New Computer-Aided Diagnosis of Dementia Using PET
Author Information
Author(s): Kakimoto Akihiro, Kamekawa Yuichi, Ito Shigeru, Yoshikawa Etsuji, Okada Hiroyuki, Nishizawa Sadahiko, Minoshima Satoshi, Ouchi Yasuomi
Primary Institution: Hamamatsu Photonics K.K.
Hypothesis
Can a new computer-aided diagnosis method accurately differentiate Alzheimer's disease and mild cognitive impairment from normal adults?
Conclusion
The automated computer-aided evaluation method provided good accuracy for differential diagnosis of Alzheimer's disease and mild cognitive impairment.
Supporting Evidence
- The sensitivity and specificity for differentiating normal adults from Alzheimer's patients were both 100% in the training group.
- In the test group, sensitivity was 100% and specificity was 95%.
- The method achieved 88% accuracy in differentiating AD-converters from non-converters in the MCI group.
Takeaway
Researchers created a computer program to help doctors tell if someone has Alzheimer's disease or mild cognitive impairment by looking at brain scans.
Methodology
The study involved 101 adults who underwent PET scans, with a new method developed to analyze brain regions for diagnosing dementia.
Potential Biases
Potential for misdiagnosis due to reliance on automated imaging analyses.
Limitations
The method's accuracy may be affected by variations in computer-generated sensitivity and requires clinical assessment to minimize misdiagnosis.
Participant Demographics
40 normal adults, 37 Alzheimer's patients, and 24 mild cognitive impairment patients, with a mix of males and females.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website