Digital Biomarkers in Neurology

Primary Category

Digital Neurology

P-Category

Secondary Category

S-Category

Authors:

Afshan Mumtaz,
Talha Nazir MD,
Hafsa Shahid,
Muhammad Mushood Ur Rehman MBBS,
Filzah Faheem MD,
Junaid Kalia MD

Introduction

Digital biomarkers (DBMs) are objective quantifiable data points (endpoints).

They are collected with the help of digital devices which are

Wearables
Digestible capsules
Implants
Wearable tools such as watches to track steps for fitness.
Digestible capsules are used to record data for gas volume
Implantable tools to measure heart rhythm

DBMs are a crucial part of digital health technologies.

Defining Digital Biomarkers (DBMs)

💡

According to the Food and Drug Administration (FDA), “Digital biomarkers are a set of characteristics and properties collected from digital health technology, which is measured as an indicator of the biological, pathological process and the response to any exposure or intervention which can be therapeutic.”

Defining Digital Health Technologies

💡

Definition of digital health technologies (DHT)

A system that uses computing platforms, connectivity, software, and sensors for healthcare and related uses.

Examples:

1.Wellness apps that reminds a person if stays long in sun to limit UV exposure.

2.Apps to send reminder for medicine reminders, so it helps in adherence to treatment.

3.Sensors that can collect data and latter can help to study and develop medical product.

Figure 1: HealthIoT tools, measures, and devices

Table 1: Types of data collected by wearable devices

Types	Definition	Examples
Passive Data	Passive digital biomarker data is collected from sensors that are integrated when the user wears the devices	Accelerometer, Gyroscope, Location, and distance traveled.
Active Data	Active digital biomarker data is when the user interacts with the devices or gives any input.	Cameras, Forms, Voice, Symptom reporting

Figure 2: Passive-Hybrid-Active Continuum of data collection example of sleep monitoring

Source: Coravos, et al. (2019). Digital Medicine: A Primer on Measurement. Digital Biomarkers, 3(2), 31–71. https://doi.org/10.1159/000500413

Understanding Digital Endpoints

Defined as “ Data generated by sensors outside the clinical environment, for example in a patient's free-living conditions.”

There are two types of digital endpoints

Digital Biomarkers (DBMs)
Electronic Clinical Outcome Assessment (eCOA)

Table 2: Type of Digital Endpoints

Type of Endpoint	Description	Modality
Digital Biomarkers	Indicator of a biological and pathological process	Objective
Clinical Outcome Assessment	Direct measure of how the patient feels, survive, and function.	Subjective

Table 3. Categories of Digital Biomarkers

Biomarker category	BEST definition	Digital biomarker example
Diagnostic biomarker	A biomarker used to detect or confirm the presence of a disease or condition of interest or to identify individuals with a subtype of the disease	An algorithmic classification of cardiovascular features extracted from optical sensors on wearable devices to identify atrial fibrillation
Monitoring biomarker	A biomarker measured repeatedly for assessing the status of a disease or medical condition or for evidence of exposure to (or effect of) a medical product or an environmental agent	An accelerometer-based sensor device that collects data about chest and limb movement to measure gait in patients with Huntington’s Disease
Pharmaco-dynamic/Response biomarker	A biomarker used to show that a biological response has occurred in an individual who has been exposed to a medical product or an environmental agent	A wrist-worn DHT may collect accelerometer data and use the data to detect physiological changes (e.g., tremor and bradykinesia) in response to a pharmacological agent

Electronic Clinical Outcome Assessment (eCOA) types

Electronic Clinical Outcome Assessment (eCOA) is a digital record of subjective assessment in different domains of the patient journey described in Table 4.

Electronic Patient-Reported Outcome (ePRO)
Electronic Performance Outcome (ePerfO)
Electronic Clinician-Reported Outcome (eClinRO)
Electronic Observer-Reported Outcome (eObsRO)

Table 4: Types of Clinical Outcome Assessment (eCOA)

eCOA	Definition	Example
ePRO	Information reported by patients with the help of electronic devices	Rating of pain activity or severity of migraine asking them to grade on 1-10 scale
ePerfO	Measuring the functional ability of participants using electronic devices	Tapping exercises on a smartphone for bradykinesia in parkinsonism/memory recall in dementia.
eClinRO	Clinician observing the participants and grading them	Alzheimer’s disease who is unable to report so clinician will report.
eObsRO	Life partner, caretaker, parent observing the patient	Unconscious patient observed by any person

Application of Digital Biomarkers

Digital biomarkers are easy to access, cheaper , providing continuous health data not restricted to just visits.

