TapTalkTest Project:Development of a Non-invasive Screening Test to Detect Risk of Alzheimer's Disease Pathology
Study Details
Study Description
Brief Summary
This project aims to produce a solution for the rising incidence of dementia. This is particularly pertinent in Tasmania, Australia, with a rapidly ageing population and the oldest demographics of all Australian states. We will develop TapTalk, a new screening test that detects risk of Alzheimer's disease (AD) pathology. TapTalk, will record a person's hand movements and speech patterns with a smartphone. Computer algorithms will learn which patterns of data are associated with AD pathology. This innovative test is based on: (i) emerging research that fine motor control required for hand and speech movements is sensitive to early AD pathology and (ii) our new machine learning methods.
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Detailed Description
This project aims to produce a solution for the rising incidence of dementia. This is particularly pertinent in Tasmania, with a rapidly ageing population. We will develop TapTalk, a new screening test that detects risk of Alzheimer's disease (AD) pathology. Accounting for 70% of all dementias, the brain pathology of AD progresses silently for more than 10 years before cognitive symptoms emerge (preclinical AD). We could prevent 40% of dementia by modifying risk factors such as physical inactivity and smoking. So what is stopping us? Our lack of a cost-effective screening tool means we cannot target interventions, or recruit to drug trials, in early AD. Currently, cognitive tests lack sensitivity in preclinical AD, and specialist AD biomarker tests are invasive or costly.
We will address the hypothesis: "Hand-speech movement patterns will detect the risk of
Alzheimer's disease pathology in research and clinical cohorts" through three aims:
-
Develop and validate analytic algorithms for TapTalk by determining which combinations of hand-speech movement data most accurately detect preclinical AD
-
Develop smartphone capability for TapTalk and determine usability and validity
-
Prospectively validate TapTalk in people who have cognitive symptoms against gold-standard clinical diagnosis of Mild Cognitive Impairment (MCI) and AD dementia
AIM 1 Problem: Identify which combination of hand-speech tests will be most discriminatory.
Method: We will develop software to video-record a 2-minute oral DDK (diadochokinesis) test, where participants make speech-liek sounds repetitively e.g. pa-ta-ka. We already have software to collect hand movements (see TAS Test project). We will invite 500 ISLAND Project participants (>50 years old) with normal cognition to compete the hand-speech tests. All participants have provided blood samples for p-tau181 levels. This new assay quantifies AD pathology (using our ultrasensitive Simoa analyser) but the practicalities and cost of accessing the highly-specialist analytic equipment limit wide accessibility. We use >1.81 pg/ml as the cut-off as this is highly predictive of AD risk (hazard ratio 10.9).
Analysis: We will use deep neural networks to automatically track video keypoints (e.g. finger/thumb tips) and audio features (e.g. pa-ta-ka). A sliding window approach extracts measures (e.g. speed/rhythm) as input data for developing an algorithm that that classifies p-tau181 levels. Outcome: TapTalk protocol and algorithm.
AIM 2 Problem: Develop smartphone capabilities and age/cognitive status cut-offs Method We will develop a smartphone app. ISLAND Project participants (CANTAB cognitive tests every 24 months in-kind) will be invited to complete TapTalk online every 12 months.
Analysis: Multi-level regression models will measure within-subject variability, and group differences on TapTalk and CANTAB at baseline, 12 and 24 months.
Outcome: An externally validated TapTalk algorithm that produces AD risk scores across age and cognitive ranges.
AIM 3 Problem: Validate TapTalk in people with cognitive symptoms. Method: Our clinician researchers working at the Royal Hobart Hospital (RHH) will recruit 100 patients with cognitive symptoms (>3months) from RHH acute medical/subacute units. The research assistant (RHHF funding requested) will complete a standard cognitive screening tool (MoCA) and smartphone TapTalk then invite patients to attend the new ISLAND cognitive clinic after discharge. This 'one-stop' interdisciplinary clinic provides bulk-billed neuropsychological and geriatrician/neurologist/physiotherapist/speech pathologist assessments. We will also recruit 100 consecutive patients referred to the clinic by their GPs and all patients will complete TapTalk.
Analysis: The accuracy of TapTalk and MoCA will be compared to diagnosis using ROC analysis.
Outcome: TapTalk prospectively clinically validated.
