Early diagnosis and treatment of Alzheimer's disease

Machine learning for the life-time risk prediction of Alzheimer's disease: a systematic review

Alzheimer’s disease is a neurodegenerative disorder and the most common form of dementia. Early diagnosis may assist interventions to delay onset and reduce the progression rate of the disease. We systematically reviewed the use of machine learning algorithms for predicting Alzheimer’s disease using single nucleotide polymorphisms and instances where these were combined with other types of data. We evaluated the ability of machine learning models to distinguish between controls and cases, while also assessing their implementation and potential biases. Articles published between December 2009 and June 2020 were collected using Scopus, PubMed and Google Scholar. These were systematically screened for inclusion leading to a final set of 12 publications. Eighty-five per cent of the included studies used the Alzheimer's Disease Neuroimaging Initiative dataset. In studies which reported area under the curve, discrimination varied (0.49–0.97). However, more than half of the included manuscripts used other forms of measurement, such as accuracy, sensitivity and specificity. Model calibration statistics were also found to be reported inconsistently across all studies. The most frequent limitation in the assessed studies was sample size, with the total number of participants often numbering less than a thousand, whilst the number of predictors usually ran into the many thousands. In addition, key steps in model implementation and validation were often not performed or unreported, making it difficult to assess the capability of machine learning models.

Reduced Hippocampal Glutamate and Posterior Cingulate N-Acetyl Aspartate in Mild Cognitive Impairment and Alzheimer's Disease Is Associated with Episodic Memory Performance and White Matter Integrity in the Cingulum: A Pilot Study

Identification of biological changes underlying the early symptoms of Alzheimer's disease (AD) will help to identify and stage individuals prior to symptom onset. The limbic system, which supports episodic memory and is impaired early in AD, is a primary target. In this study, brain metabolism and microstructure evaluated by high field (7 Tesla) proton magnetic resonance spectroscopy (1H-MRS) and diffusion tensor imaging (DTI) were evaluated in the limbic system of eight individuals with mild cognitive impairment (MCI), nine with AD, and sixteen normal elderly controls (NEC). Left hippocampal glutamate and posterior cingulate N-acetyl aspartate concentrations were reduced in MCI and AD compared to NEC. Differences in DTI metrics indicated volume and white matter loss along the cingulum in AD compared to NEC. Metabolic and microstructural changes were associated with episodic memory performance assessed using Craft Story 21 Recall and Benson Complex Figure Copy. The current study suggests that metabolite concentrations measured using 1H-MRS may provide insight into the underlying metabolic and microstructural processes of episodic memory impairment.

Lacidipine Prevents Scopolamine-Induced Memory Impairment by Reducing Brain Oxido-nitrosative Stress in Mice

Cholinergic deficits and oxido-nitrosative stress are consistently associated with Alzheimer's disease (AD). Previous findings indicate that acetylcholine subdues Ca²⁺ current in the brain. Cholinergic antagonists (e.g., scopolamine) can instigate Ca²⁺-induced redox imbalance, inflammation, and cell-death pathways leading to AD-type memory impairment. Earlier, several Ca²⁺-channel blockers (CCB, e.g., dihydropyridine type) or cholinergic enhancers showed promising results in animal models of AD. In the present research, pretreatment effects of lacidipine (L-type CCB) on learning and memory functions were investigated using the scopolamine mouse model of AD. Swiss albino mice (20-25 g) were administered lacidipine (1 and 3 mg/kg) for 14 days. Scopolamine, an anti-muscarinic drug, was given (1 mg/kg) from days 8 to 14. The mice were subjected to elevated plus maze (EPM) and passive-avoidance (PA) paradigms. Bay-K8644 (a Ca²⁺-channel agonist) was administered before behavioral studies on days 13 and 14. Biochemical parameters of oxidative stress and acetylcholinesterase (AChE) activity were quantified using the whole brain. Behavioral studies showed an increase in transfer latency (TL) in the EPM test and a decrease in step-through latency (STL) in the PA test in scopolamine-administered mice. Scopolamine enhanced the AChE activity and oxidative stress in the brain of mice which resulted in memory impairment. Lacidipine prevented the amnesia against scopolamine and reduced the oxidative stress and AChE activity in the brain of mice. Bay-K8644 attenuated the lacidipine-induced improvement in memory and redox balance in scopolamine-administered mice. Lacidipine can prevent the oxidative stress and improve the cholinergic function in the brain. These properties of lacidipine can mitigate the pathogenesis of AD-type dementia.

Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid

Current Alzheimer's disease (AD) diagnostics is based on clinical assessments, imaging and neuropsychological tests that are efficient only at advanced stages of the disease. Early diagnosis of AD will provide decisive opportunities for preventive treatment and development of disease-modifying drugs. Cerebrospinal fluid (CSF) is in direct contact with the human brain, where the deadly pathological process of the disease occurs. As such, the CSF biochemical composition reflects specific changes associated with the disease and is therefore the most promising body fluid for AD diagnostic test development. Here, we describe a new method to diagnose AD based on CSF via near infrared (NIR) Raman spectroscopy in combination with machine learning analysis. Raman spectroscopy is capable of probing the entire biochemical composition of a biological fluid at once. It has great potential to detect small changes specific to AD, even at the earliest stages of pathogenesis. NIR Raman spectra were measured of CSF samples acquired from 21 patients diagnosed with AD and 16 healthy control (HC) subjects. Artificial neural networks (ANN) and support vector machine discriminant analysis (SVM-DA) statistical methods were used for differentiation purposes, with the most successful results allowing for the differentiation of AD and HC subjects with 84% sensitivity and specificity. Our classification models show high discriminative power, suggesting the method has a great potential for AD diagnostics. The reported Raman spectroscopic examination of CSF can complement current clinical tests, making early AD detection fast, accurate, and inexpensive. While this study shows promise using a small sample set, further method validation on a larger scale is required to indicate the true strength of the approach.

Multivariate Statistical Analysis of Surface Enhanced Raman Spectra of Human Serum for Alzheimer’s Disease Diagnosis

Alzheimer’s disease (AD) is the most common form of dementia worldwide and is characterized by progressive cognitive decline. Along with being incurable and lethal, AD is difficult to diagnose with high levels of accuracy. Blood serum from Alzheimer’s disease (AD) patients was analyzed by surface-enhanced Raman spectroscopy (SERS) coupled with multivariate statistical analysis. The obtained spectra were compared with spectra from healthy controls (HC) to develop a simple test for AD detection. Serum spectra from AD patients were further compared to spectra from patients with other neurodegenerative dementias (OD). Colloidal silver nanoparticles (AgNPs) were used as the SERS-active substrates. Classification experiments involving serum SERS spectra using artificial neural networks (ANNs) achieved a diagnostic sensitivity around 96% for differentiating AD samples from HC samples in a binary model and 98% for differentiating AD, HC, and OD samples in a tertiary model. The results from this proof-of-concept study demonstrate the great potential of SERS blood serum analysis to be developed further into a novel clinical assay for the effective and accurate diagnosis of AD.

Raman spectroscopy of blood serum for Alzheimer's disease diagnostics: specificity relative to other types of dementia

The key moment for efficiently and accurately diagnosing dementia occurs during the early stages. This is particularly true for Alzheimer's disease (AD). In this proof-of-concept study, we applied near infrared (NIR) Raman microspectroscopy of blood serum together with advanced multivariate statistics for the selective identification of AD. We analyzed data from 20 AD patients, 18 patients with other neurodegenerative dementias (OD) and 10 healthy control (HC) subjects. NIR Raman microspectroscopy differentiated patients with more than 95% sensitivity and specificity. We demonstrated the high discriminative power of artificial neural network (ANN) classification models, thus revealing the high potential of this developed methodology for the differential diagnosis of AD. Raman spectroscopic, blood-based tests may aid clinical assessments for the effective and accurate differential diagnosis of AD, decrease the labor, time and cost of diagnosis, and be useful for screening patient populations for AD development and progression. Multivariate data analysis of blood serum Raman spectra allows for the differentiation between patients with Alzheimer's disease, other types of dementia and healthy individuals.