Creates more precise, personalized plan getting detail at cellular level helping in field of precision medicine.

Digital biomarkers can help in managing patient according to severity of disease.

💡

Recently, in March 2022 FDA (food and drug administration) issued graft guidance providing its recommendation on the use of digital health data in clinical investigations.

The digital biomarkers (endpoints) are used by the digital medicine society in partnership with multiple pharmaceutical companies, for the launch of 3Ps of digital endpoints(3Ps), which is a tool kit of resources created to facilitate the inclusion of digital endpoints as evidence for payers and helping them in reimbursement and development of the new medical product.

Table 5: 3Ps of Digital endpoints in Tool kit Resources

Tool kit Resources	Description
Project/ Patient toolkit	Patient groups that are vital to establishing the value of evidence derived from digital endpoints
Pharma toolkit	Companies developing new drugs and medical products are evaluated using data derived from digital endpoints
Payer toolkit	Organizations making reimbursement decisions about new drugs explain their efficacy using data derived from digital endpoints

Digital biomarkers in clinical care

Clinical care can be done remotely.

The care team should be able to provide the summary with red flags so, that patient should know when to report.

For quality digital care, these two things should be kept in mind:

Clinical practice guidelines.
Care pathways.

The care team should be able to optimize the genetic data with the storage data.

For example, Abilify MyCite is a product consist of aripiprazole tablets in software-based ingestible event marker for tracking drug intake.

Table 6: Real-Time Use of Digital Biomarkers

Disease/Conditions	Tool	Digital Biomarker	Measures	Data from patient
Social Anxiety	Software app	1. Heart Rate 2. Heart Rate Variability 3. Exposure to light social contact 4. Location-based marker	1. Level of anxiety 2. Triggers of anxiety 3. Risks of Anxiety	1. Passive 2. Active How does the patient text or talk on the phone
Parkinsonism	Smartphone app	1. Tapping 2. Speed of typing	1.Vocal assessment 2.Motor coordination	1.What is the quality of voice 2.Tone of the voice 3.Movement of the hand while holding a phone
Tremors	Touchscreen sensors, wearable wrist device	1.Hand movement (amplitude and length in resting and during movement).	Fine motor skills	1.Can detect human tapping 2.Swiping 3.Typing
Ataxia	Inertial sensors (accelerometer and gyrometer)	1. Step variability 2. Lateral sway	Gait metrics	1 .Can detect human motion 2. Posture
Rehabilitations (orthopaedic surgery)	App-enabled wearable sensors	Posture cubic	Monitoring rehab exercises	1. Range of motions 2. step counts
Stroke, tumor	Camera, wearable devices	1.Mapping metabolic equivalents(MET) to energy level. 2.Stride count 3.stride duration 4.normalized stride count 5.posture cubic	1. Eye co- ordination and reaction 2. Physical activity, 3. Functional range of movement analysis	1. Detect eye movement 2. Pupil dilation and expressions
Alzheimer’s disease	Smart devices	Digitized cognitive testing for focus, verbal memory and attention.	Cognitive impairment	A survey of 10-minute set of activities that are designed for cognitive impairment while doing different aspects of day-to-day activities
ADHD (For patients in trial of stimulants)	Wearable cardiac monitor	Irregular heart rate	Arrythmia	Irregularities in heart rate
Multiple Sclerosis	Smart phone app	1.Typing speed 2.How long the key is pressed 3.Latency of key 4.Errors in Punctuation marks 5.Words space error	1. Motor defect 2. Cognitive Defect	1. Clinical Arm functionality 2. Disease severity

Figure 3: Developing measures that matter, a framework for creating digital biomarkers

Source: Developing and Selecting Digital Clinical Measures That Matter to Patients – Digital Medicine Society (DiMe), 2021)

Digital biomarkers in clinical research

Clinical trial lifecycle

💡

Design and feasibility studies lead to the launch of a study, followed by a trial, and eventually the development of a regulatory submission.

