Accelerometers have the ability to capture significant quantities of raw data, potentially containing patterns which, if discoverable, could be used to quantify specific motor movements. The ability to detect such movements has value in identifying periods of tremor or other neuromuscular disorder.
We conducted a proof of concept for developing digital biomarkers from raw accelerometer data that we presented as a poster entitled 'Proof of Concept for the Development of Digital Biomarker using Raw Accelerometer Data' from a Wrist Worn Device at the DIA US meeting in 2016.
There is increasing interest in the use on accelerometer based wrist-worn devices in clinical trials. What isn’t well know is that wearables have been around for over 40 years with the first research papers citing the use of accelerometer based wrist-worn devices to capture human activity and sleep patterns appearing in the 1970’s.
Accelerometers are electromechanical devices that measure acceleration forces. They have a wide variety of applications and are found in phones, in drones for flight stabilisation, are used by seismologists to detect earthquakes and are key components in the deployment of air bags where they are used to detect car crashes.
The most common types used in wearables today are triaxial MEMS accelerometers; small micro electro-mechanical systems (MEMS), that measure acceleration in 3 dimensions and are very sensitive to human motor movements.
These devices are capable of sampling up to 100 hertz- which results in 100 data points been collected every second. Potentially one device worn continuously for 7 days could produce 60million datasets. The management of this level of data was beyond both the memories and the analytics capabilities of these devices.
Originally the data generated was compressed and filtered by on-board firmware into epochs of 30seconds[1]*. This pre-processing significantly reduces the amount of data so in the example above, where the device is worn for 7 days, the output is 20 thousand datasets rather than 60 million.
This is still a sizable amount and further analysed by validated algorithms generates discrete sleep and activity endpoints. From a data management perspective, within a clinical trial, the data from accelerometers can be managed in a similar fashion to blood pressure or temperature with 7 days of accelerometer data producing a finite number of clinically relevant endpoints.
The use of accelerometer data in this manner is well established, although limited to researchers and clinicians, focusing on the quantification of physical activity and sleep patterns. What is less well understood is the additional value that potentially exists in the raw accelerometer data, which may have potential in the monitoring and assessment of specific motor movements such as tremor.
For this experiment we selected tooth-brushing as a surrogate for tremor as it was easy to reproduce the action and the movement was discrete and finite. Context is essential in the management of raw data and we used a diary to timestamp the periods of interest, this allows for the identification of the signal of interest.
The training data used to generate the algorithms was different to the data periods that were tested. A set of classical machine models (decision trees, random forest, etc.) were built on the training dataset. A number of algorithms were identified and tested the best one had a positive predicative value of 0.9991.
This Proof of concept has demonstrated that it is possible to use machine learning techniques to train a classification model from summarized raw accelerometer data to identify periods of specific movement patterns. There are issues regarding scalability but the potential value of accelerometer based devices to provide insights into human physical behaviours is considerable.
The advent of Artificial Intelligence and machine learning platforms will transform the ability of these devices to identity new and exploratory endpoints in patients with neuromuscular disease. This approach has potential application in objectively measuring motor movement events in neuromuscular disorders but also in the development of unique personal digital fingerprints.
Reference:
[1] Other epochs can be selected, earlier models generated data in 1 minute epochs, 30 seconds are most common in sleep studies, with shorter epochs used in the assessment of physical activity.
