias as studies with positive findings may be more likely to be published.

Limitations

The study is limited by potential sample bias due to reliance on the ADNI database and the inclusion of only case-control studies.

Participant Demographics

Participants included individuals diagnosed with mild cognitive impairment and Alzheimer's disease from diverse backgrounds across multiple countries.

Statistical Information

P-Value

p<0.05

Confidence Interval

95%CI: 0.34 ~ 1.00

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1007/s10072-024-07731-1

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication