One of the most prevalent neurodegenerative disease, Alzheimer's disease (AD) affects about 6.5 million Americans 65 and older, and its prevalence is expected to more than quadruple by 2060. Clinical signs of AD are usually preceded by pathologic alterations in the brain. It is anticipated that people with AD-specific pathologic alterations may develop dementia at different rates in the absence of disease-modifying treatments.
Slow amyloid-β (Aβ) protein aggregation, hyperphosphorylated tau (p-tau) buildup, and concurrent functional and structural neuronal degeneration are hallmark degenerative brain alterations in AD. Imaging and biofluid biomarkers offer in vivo estimates of brain disease with differing degrees of accuracy, but postmortem pathology is still the gold standard for measuring AD pathology.
The application of blood-based biomarkers (BBMs) of neurodegeneration (e.g., neurofilament light chain, NfL) and core pathological biomarkers (e.g., Aβ and phosphorylated tau, p-tau) has a high potential, according to results from many studies. Therefore, by evaluating BBM, CSF, and MRI measures separately, adding BBMs to CSF measures, and adding BBMs to the combination of CSF and MRI, this study examined the ability of various biomarker combinations (i.e., CSF, MRI, and BBMs) and the impact of each distinct measure to the models to predict MCI-conversion.
The data from the Alzheimer's Disease Neuroimaging Initiative was utilized. Data from participants who were diagnosed with dementia at the 2-year follow-up visit and who remained cognitively stable (CN-s) were used to train machine learning models. The models were used to forecast when people with MCI will develop dementia. This evaluated the performance of models containing plasma biomarkers both alone and in conjunction with CSF and MRI measurements.
The models using plasma biomarkers distinguished CN-s persons from AD with an AUC of 0.75 ± 0.03 and could identify conversion to dementia in MCI patients with an AUC of 0.64 ± 0.03. Combining plasma biomarker models with CSF and MRI measurements improved their performance.
Overall, this study demonstrated that machine learning models using a variety of feature sets may be used to predict the course of the illness in patients with MCI and to distinguish AD patients from cognitively normal ones. All things considered, predictive tools have the potential to be extremely effective instruments that influence clinical research and "real-world" clinical decision-making with more development and validation.
Reference:
Nallapu, B. T., Petersen, K. K., Lipton, R. B., Davatzikos, C., & Ezzati, A. (2024). Plasma Biomarkers as Predictors of Progression to Dementia in Individuals with Mild Cognitive Impairment. In Journal of Alzheimer’s Disease (Vol. 98, Issue 1, pp. 231–246). SAGE Publications. https://doi.org/10.3233/jad-230620
Disclaimer: This website is primarily for healthcare professionals. The content here does not replace medical advice and should not be used as medical, diagnostic, endorsement, treatment, or prescription advice. Medical science evolves rapidly, and we strive to keep our information current. If you find any discrepancies, please contact us at corrections@medicaldialogues.in. Read our Correction Policy here. Nothing here should be used as a substitute for medical advice, diagnosis, or treatment. We do not endorse any healthcare advice that contradicts a physician's guidance. Use of this site is subject to our Terms of Use, Privacy Policy, and Advertisement Policy. For more details, read our Full Disclaimer here.
NOTE: Join us in combating medical misinformation. If you encounter a questionable health, medical, or medical education claim, email us at factcheck@medicaldialogues.in for evaluation.