Biomarkers for Alzheimer's Disease in the Current State: A Narrative Review

Abstract

Alzheimer's disease (AD) has become a problem, owing to its high prevalence in an aging society with no treatment available after onset. However, early diagnosis is essential for preventive intervention to delay disease onset due to its slow progression. The current AD diagnostic methods are typically invasive and expensive, limiting their potential for widespread use. Thus, the development of biomarkers in available biofluids, such as blood, urine, and saliva, which enables low or non-invasive, reasonable, and objective evaluation of AD status, is an urgent task. Here, we reviewed studies that examined biomarker candidates for the early detection of AD. Some of the candidates showed potential biomarkers, but further validation studies are needed. We also reviewed studies for non-invasive biomarkers of AD. Given the complexity of the AD continuum, multiple biomarkers with machine-learning-classification methods have been recently used to enhance diagnostic accuracy and characterize individual AD phenotypes. Artificial intelligence and new body fluid-based biomarkers, in combination with other risk factors, will provide a novel solution that may revolutionize the early diagnosis of AD.

Keywords: Alzheimer’s disease (AD); biomarkers; low or non-invasively; machine-learning classification.

Figure 1

The pathogenesis and temporal changes of Alzheimer’s disease (AD). AD is characterized by the accumulation of amyloid-beta (Aβ), tau, p-tau, brain atrophy, and cognitive decline. Accumulation of Aβ occurs gradually from the presymptomatic period. In the mild cognitive impairment stage (MCI), Aβ deposits and tau-mediated neuronal damage, and short-term memory problems progress gradually. In the dementia stage, Aβ deposit and tau-mediated neuropathy further structural abnormalities of the brain and memory impairment occurs. The black lines indicate the accumulation of Aβ in the brain.

Figure 2

Biomarker-screening modalities for AD. Conventionally used biomarkers for Alzheimer’s disease (AD) include positron emission tomography (PET) and single-photon emission computed tomography (SPECT) to examine brain function and nuclear magnetic resonance to analyze structural changes in the brain. AD biomarkers include amyloid β 42 (Aβ42), phosphorylated tau (p-tau), and total tau (t-tau) levels in cerebrospinal fluid. New biomarkers such as optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) for measuring eye vascular abnormalities, electroencephalograms (EEG) for measuring brain waves, and AD marker genes have been found. Biomarkers in urine, blood, and saliva have also been identified.

Figure 3

Extensive data search by machine learning. The first step is to collect big data from dementia patients. Then, they are labeled as presymptomatic (Pres.), mild cognitive impairment (MCI), and Alzheimer’s disease (AD) patients. Next, input to machine learning from a large amount of labeled data. The results of this machine learning are evaluated to calculate a model that can make accurate predictions. The next stage is the implementation phase. New unlabeled invasive data, PET (positron emission tomography), and MRI (magnetic resonance imaging) data are used to train machine learning models and make predictions. The output is the result of predicting whether the patient is Pres., MCI, or AD. These results can be used for the early diagnosis of AD. Furthermore, to develop accurate early diagnosis techniques, it is crucial to improve machine-learning models with feedback from diagnostic data.