RESUMO
Alzheimer's disease is a progressive neurodegenerative disorder, the early detection of which is crucial for timely intervention and enrollment in clinical trials. However, the preclinical diagnosis of Alzheimer's encounters difficulties with gold-standard methods. The current definitive diagnosis of Alzheimer's still relies on expensive instrumentation and post-mortem histological examinations. Here, we explore label-free Raman spectroscopy with machine learning as an alternative to preclinical Alzheimer's diagnosis. A special feature of this study is the inclusion of patient samples from different cohorts, sampled and measured in different years. To develop reliable classification models, partial least squares discriminant analysis in combination with variable selection methods identified discriminative molecules, including nucleic acids, amino acids, proteins, and carbohydrates such as taurine/hypotaurine and guanine, when applied to Raman spectra taken from dried samples of cerebrospinal fluid. The robustness of the model is remarkable, as the discriminative molecules could be identified in different cohorts and years. A unified model notably classifies preclinical Alzheimer's, which is particularly surprising because of Raman spectroscopy's high sensitivity regarding different measurement conditions. The presented results demonstrate the capability of Raman spectroscopy to detect preclinical Alzheimer's disease for the first time and offer invaluable opportunities for future clinical applications and diagnostic methods.
Assuntos
Doença de Alzheimer , Análise Espectral Raman , Análise Espectral Raman/métodos , Doença de Alzheimer/diagnóstico , Doença de Alzheimer/líquido cefalorraquidiano , Humanos , Aprendizado de Máquina , Masculino , Feminino , Biomarcadores/líquido cefalorraquidiano , Idoso , Diagnóstico PrecoceRESUMO
BACKGROUND: GOIZ ZAINDU ("caring early" in Basque) is a pilot study to adapt the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) methodology to the Basque population and evaluate the feasibility and adherence to a FINGER-like multidomain intervention program. Additional aims included the assessment of efficacy on cognition and data collection to design a large efficacy trial. METHOD: GOIZ ZAINDU is a 1-year, randomized, controlled trial of a multidomain intervention in persons aged 60+ years, with Cardiovascular Risk Factors, Aging and Dementia (CAIDE) risk score ≥ 6, no diagnosis of dementia, and below-than-expected performance in at least one of three cognitive screening tests. Randomization to a multidomain intervention (MD-Int) or regular health advice (RHA) was stratified by sex, age (>/≤ 75), and cognitive status (mild cognitive impairment (MCI)/normal cognition). MD-Int included cardiovascular risk factor control, nutritional counseling, physical activity, and cognitive training. The primary outcomes were retention rate and adherence to the intervention program. Exploratory cognitive outcomes included changes in the Neuropsychological Test Battery z-scores. Analyses were performed according to the intention to treat. RESULTS: One hundred twenty-five participants were recruited (mean age: 75.64 (± 6.46); 58% women). The MD-Int (n = 61) and RHA (n = 64) groups were balanced in terms of their demographics and cognition. Fifty-two (85%) participants from the RHA group and 56 (88%) from the MD-Int group completed the study. More than 70% of the participants had high overall adherence to the intervention activities. The risk of cognitive decline was higher in the RHA group than in the MD-Int group in terms of executive function (p =.019) and processing speed scores (p =.026). CONCLUSIONS: The GOIZ-ZAINDU study proved that the FINGER methodology is adaptable and feasible in a different socio-cultural environment. The exploratory efficacy results showed a lower risk of decline in executive function and processing speed in the intervention group. These results support the design of a large-scale efficacy trial. TRIAL REGISTRATION: GOIZ ZAINDU feasibility trial was approved and registered by the Euskadi Drug Research Ethics Committee (ID: PI2017134) on 23 January 2018. Retrospectively registered in ClinicalTrials.gov (NCT06163716) on 8 December 2023.