Alzheimer's disease (AD) is a complex brain disorder that causes progressive cognitive decline, and neuropsychiatric complications, ranking among the top 10 causes of death. Clinically, there are three stages of cognitive decline: dementia, mild cognitive impairment (MCI), and subjective cognitive decline (self-reported cognitive issues). Both MCI and subjective cognitive decline are recognized as risk factors for dementia, but most countries do not recommend specific treatments outside of clinical trials. Identifying preventive indicators of AD is critical for developing effective disease control strategies. The diagnosis of MCI or dementia is typically made by a clinician through detailed neuropsychological and neurological assessments, basic lab tests, and structural brain imaging (MRI or CT scans). Additional diagnostic methods may include biomarkers from PET brain scans or cerebrospinal fluid (CSF). Since CSF collection requires lumbar punctures, finding less invasive blood-based biomarkers is crucial. A key goal of precision medicine, though highly challenging, is to improve the classification of pathological conditions based on molecular markers rather than relying solely on clinical symptoms. From this perspective, providing a clear and objective identification of conditions that could progress into more severe symptoms while distinguishing them from other types of impairments is crucial for improving early detection of AD. A clustering-based molecular stratification of MCI patients by analyzing transcriptomic data from blood samples provided by the ADNI (Alzheimer’s Disease Neuroimaging Initiative) resource is realized with this aim. A specific AI-based pipeline is built to perform the transcriptomic analysis, integrating unsupervised and supervised learning approaches. Starting with feature selection techniques, the pipeline uses deep learning-based autoencoders to embed gene expression data from 381 patients into a lower-dimensional latent space. This latent representation is then fed into a clustering algorithm to determine the final result. The identified MCI patient clusters show significant molecular, clinical, and pathophysiological differences. Differences are also evident between some MCI patient clusters compared to patients with AD diagnosis, as well as with control samples. To our knowledge, this is the first study to demonstrate a molecular-based stratification of MCI patients using blood transcriptomic data. These findings can lead to an early and precise diagnosis of dementia and related conditions, offering a more objective alternative to standard cognitive-based definitions often influenced by subjective interpretation.
Clustering-based stratification of mild cognitive impairment: Insights from blood transcriptomic data
Laura Antonelli
;Claudia Di Napoli;Lucia Maddalena;Giovanni Paragliola;Patrizia Ribino;Luca Serino;Ilaria Granata
2024
Abstract
Alzheimer's disease (AD) is a complex brain disorder that causes progressive cognitive decline, and neuropsychiatric complications, ranking among the top 10 causes of death. Clinically, there are three stages of cognitive decline: dementia, mild cognitive impairment (MCI), and subjective cognitive decline (self-reported cognitive issues). Both MCI and subjective cognitive decline are recognized as risk factors for dementia, but most countries do not recommend specific treatments outside of clinical trials. Identifying preventive indicators of AD is critical for developing effective disease control strategies. The diagnosis of MCI or dementia is typically made by a clinician through detailed neuropsychological and neurological assessments, basic lab tests, and structural brain imaging (MRI or CT scans). Additional diagnostic methods may include biomarkers from PET brain scans or cerebrospinal fluid (CSF). Since CSF collection requires lumbar punctures, finding less invasive blood-based biomarkers is crucial. A key goal of precision medicine, though highly challenging, is to improve the classification of pathological conditions based on molecular markers rather than relying solely on clinical symptoms. From this perspective, providing a clear and objective identification of conditions that could progress into more severe symptoms while distinguishing them from other types of impairments is crucial for improving early detection of AD. A clustering-based molecular stratification of MCI patients by analyzing transcriptomic data from blood samples provided by the ADNI (Alzheimer’s Disease Neuroimaging Initiative) resource is realized with this aim. A specific AI-based pipeline is built to perform the transcriptomic analysis, integrating unsupervised and supervised learning approaches. Starting with feature selection techniques, the pipeline uses deep learning-based autoencoders to embed gene expression data from 381 patients into a lower-dimensional latent space. This latent representation is then fed into a clustering algorithm to determine the final result. The identified MCI patient clusters show significant molecular, clinical, and pathophysiological differences. Differences are also evident between some MCI patient clusters compared to patients with AD diagnosis, as well as with control samples. To our knowledge, this is the first study to demonstrate a molecular-based stratification of MCI patients using blood transcriptomic data. These findings can lead to an early and precise diagnosis of dementia and related conditions, offering a more objective alternative to standard cognitive-based definitions often influenced by subjective interpretation.File | Dimensione | Formato | |
---|---|---|---|
Clustering-based stratification of mild cognitive impairment. Insights from blood transcriptomic data.pdf
accesso aperto
Licenza:
Creative commons
Dimensione
1.79 MB
Formato
Adobe PDF
|
1.79 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.