Study Design
Arms and Interventions
Arm | Intervention/Treatment |
---|---|
ISLAND cohort About 1,000 participants completed hand motor and speech tests online and 150 will attend the research centre for usablity assessments |
Diagnostic Test: Tap Talk online program
Online hand and speech motor testing
|
Clinical The new app will be tested in about 100 patients at each of the ISLAND Cognitive Clinic or the Royal Hobart Hospital |
Diagnostic Test: Tap Talk online program
Online hand and speech motor testing
|
Outcome Measures
Primary Outcome Measures
- Classification accuracy for blood biomarker of Alzheimer's disease, ptau181 in adults without cognitive symptoms [2024]
Area under a receiver operating characteristic (ROC) curve - AUC
- Odds ratio of cognitive decline in adults without cognitive symptoms [2025]
Mixed effects logistic regression will be used to estimate the odds of a participant being confirmed as 'declining' at time T2 (24 months) conditioned on TapTalk score at time T1 (12 months), where the main measure of cogitive function is the CANTAB paired associate learning (PAL) test.
- Classification accuracy for prospectively predicting risk of MCI and AD in adults with cognitive symptoms [2025]
We will calculate AUC for TapTalk and MoCA. 95% confidence intervals will be obtained using bootstrapping. Covariates may include age, gender, APOE4, years of education, and handedness. We will estimate cut-off scores for TapTalk and MoCA to differentiate between cognitively unimpaired vs MCI, and between cognitively unimpaired vs AD using the Youden index to optimise the trade-off between sensitivity and specificity. Classification accuracy (sensitivity and specificity) using these cut-offs will be compared using McNemar's test.
Eligibility Criteria
Criteria
AIM 1 AND AIM 2 Eligibility criteria
Inclusion Criteria:
- Adults >50 years old who are participants in the ISLAND Project and who have provided a blood sample and have normal cognition and no persistent (>3 months) cognitive symptoms will be eligible.
Exclusion Criteria:
- Impaired cognition, defined by a validated cut-off score >1.5 SD above the mean total errors adjusted for age and gender on the Paired Associates Learning sub-test of CANTAB.
AIM 3 Eligibility criteria Inclusion Criteria: >3 months of persistent cognitive symptoms (patient- or family-reported) and >50 years old.
Exclusion criteria: Acutely unwell, significant impairment of hand function, or known diagnosis of mild cognitive impairment (MCI) or dementia.
Contacts and Locations
Locations
Site | City | State | Country | Postal Code | |
---|---|---|---|---|---|
1 | University of Tasmania | Hobart | Tasmania | Australia | 7001 |
Sponsors and Collaborators
- University of Tasmania
Investigators
- Study Director: James Vickers, PhD, University of Tasmania
Study Documents (Full-Text)
None provided.More Information
Additional Information:
- ISLAND Project - 10-year prospective cohort study that we will recruit participants from in Aims 1 and 2
- ISLAND Clinic - a one-stop cognitive assessment clinic that we will recruit participants from in Aim 3
Publications
- Alty J, Bai Q, Li R, Lawler K, St George RJ, Hill E, Bindoff A, Garg S, Wang X, Huang G, Zhang K, Rudd KD, Bartlett L, Goldberg LR, Collins JM, Hinder MR, Naismith SL, Hogg DC, King AE, Vickers JC. The TAS Test project: a prospective longitudinal validation of new online motor-cognitive tests to detect preclinical Alzheimer's disease and estimate 5-year risks of cognitive decline and dementia. BMC Neurol. 2022 Jul 18;22(1):266. doi: 10.1186/s12883-022-02772-5.
- Alty J, Lawler K, Salmon K, McDonald S, Stuart K, Cleary A, Ma J, Rudd K, Wang X, Chiranakorn-Costa S, Collins J, Merl H, Lin X, Vickers JC. A new one-stop interdisciplinary cognitive clinic model tackles rural health inequality and halves the time to diagnosis: Benchmarked against a national dementia registry. Int J Geriatr Psychiatry. 2023 Aug;38(8):e5988. doi: 10.1002/gps.5988.
- Bartlett L, Bindoff A, Doherty K, Kim S, Eccleston C, Kitsos A, Roccati E, Alty J, King AE, Vickers JC. An online, public health framework supporting behaviour change to reduce dementia risk: interim results from the ISLAND study linking ageing and neurodegenerative disease. BMC Public Health. 2023 Sep 29;23(1):1886. doi: 10.1186/s12889-023-16805-2.
- Huang G, Li R, Bai Q, Alty J. Multimodal learning of clinically accessible tests to aid diagnosis of neurodegenerative disorders: a scoping review. Health Inf Sci Syst. 2023 Jul 22;11(1):32. doi: 10.1007/s13755-023-00231-0. eCollection 2023 Dec.
- Wang X, St George RJ, Bindoff AD, Noyce AJ, Lawler K, Roccati E, Bartlett L, Tran SN, Vickers JC, Bai Q, Alty J. Estimating presymptomatic episodic memory impairment using simple hand movement tests: A cross-sectional study of a large sample of older adults. Alzheimers Dement. 2023 Jul 30. doi: 10.1002/alz.13401. Online ahead of print.
- UTasmania