The researchers design the Digital Clinical Trial protocol in advance and discuss it with the sponsoring firms.

This protocol is disseminated digitally to the individuals who voluntarily consented to participate in the study.

These participants are then randomly exposed to the specified medical intervention.

Participants process their own data consisting of a number of digital biomarkers.

Findings are then gathered, organized, analyzed, and sent back to the study team.

Novel endpoints

Novel endpoints are used for clinical trials.

There are multiple positive effects of developing novel endpoints in clinical trials, which are short, medium, and long term, concerning patient care, efficacy, and efficiency.

Evidence-based, and stakeholders do collaborative efforts to get better results.

Novel endpoints are gaining importance as they add the complementary needs of the studies.

Used to identify the gaps and barriers.

Advantages Of Novel End Points In Interventional Trials

Collects data of patients outside the clinic including the daily chores.

Create alliance amongst the healthcare ecosystem i-e payers, sponsors, and patients.

Some promising treatment is rejected before phase 3, novel endpoints help to go it to phase 3.

Foundation Of Determining Fit For Purpose Biometric Monitoring Technologies(BioMeTs)

The evaluation of BioMeTs, can fit to purpose can be use in clinical trials.

Design Specification and Modular Prototyping

A three- component framework is proposed for foundational evaluation of BioMets, which includes

Verification

BioMets, is the technology which evaluates and demonstrate the performance of sensor, by comparing the sample level data with pre-specified set of criteria.

Analytical Validation

Evaluates the performance of algorithm, and the ability of BioMeTs to measure, detect, predict, behavioral and physiological metrics.

Clinical Validation

Evaluates if BioMeTs identifies, measures and predict meaningful clinical, physical experience in a stated context of use which includes specified population.

Clinical Utility

Neurological ongoing trials using digital biomarkers

Phase 2 study (2016)

To measure the seizure activity as assessed by Change in Electrodermal Activity (EDA) from Visit 1 to Visit 9 (Up to 8.5 months) in Rett Syndrome.

Phase 0 study (2017)

To assess variability in Cognitive Performance using the prime outcome measure; high-frequency mood capture in Major Depressive Disorder (MDD)

Phase 1b study (2018)

To measure gait task with smart phone in trouser/belt walking (20yards) turning around and returning to starting point (degree/sec) to determine any gait abnormality at earliest stage.

Phase 0 study (2018)

Detection of brain changes related to mild cognitive impairment and dementia due to Alzheimer’s disease using CG scores(for accuracy and reaction speed).

Phase 4 study (2020)

Determine the changes in Parkinson’s Disease symptoms as assessed by Parkinson’s Kinetigraph/Personal Kinetigraph(PKG) by wearable devices(baseline to week12).

Phase 2 study (2021)

Employing a 3D optical motion capture system (recording upto 10 weeks) to determine the effect of deutetrabenazine on facial movements at rest and during functional task performance in Huntington’s Disease.

Phase 4 study (2021)

Define a correlation between digital outcome assessments (DOAs) and MRI measures of brain tissue damage in people living with Multiple sclerosis(MS).

Digital Biomarkers In Public Health

Digital biomarkers are used in clinical trials, which can be cross sectional and longitudinal.

Providing us

Easy and remote access
An unbiased, reliable , patient centric data
Create an infrastructure for predictive diagnosis.

Digital biomarkers in predictive diagnosis

Predict the effectiveness of medical treatment by tracing patient recovery,
Can help detect disease and
It can also be very transformative in near future.

It can transform healthcare, by early diagnosis of diseases like Alzheimer’s helping us to get the preventive approach and delaying the onset of disease with lifestyle changes.

CognICA integrated cognitive assessment (ICA) test is developed by London based company to test display images at rapid pace on iPad screen and asks users to identify them as animals or non animals.
Recently, FDA has approved an artificial intelligence based test for early detection of dementia on Ipad in five minutes.
The ability of health brain to process images of animals is in less than 200 milli seconds.
This test helps us detect early, before severity of the disease begins.

In multiple sclerosis, vision is mostly affected, presented mostly in the form of optic neuritis, measurement of the retinal nerve fiber layer can be used as digital biomarker,

Regular, monitoring of peripapillary retinal fiber layer, can be used as to monitor the disability in multiple sclerosis.

With the use of digital biomarkers, diabetes mellitus type || may be prevented in targeted population, by analyzing the risk factors.

Encouraging to wear fit bit watches.
Like promoting more walk in obese patients.

If we talk about the future applications in digital biomarkers, the creation of digital biomarker panels, which has both traditional and digital biomarkers giving it better way to explain human health and disease.

In Precision medicine, digital biomarker can play a major role.

As it can be used to facilitate new drug development.
To develop targeted therapies.

Limitations

Lack of regulatory oversight

Limited funding opportunities

General mistrust of sharing personal data

Shortage of open-source data and code

Standards and validation methods in digital biomarker research is limited

Conclusion

💡

The digital biomarkers should undergo significant research like traditional biomarkers to ensure they are accurate, and reliable demonstrating specificity and sensitivity, noninferiority, equivalence, or superiority.

With the wealth of new data, researchers, clinicians, entrepreneurs and consumers better understand states of both health and disease by the help of digital biomarkers.

Digital biomarkers are consumers generated physiological and behavioral measures collected through digital tools creating digital data, that can be be used, influence and predict health related outcomes especially in the field of neurology and psychiatry.

The future of medicine, lies with the advancement of artificial intelligence and implementation of digital biomarkers in figuring deadly disease with smart devices and digital biomarkers.

We expect some devastating revolution in nearly all the fields of medicine with the usage of digital biomarkers.

Bibliography

Neurodiem. (2022). Neurodiem, your daily connection to neuroscience. Neurodiem. https://www.neurodiem.com

The Future of Digital Biomarkers. (2021). Gehealthcare.com. https://www.gehealthcare.com/article/the-future-of-digital-biomarkers

Taylor, P. (2022, May 26). Cumulus puts its digital biomarkers for CNS diseases to the test. Pharmaphorum.com; Pharmaphorum. https://pharmaphorum.com/news/cumulus-puts-its-digital-biomarkers-for-cns-diseases-to-the-test/

healios. (2021, September 19). Healios Digital Health Platform - Empowering Neurology and Clinical Trials teams through novel digital biomarkers and remote monitoring. Healios.io. https://healios.io/dreams/

Ontario Brain Institute. (2020). Webinar - Digital Biomarkers in Brain Health [YouTube Video]. In YouTube. https://www.youtube.com/watch?v=WHTOmh9--Uo

Mahadevan N, Demanuele C, Zhang H, et al. Development of digital biomarkers for resting tremor and bradykinesia using a wrist-worn wearable device. https://www.nature.com/articles/s41746-019-0217-7

Perez, M. V., Mahaffey, K. W., Hedlin, H., Rumsfeld, J. S., Garcia, A., Ferris, T., Balasubramanian, V., Russo, A. M., Rajmane, A., Cheung, L., Hung, G., Lee, J., Kowey, P., Talati, N., Nag, D., Gummidipundi, S. E., Beatty, A., Hills, M. T., Desai, S., & Granger, C. B. (2019). Large-Scale Assessment of a Smartwatch to Identify Atrial Fibrillation. from https://www.pcronline.com/PCR-Publications/Young-EAPCI-PCR-Journal-Club/Large-scale-assessment-Smartwatch-atrial-fibrillation

Andrzejewski, K. L., Dowling, A. V., Stamler, D., Felong, T. J., Harris, D. A., Wong, C., Cai, H., Reilmann, R., Little, M. A., Gwin, J. T., Biglan, K. M., & Dorsey, E. R. (2016). Wearable Sensors in Huntington Disease: A Pilot Study. from https://publications.aston.ac.uk/id/eprint/28234/1/wearables_HD_2016.pdf

Mahadevan, N., Demanuele, C., Zhang, H., Volfson, D., Ho, B., Erb, M. K., & Patel, S. (2020). Development of digital biomarkers for resting tremor and bradykinesia using a wrist-worn wearable device. from https://www.nature.com/articles/s41746-019-0217-7

Bosl, W. J., Tager-Flusberg, H., & Nelson, C. A. (2018). EEG Analytics for Early Detection of Autism Spectrum Disorder: A data-driven approach. Scientific Reports, 8(1). from https://www.nature.com/articles/s41598-018-24318-x

