Many individuals with Alzheimer’s disease or other forms of dementia go undiagnosed until they reach the later stages of the disease. On the other hand, individuals who do receive an earlier dementia diagnosis do not currently have the means to properly monitor the progression of their disease. Tracking the progress following a diagnosis is critical—especially for those undergoing treatment—to understand how their cognitive and functional abilities are changing.
While there are currently several methods to diagnose dementia through predictive biomarkers, they are often rather inaccessible and undesirable due to the cost and invasiveness. As for analysis and monitoring tools, traditional methods in place are outdated and lack the granularity for meaningful data analysis and tracking.
Below we detail a brief description of current monitoring tools and diagnostic tools and the need to provide more accessible and robust patient care, such as a comprehensive brain test app for dementia.
Conventional methods for screening, analyzing, and monitoring brain health and dementia include the Mini-Mental State Exam (MMSE), the Montreal Cognitive Assessment (MoCA), and the Mini-Cog, which were developed in 1975, 1996, and 2000, respectively.
The MMSE and MoCA are routine cognitive screening tools rated on a 30-point scale that aim to assess cognitive abilities. The MMSE consists of a series of questions and tests, evaluating several cognitive abilities, including memory, attention, and language. The MoCA incorporates elements of the MMSE with the addition of a Clock Drawing Test (CDT). Similarly, the Mini-Cog is a short-duration screening tool consisting of a three-item recall test and a CDT used to assess memory, cognitive function, visual-motor skills, language comprehension, and executive function.
Perhaps the greatest issue with conventional pencil and paper cognitive tests is the narrow nature and lack of ecological validity—the concept of realism with which the design of cognitive evaluation matches and aligns with real-world activities. In other words, conventional cognitive assessments do not evaluate the cognitive and functional abilities required to complete day-to-day activities, such as dressing, bathing, and grooming.
Tools, such as the MMSE, MoCA, and Mini-Cog, exercise the brain in a low cognitive load state through a series of memory tests, written questions, and drawings. If a brain test app for dementia could implement exercises that place the brain under a higher cognitive load to better simulate day-to-day functioning, the brain health of individuals would become more robust and clear, helping to better guide treatment paths.
Traditional methods for predictive diagnosis of Alzheimer’s and other forms of dementia include positron emission tomography (PET), magnetic resonance imaging (MRI), and cerebrospinal fluid (CSF). Each of these methods is detailed further in the table below.
|Diagnostic Tool||Means of Predictive Diagnosis|
|PET||PET scans can be implemented to analyze patterns of brain activity associated with dementia. Amyloid PET scans utilize radioactive tracers to highlight amyloid protein plaques (a neuropathological hallmark of Alzheimer’s disease) within the brain.|
|MRI||MRI reveals the anatomical structure of the brain, helping to rule out tumors, hemorrhages, and other conditions which present similarly to dementia. MRI can also be used to assess volume changes in characteristic parts of the brain, such as the temporal and parietal lobes.|
|CSF||CSF can be collected from the subarachnoid space in the spine via a lumbar puncture and analyzed for biomarkers associated with cognitive disease. For Alzheimer’s disease, levels of beta-amyloid, total tau, and phospho-tau can be measured to provide a diagnosis.|
While traditional tools for predictive diagnosis of dementia are scientifically valid methods and have diagnostic accuracies ranging from 69-75%, these tools are invasive, expensive, and time-consuming. The very nature of such approaches to diagnosing dementia makes receiving a diagnosis inaccessible to many individuals, depriving them of the opportunity for early detection, intervention, and treatment.
Altoida is developing a precision neurology platform to measure and analyze nearly 800 unique digital biomarkers associated with cognitive impairment. Our iOS- and Android-based augmented reality (AR) activities are designed to place the user’s brain under a higher cognitive load while mimicking aspects of day-to-day activities on both a cognitive and functional level. These highly personalized measurements of brain health will provide a comprehensive and robust approach to monitoring brain health.
We are also working to implement our innovative artificial intelligence (AI) to assist in predicting the onset of neurological disease. Our goal is for our platform and AI to support a breadth of diagnoses.