Alzheimer's Disease (AD) is one of the most common forms of dementia to occur in elderly populations around the globe, currently affecting over 30 million people worldwide. As the U.S. elderly population continues to increase, the incidence of AD rises as well, as there is no known neuroprotective therapy or cure. The most common symptoms include memory loss, cognitive impairment, disorientation, and psychiatric issues. The initial diagnosis is achieved through a combination of clinical criteria including a neurological examination, mental status tests and brain imaging. However, these strategies are challenging for detection of early AD or patients with mild symptoms, specifically during the mild cognitive impairment (MCI) stage. Mental status tests and subjective journals, kept by patients or caregivers, are often used to track AD progression, but have low sensitivity and reliability for clinical trials. The most strongly established biomarkers for AD, including amyloid beta, tau protein, and phosphorylated tau, are all obtained thru CSF requiring invasive lumbar puncture. ALZ-Stage technology will provide a convenient and accessible, yet comprehensive analytics suite to detect and stage Alzheimer's disease progression. The platform will integrate a progressive suite of diagnostic tests using a variety of biological, neurological, and behavioral platforms, subjective and objective inputs, and active and passive test components. The test battery may include blood sample, urine samples, wearable sensors, mobile phone sensors and behavioral tracking. The implementation strategy will progress from lower cost, more readily accessible and passive monitoring devices to more expensive, invasive and burdensome test as likelihood or ALZ stage increases. Unique patient demographics may impact sensitivity. For example, AD incidence in women is twice as high as men. Additionally, based on socio-economic or geographic disparities some populations may only have access to certain types of test equipment or supplies compared to others. Therefore, ALZ-Stage will use AI algorithms not only to detect and stage AD, but will also determine the specific test battery to use based on availability of test options and patient demographics. The Phase I effort will target the highest risk project component which includes core algorithm development and verification. We will increase likelihood of project success by building on our existing framework that has shown strong feasibility for adaptively predicting test batteries to screen patients for Parkinson's disease. The work will be completed through strong collaboration with our expert technical team at Elder Research and our strong clinical consultants. More specifically, Phase I tasks will focus on developing an array of biomarker test suites for AD, collecting data from a wide range of AD subjects and controls with widely varying demographics, and using that data to build a two layer intelligent algorithm that can determine the most appropriate test battery for a subject and also accurately detect and stage AD during the MCI stage.
Public Health Relevance Statement: The objective is to design, develop and demonstrate feasibility of ALZ-Stage, an artificial intelligence driven technology that utilizes an adaptive suite of personalized diagnostic tests to both detect and determine the progressive stage of MCI in Alzheimer's disease. While more than 5.7 million Americans are living with Alzheimer's, early and accurate diagnosis can significantly improve outcomes and could save up to $7.9 trillion in healthcare and long-term costs. Therefore, a low-cost, personalized, and widely accessible test suite to detect and stage AD progression would have a significant positive impact on healthcare outcomes and costs, as well as neuroprotective trials aimed at stopping or slowing disease progression.
Project Terms: accurate diagnosis; Affect; Algorithms; Alzheimer disease screening; Alzheimer's Disease; Alzheimerâs disease biomarker; American; Amyloid; Amyloid beta-Protein; Artificial Intelligence; base; Behavioral; Biological; Biological Markers; Blood; Blood specimen; Brain imaging; Car Phone; care outcomes; Caregivers; Cause of Death; Cerebrospinal Fluid; Clinical; Clinical Trials; cognitive performance; Collaborations; common symptom; Consumption; cost; Data; Data Collection; Data Set; Data Sources; Dementia; demographics; design; Development; Diagnosis; Diagnostic tests; Disease Progression; Disorientation; Early Diagnosis; early screening; Elderly; Equipment; Geography; Health Care Costs; Healthcare; high risk; Impaired cognition; implementation strategy; improved outcome; Incidence; inflammatory marker; innovation; Intelligence; Journals; Maps; Memory Loss; men; mental state; mild cognitive impairment; Monitor; monitoring device; Neurologic; Neurologic Examination; Oxidative Stress; Parkinson Disease; patient screening; Patients; personalized diagnostics; Phase; Population; potential biomarker; predictive test; Research; Sampling; screening; Sensitivity and Specificity; sensor; Small Business Innovation Research Grant; social media; socioeconomics; Source; Specificity; Spinal Puncture; Staging; success; Symptoms; tau Proteins; tau-1; Technology; Testing; Time; Underserved Population; Urine; wearable device; Woman; Wor