In this section
-
Digital Disruption
- AI and clinical trials
-
Clinical trial data anonymisation and data sharing
-
Clinical Trial Tokenisation
-
Closing the evidence gap: The value of digital health technologies in supporting drug reimbursement decisions
-
Digital disruption in biopharma
-
Disruptive Innovation
- Remote Patient Monitoring
-
Personalising Digital Health
- Real World Data
-
The triad of trust: Navigating real-world healthcare data integration
-
Patient Centricity
-
Agile Clinical Monitoring
-
Capturing the voice of the patient in clinical trials
-
Charting the Managed Access Program Landscape
-
Developing Nurse-Centric Medical Communications
- Diversity and inclusion in clinical trials
-
Exploring the patient perspective from different angles
-
Patient safety and pharmacovigilance
-
A guide to safety data migrations
-
Taking safety reporting to the next level with automation
-
Outsourced Pharmacovigilance Affiliate Solution
-
The evolution of the Pharmacovigilance System Master File: Benefits, challenges, and opportunities
-
Sponsor and CRO pharmacovigilance and safety alliances
-
Understanding the Periodic Benefit-Risk Evaluation Report
-
A guide to safety data migrations
-
Patient voice survey
-
Patient Voice Survey - Decentralised and Hybrid Trials
-
Reimagining Patient-Centricity with the Internet of Medical Things (IoMT)
-
Using longitudinal qualitative research to capture the patient voice
-
Agile Clinical Monitoring
-
Regulatory Intelligence
-
An innovative approach to rare disease clinical development
- EU Clinical Trials Regulation
-
Using innovative tools and lean writing processes to accelerate regulatory document writing
-
Current overview of data sharing within clinical trial transparency
-
Global Agency Meetings: A collaborative approach to drug development
-
Keeping the end in mind: key considerations for creating plain language summaries
-
Navigating orphan drug development from early phase to marketing authorisation
-
Procedural and regulatory know-how for China biotechs in the EU
-
RACE for Children Act
-
Early engagement and regulatory considerations for biotech
-
Regulatory Intelligence Newsletter
-
Requirements & strategy considerations within clinical trial transparency
-
Spotlight on regulatory reforms in China
-
Transfer of marketing authorisation
-
An innovative approach to rare disease clinical development
-
Therapeutics insights
- Endocrine and Metabolic Disorders
- Cardiovascular
- Cell and Gene Therapies
- Central Nervous System
-
Glycomics
- Infectious Diseases
- NASH
-
Oncology
- Paediatrics
-
Respiratory
-
Rare and orphan diseases
-
Advanced therapies for rare diseases
-
Cross-border enrollment of rare disease patients
-
Crossing the finish line: Why effective participation support strategy is critical to trial efficiency and success in rare diseases
-
Diversity, equity and inclusion in rare disease clinical trials
-
Identify and mitigate risks to rare disease clinical programmes
-
Leveraging historical data for use in rare disease trials
-
Natural history studies to improve drug development in rare diseases
-
Patient Centricity in Orphan Drug Development
-
The key to remarkable rare disease registries
-
Advanced therapies for rare diseases
-
Transforming Trials
-
Accelerating biotech innovation from discovery to commercialisation
-
Ensuring the validity of clinical outcomes assessment (COA) data: The value of rater training
-
Linguistic validation of Clinical Outcomes Assessments
-
Optimising biotech funding
- Adaptive clinical trials
-
Best practices to increase engagement with medical and scientific poster content
-
Decentralised clinical trials
-
Biopharma perspective: the promise of decentralised models and diversity in clinical trials
-
Decentralised and Hybrid clinical trials
-
Practical considerations in transitioning to hybrid or decentralised clinical trials
-
Navigating the regulatory labyrinth of technology in decentralised clinical trials
-
Biopharma perspective: the promise of decentralised models and diversity in clinical trials
-
eCOA implementation
- Flexible delivery models
-
Implications of COVID-19 on statistical design and analyses of clinical studies
-
Improving pharma R&D efficiency
-
Increasing Complexity and Declining ROI in Drug Development
-
Innovation in Clinical Trial Methodologies
- Partnership insights
-
Risk Based Quality Management
-
Transforming the R&D Model to Sustain Growth
-
Accelerating biotech innovation from discovery to commercialisation
-
Value Based Healthcare
-
Strategies for commercialising oncology treatments for young adults
-
US payers and PROs
-
Accelerated early clinical manufacturing
-
Cardiovascular Medical Devices
-
CMS Part D Price Negotiations: Is your drug on the list?
-
COVID-19 navigating global market access
-
Ensuring scientific rigor in external control arms
-
Evidence Synthesis: A solution to sparse evidence, heterogeneous studies, and disconnected networks
-
Global Outcomes Benchmarking
-
Health technology assessment
-
Perspectives from US payers
-
ICER’s impact on payer decision making
-
Making Sense of the Biosimilars Market
-
Medical communications in early phase product development
-
Navigating the Challenges and Opportunities of Value Based Healthcare
-
Payer Reliance on ICER and Perceptions on Value Based Pricing
-
Payers Perspectives on Digital Therapeutics
-
Precision Medicine
-
RWE Generation Cross Sectional Studies and Medical Chart Review
-
Survey results: How to engage healthcare decision-makers
-
The affordability hurdle for gene therapies
-
The Role of ICER as an HTA Organisation
-
Strategies for commercialising oncology treatments for young adults
-
Blog
-
Videos
-
Webinar Channel