SBIR-STTR Award

This project addresses a critical need for early detection of mild cognitive impairment (MCI) and other Alzheimer's-related dementias (ADRD). Advances in smartphone hardware, computer vision, and machine learning have enabled the possibility of producing smartphone-based cognitive testing applications able to collect electronic sensor data and transform it into highly informative phenotypes that can serve as early indicators of future disease progression. In this project, we aim to develop a revolutionary new smartphone- based cognitive testing platform, called CTX, that will enable the rapid development and deployment of smartphone-based tests that can capture raw sensor streams in a synchronized fashion, subsample and compress the combined streams, and transmit them to a cloud server for subsequent analysis and modeling. CTX will provide a high-level application development framework that will significantly reduce the time and technical knowledge required to produce a smartphone-based cognitive testing application by providing an application programming interface (API) that enables developers to simply declare what sensor data should be collected and when. The framework will handle all the details of collecting the sensor data, synchronizing it, and transmitting it to a back-end server. The API will also have a variety of other high-level features to facilitate development of cognitive test apps. To demonstrate the feasibility of our vision for CTX, in Aim 1 of this project we will develop the software framework, back-end server software and a prototype smartphone app to exercise and validate many of the platform's features. For Aim 2, we will develop three different tests for this app to test saccade (eye movement) latency, verbal recall, and wrist mobility, each collecting a different type of sensor data (video, audio, and inertial measurement). These tests were selected because their results have been been shown to be predictive of MCI. We will implement phenotype extraction pipelines that employ advanced signal processing, machine learning, and computer vision algorithms to extract the target phenotypes from the sensor data collected for these tests and demonstrate they operate with sufficient accuracy to replicate published experimental designs. Successful completion of this project will eliminate the need for expensive and cumbersome phenotype collection equipment (e.g., eye tracking stations) and create the possibility of generating data from which MCI onset can be predicted. Data collected in Phase II via these and other such tests will enable us to apply our machine learning expertise to produce models able to predict transition to MCI that are both sensitive and specific, transforming any smartphone into an MCI risk assessment tool available for at-home use by millions of people.

Public Health Relevance Statement:
Project Narrative This NIH Phase I project will address the critical need for early detection of Alzheimer's Disease (AD) and Alzheimer's-related dementias (ADRD) by developing a revolutionary new smartphone-based cognitive testing platform that will provide individuals with an ongoing status of their cognitive health. Doctors who are given access to the results of these tests will be able to monitor patients more closely and provide more timely diagnoses. By studying test results from many people, researchers may someday be able to identify patterns that can distinguish mild cognitive impairment from normative age-related cognitive decline.

Project Terms:
Achievement; Address; Adult; Age; age related; age related cognitive change; Age-associated memory impairment; Algorithms; Alzheimer disease detection; Alzheimer's Disease; Alzheimer's disease model; Apple; application programming interface; Assessment tool; Back; base; Big Data; Cellular Phone; cloud platform; Cognitive; cognitive development; cognitive task; cognitive testing; cohort; Collection; Computer software; Computer Vision Systems; cost; crowdsourcing; Cyclophosphamide; Data; data modeling; Data Set; Dementia; Detection; Development; Devices; Diagnosis; diagnostic screening; Diagnostic tests; Disease Progression; Early Diagnosis; Elderly; Emotional; Equipment; Exercise; Exhibits; Experimental Designs; Eye; Eye Movements; Face; Facial Expression; Forearm; Frequencies; Future; Genetic Risk; Genotype; Goals; Health; Healthcare; Home environment; Image; Individual; interest; Knowledge; Lead; Machine Learning; markov model; Measurement; Memory impairment; Methods; mild cognitive impairment; Modeling; Monitor; Patient Monitoring; Patients; Pattern; Phase; Phenotype; predictive modeling; prototype; Publishing; Reporting; Research Infrastructure; Research Personnel; response; Risk Assessment; Rotation; Saccades; Scanning; screening; Secure; Sensitivity and Specificity; sensor; signal processing; Small Business Innovation Research Grant; smartphone Application; software development; Software Framework; Software Tools; Stream; success; Tablets; Telephone; Test Result; Testing; Time; United States National Institutes of Health; Vision; Visuospatial; Work; Wrist; Yang

In this Phase II SBIR project, Parabon NanoLabs will complete the development, validation andcommercialization of CTX, a revolutionary smartphone- and tablet-based cognitive testingplatform for collection and analysis of measurements of cognitive performance ("phenotypes").Traditionally, cognitive assessments are performed in a clinic using either simple surveys thatassess only some aspects of cognition or expensive, single-purpose equipment such as eye trackingstations. Such testing lacks the frequency and precision needed to detect subtle early changes thatsignal the onset of mild cognitive impairment (MCI) or early-symptomatic dementia. Instead,CTX will take full advantage of mobile sensors (e.g., audio, video, touchscreen, and motion) toenable in-depth cognitive testing anytime, anywhere. Regular use of CTX will allow a clearerpicture of each user's cognitive abilities to emerge, enabling early detection of subtle changes. CTXis not intended to replace neurologists but instead to extend their reach by allowing regular,widespread screening for improved disease detection and patient monitoring. The long-range goalof CTX is to allow aging adults to monitor and manage their cognitive health more effectively andto provide pre-symptomatic indicators of pending dementia to patients and their clinicians, thusenabling early intervention and planning.After a highly successful Phase I project, CTX already enables rapid development of mobile teststhat can capture raw sensor streams in a synchronized fashion and transmit them to a cloud serverfor subsequent analysis and reporting. Sophisticated analytics pipelines have been developed toconvert these sensor streams into cognitive phenotypes (e.g., extracting eye movement data fromselfie video taken during a cognitive test). Using the CTX framework, the Parabon team hasalready developed an Apple® iOS® mobile app with proof-of-principle tests for assessing verbalrecall, eye movement, motor function, and episodic memory.In Phase II, we propose to develop two new suites of CTX tests for one-time cognitive impairmentscreening and cognitive performance monitoring, as well as phenotype extraction pipelines foreach. We will evaluate tests in normal and affected cohorts to determine usability, user retentionand whether resulting phenotypes enable accurate cognitive assessments by clinicians. Ourspecific aims are to (1) Develop new and engaging cognitive tests and pipelines for assessing visualsearch and targeting, expressive and receptive language, motor movement and episodic memory;(2) Validate measures in cognitively normal and impaired cohorts; and (3) Analyze and preparedata for publication and premarket submissions to the FDA.

Public Health Relevance Statement:
PROJECT NARRATIVE According to the World Health Organization, the number of people living with dementia is expected to triple from 50 million to 152 million by 2050. Existing pen-and-paper cognitive tests used for dementia screening were designed to detect overt disease, but early detection of cognitive decline is needed for proper intervention and planning. In this project, we are developing a smartphone- and tablet-based set of highly accurate tests that can be used for one-time cognitive impairment screening and game-like activities for ongoing cognitive health monitoring.

Project Terms:
<3-D><3D><3-Dimensional><21+ years old>