Coravos, A., Khozin, S., & Mandl, K. D. (2019). Developing and adopting safe and effective digital biomarkers to improve patient outcomes. Npj Digital Medicine, 2(1). from https://www.nature.com/articles/s41746-019-0090-4

The Future of Digital Biomarkers. (2021). Gehealthcare.com. from https://www.nature.com/articles/s41746-019-0090-4

The, F. (2022). FINAL The Playbook - v1.1 (4.7.21). Google Docs. https://docs.google.com/presentation/d/1vBEa_ZBhutOCAVVZ2z5Qq8xG2uQ3y2B61LwMUQPJnmw/edit#slide=id.p323

Using evidence from digital endpoints to demonstrate the value of a new drug: Considerations and recommendations. (n.d.). Dimesociety.Org. Retrieved April 9, 2022, from https://www.dimesociety.org/wp-content/uploads/3P-considerations-and-recommendations.pdf

Digital Biomarkers for Alzheimer’s Disease: Early Diagnosis Means Early Treatment - Altoida. Altoida. Published August 17, 2021. Accessed June 10, 2022. https://altoida.com/blog/digital-biomarkers-for-alzheimers-disease-early-diagnosis-means-early-treatment/‌

Coravos, A., Goldsack, Jennifer C., Karlin, Daniel R., Nebeker, C., Perakslis, E., Zimmerman, N., & Erb, M. Kelley. (2019). Digital Medicine: A Primer on Measurement.

Jacobson, N. C., & Bhattacharya, S. (2022). Digital biomarkers of anxiety disorder symptom changes: Personalized deep learning models using smartphone sensors accurately predict anxiety symptoms from ecological momentary assessments. Behaviour Research and Therapy, 149, 104013. https://doi.org/10.1016/j.brat.2021.104013

Sensor-integrated ePRO. BioSensics. Published 2022. Accessed June 10, 2022. https://biosensics.com/technologies/sensor-integrated-epro

Taylor, P. (2021, October 22). FDA clears AI-powered digital test for early dementia. Pharmaphorum.com; Pharmaphorum. https://pharmaphorum.com/news/fda-clears-ai-powered-digital-test-for-early-dementia/

Roadmap to patient-focused outcome measurement - Google Search. (2013). Google.com. https://www.google.com/search?q=Roadmap+to+patient-focused+outcome+measurement&source=lnms&tbm=isch&sa=X&ved=2ahUKEwii97vgzqL4AhUepokEHdd2CZcQ_AUoAnoECAEQBA&biw=1536&bih=848&dpr=1#imgrc=z63D1w2vD0APlM

‌

AizaMD™: Revolutionizing Clinical Documentation

Discover the power of our ambient clinical documentation system, designed to transform clinical encounters into structured SOAP notes with unmatched ease. Experience exceptional value for less than $3 per day—cheaper than your daily coffee!

Save Time: Free up over 90 minutes daily for each provider.

Boost Revenue: Increase daily revenue by at least $1,000 per provider.

Enhance Coding Quality: Our detailed documentation supports superior coding accuracy, ensuring optimal reimbursement.

Maximize Engagement and Interaction: Dedicate more time to patient care and less to typing, fostering richer and more effective conversations between clinicians and patients

AizaMD.AI - Ambient Clinical Documentation.pdf

2011.4KB

The Future of Optimized Clinical Documentation - AizaMD.AI

Revolutionize patient care with AizaMD's AI-driven clinical note-taking system. Effortlessly generate secure notes with ICD-10 codes, saving time and ensuring efficient documentation

http://aizamd.ai/

AizaMD™: Automated Radiology Report Generation!

Discover our breakthrough Radiology AI reporting platform built on Ambient AI. It enhances productivity and minimizes fatigue. Benefit from best-in-class accuracy with our automated radiology report generation, all at market-leading pricing.

📈 Efficiency: Cut dictation times by up to 50% (Less words, More report!

🎯 Focus: Keep your eyes on the images, not the keyboard!

💸 Revenue: Boost revenue by at least 20%

📑 Clarity: Patient summary in plain English

Introduction to ARRG - Reimagine Radiology Report Generation.pdf

1508.6KB

‌