Risk Factors for Progression of Alzheimer Disease in a Canadian Population: The Canadian Outcomes Study in Dementia (COSID)

OBJECTIVE

To determine risk factors for clinically significant progression during 12 months in patients with mild-to-moderate Alzheimer disease.

METHOD

Community-dwelling patients with mild-to-moderate Alzheimer disease were enrolled in a 3-year prospective study, the Canadian Outcomes Study in Dementia (commonly referred to as COSID), at 32 Canadian sites. Assessments included the Global Deterioration Scale (GDS) for disease severity, the Mini-Mental State Examination (MMSE) for cognition, the Functional Autonomy Measurement System (SMAF) for daily functioning, and the NeuroPsychiatric Inventory (NPI) for behaviour, measured at baseline and at 12 months. Logistic regression identified factors associated with GDS decline, and subsequent stepwise regression identified key independent predictors. Area under the curve (AUC) was then calculated for the model.

RESULTS

Among 488 patients (mean age 76.5 years [SD 6.4], MMSE 22.1 [SD4.6], 44.1% male), 225 (46%) showed GDS decline. After adjusting for age, baseline risk factors for deterioration included the following: poorer cognition (lower MMSE score, OR 0.55; 95% CI 0.4 to 0.72 per 5 points, P ≤ 0.001), greater dependence (lower SMAF, OR 0.72; 95% CI 0.63 to 0.83 per 5 points, P ≤ 0.001), and more neuropsychiatric symptoms (higher NPI, OR 1.11; 95% CI 1.02 to 1.2 per 5 points, P = 0.02), with a protective effect of male sex (OR 0.59; 95% CI 0.39 to 0.9, P = 0.02), and higher (worse) GDS score (very mild, compared with mild OR 0.25; 95% CI 0.09 to 0.70, P ≤ 0.01; compared with moderate, OR 0.08; 95% CI 0.03 to 0.23, P < 0.001; compared with moderately severe, OR 0.03; 95% CI 0.01 to 0.11, P < 0.001). The AUC was 73% (P < 0.001) (sensitivity 90% and specificity 33%).

CONCLUSION

The progression of Alzheimer disease in Canada can be predicted using readily available clinical information.

Long-term progression of Alzheimer's disease in patients under antidementia drugs

BACKGROUND

Patients with Alzheimer's disease (AD), even in the presence of symptomatic relief from medical intervention, face a persistent worsening of cognitive decline and performance in activities of daily living. Data regarding the long-term disease progression outside of therapeutic trials are lacking. We examined the effects of standard of care for AD patients on the prognosis of the disease in a real-life study over a 4-year period.

METHODS

A total of 686 patients with mild-moderate AD were enrolled in 16 memory clinics (REseau sur la maladie d' Alzheimer FRançais [REAL.FR] cohort) and followed up twice annually with tools used in therapeutic trials (Mini-Mental Status Examination, Alzheimer Disease Assessment Scale-cognitive subscale [ADAS-cog]: cognitive function, Clinical Dementia Rating: dementia severity, Activity of Daily Living [ADL]: incapacities, NeuroPsychiatric Inventory: neuropsychiatric symptom).

RESULTS

More than 90% of the patients used AD-specific medication over 4 years. Patients lost on average 2.4 points per year on the Mini-Mental Status Examination and gained 4.5 points on the ADAS-cog. ADL and NeuroPsychiatric Inventory scores became significantly worse over time. Incidence of incapacities for ADL and worsening of neuropsychiatric symptoms were 52.5 (95% confidence interval [CI]: 47.7-57.4) and 51.1 (95% CI: 46.2-56.1), respectively. Rates of mortality and institutionalization were 7.4 (95% CI: 6.2-8.5) and 13.4 (95% CI: 11.7-15.1). In all, 17% of patients in mild stage at baseline (Clinical Dementia Rating = 0.5) did not experience a major event (functional disabilities, neuropsychiatric symptoms, or death) over a 4-year period.

CONCLUSIONS

As compared with previous surveys, the current study shows slower rates of decline in AD patients. The present data also underline the high level of variability of disease progression among AD patients. Outcome measures commonly used in clinical trials will need to take into account the recent changes in the prognosis of the disease.

Alzheimer's disease in the retina: imaging retinal aβ plaques for early diagnosis and therapy assessment

BACKGROUND

Definite Alzheimer's disease (AD) diagnosis at early stages is vital for targeting intervention, yet currently unavailable. Noninvasive detection of the pathological hallmark, amyloid-β protein (Aβ) plaques, is limited in the brain. However, the existence of Aβ plaques in the retina, possibly at presymptomatic stages, may improve early detection of AD.

OBJECTIVE

To summarize clinical and preclinical evidence showing that the retina, an accessible part of the central nervous system, displays abnormalities in AD, especially Aβ plaque pathology. The ability to monitor in vivo retinal plaque dynamics in response to immunotherapy is also assessed.

METHODS

Literature analysis of retinal AD pathology and imaging is provided. In our studies, systemic curcumin is administered to enable monitoring of retinal Aβ plaques in live APP(SWE)/PS1(Δ)(E9) transgenic mice by optical imaging.

RESULTS

Visual and retinal abnormalities, including early manifestation of retinal Aβ plaque pathology, have been documented in AD patients and animal models. In mouse models, retinal Aβ plaques accumulate with age and decrease in response to immunotherapy, consistent with brain pathology. Here, we demonstrate that retinal plaques can be individually monitored in real time following glatiramer acetate immunization.

CONCLUSION

Translation of noninvasive retinal-plaque imaging to humans could eventually facilitate early and accurate AD diagnosis and therapy assessment.

Cognitive exercise and its role in cognitive function in older adults

Converging lines of research indicate that complex mental activity is associated with reduced dementia risk. Thus, intense interest exists in whether different forms of cognitive exercise can help protect against cognitive decline and dementia. However, there is considerable confusion in terminology that is hindering progress in the field. We therefore introduce a concrete definition of cognitive training (CT) and make this the focus of our article. Clinical research that has evaluated CT in normal aging, mild cognitive impairment, and dementia is then critically reviewed. Despite many methodological shortcomings, the overall findings indicate that multidomain CT has the potential to improve cognitive function in healthy older adults and slow decline in affected individuals. Finally, practical issues, including the strengths and weaknesses of commercial products, are explored, and recommendations for further research and clinical implementation are made.

Is passive immunization for Alzheimer's disease 'alive and well' or 'dead and buried'?

BACKGROUND

Passive immunization strategies are under investigation as potential disease-modifying therapies for Alzheimer's disease (AD). Current approaches, based on data demonstrating behavioral improvement and reduced pathology in transgenic animal models, have focused exclusively on immune targeting of beta-amyloid.

OBJECTIVE

To examine immunization strategies for AD.

METHODS

A review of relevant publications.

RESULTS/CONCLUSIONS

Preliminary results from three Phase II trials suggest both the promise and the need to exercise caution with this method of immunotherapy. The strategies used were distinct, using monoclonal N-terminal, central epitope, and polyclonal antibodies to maximize the efficacy and safety of each approach. The tested compounds are moving into Phase III trials for mild to moderate AD. We await the discoveries that from these studies that may yield the first disease-modifying therapy for AD.