By Czuee Morey, Ph.D. | July 18, 2018

This is a summary of a talk I presented at Life Science Forum Basel, Switzerland on June 7, 2018 and at eClinical Forum, Darmstadt, Germany on May 16, 2018.

What are digital biomarkers?

I think everyone has heard of a Fitbit, and probably many of us use a Fitbit or a similar device to track our exercise or mobility, and sometimes even heart rate. Increasingly, many smartphone apps are also available for health management with or without connection to these sensor devices.

There are 318,000+ health apps and 340+ sensor devices available today and the number of apps is doubling every two years

This surge in technology has made it possible for ‘consumers’ to track their health, but also represents an interesting opportunity for remote patient monitoring in healthcare and clinical trials. Data collected about a patient’s activity and vital signs can be used to get an idea about the patient’s health status and disease progression on a daily basis. However, the problem is that a majority of these apps and devices are meant for wellness purposes and not intended to diagnose or treat diseases.

So, how can we leverage these digital devices as biomarkers – that is to get an accurate description of a disease, disease progression or effect of treatment!

This is a question that the field of digital biomarkers revolves around.

How can wearables help in clinical trials and healthcare?

In a typical clinical trial or in a clinical setting, the patient visits the hospital or clinic not more than once per month or even less frequently. So, the clinician can observe the signs and symptoms of the patient only during this visit and has almost no visibility on how the patient is doing for the 99% of the time outside the clinic. Also, in some cases such as neurological disorders, the assessments done by the doctors are based on observation which lead to inter-clinician variability of assessment.

Patients are observed only during hospital visits and in many cases (such as CNS diseases) the disease assessments are based on physician observation rather than quantitative and unbiased measures.

If digital biomarkers are used, the patients can perform these tests using smartphones or sensors in the comfort of their home. For example, in a Parkinson’s disease trial various aspects of the patient’s health (as shown in the figure) were captured in a remote study using smartphone-based apps. This allows the collection of quantitative and unbiased data on a frequent or almost continuous basis. The clinician can get almost a real-time feedback on each patient, whether they are getting better or worse. This feedback can help to inform the study protocol or even halt the study if the drug doesn’t seem to be working on most of the patients.

The Clinical Trials Transformation Initiative (CTTI) provides a framework and detailed guidance for developing digital biomarkers. They also outline various benefits of using digital biomarkers in clinical trials such as being patient-centric while also making faster decisions that save time and costs.

“Mobile technologies for data collection should be considered in all future trials to improve the quality and efficiency of clinical trials and the value of the data they collect.” – CTTI recommendations

Why do we need to validate digital biomarkers?

Recently, a couple of self-driving car accidents have made front-page news even though we have hundreds of car accidents each day due to human error! When we are dealing with human lives (as compared to online shopping predictions), we want to make sure the device and algorithms are making accurate predictions even in the variable conditions of the real world.

This is the reason why we need to develop and validate digital biomarkers rigorously to ensure we are really capturing what we intend to capture.

Considerations in developing and validating digital biomarkers.

  1. Endpoint selection: The first and most important consideration in developing digital biomarkers is not which device to use, but rather deciding which disease symptoms to capture that best represent the disease. Involving patients, care-givers and physicians in the discussion is necessary to understand which symptoms matter to patients. At the same time, its important to consider if these symptoms can be objectively measured and what is a meaningful change in measurement that reflects treatment benefit.
  2. Device selection & validation: Once it is clear what endpoints need to be captured, the right device can be selected. The device technology needs to be verified (measurement errors, variances, etc.) and device also needs to be validated for the specific use (reproducibility; accuracy & precision compared to gold standard or independent measurements). An observational study is required to ensure the suitability of the device before deploying it in a trial.
  3. Data capture & Analysis: A continuous measurement of vital signs across several patients translates to an abundance of data that might not always be necessary for the necessary endpoints. Hence, it is necessary to determine during the feasibility study which measures makes sense to capture. Setting appropriate checks to ensure quality of data and dealing with missing data and data variability is important.

The ‘garbage in – garbage out’ maxim applies not only to input data but also to the statistical models used

The algorithms and statistical models developed for converting input data to a clinically relevant phenotype also need to be validated. This is especially important because the data will be collected in the real world and not in a clinical setting, which can lead to a lot of noise and outliers.

Which diseases can be tracked with digital biomarkers?

“There is a scarcity of technology-derived measures being used as actual outcome assessments in studies of neurological diseases such as Parkinson’s and Alzheimer’s, which have a considerable unmet need for measures.” – CTTI

Heart disease and diabetes measurements are common application areas for sensor-based devices. However, digital biomarkers could have the most impact in monitoring CNS diseases since it gives us the opportunity to measure symptoms that were largely intractable until now. A recent article from Roche describes an observational study on using digital biomarkers for active and passive monitoring in a Parkinson’s disease trial.

Various sensor devices are available for tracking several aspects of health such as activity, heart rate, blood glucose and even sleep, breath, voice and temperature. Most smartphones are equipped with several sensors that can perform various motion, sound and light based tests. In addition the smartphone can be used for psychological tests or to detect finger motions through the touchscreen. These measures can be used in various combinations to predict the health aspects or symptoms required. I have given a few examples below.

Digital therapeutics – the next frontier

As you can imagine, digital biomarkers can have several applications beyond clinical trials, for example in diagnostics – to identify patients affected by a disease, to gather real-world evidence and other beyond-the-pill services.

However, the most interesting application is in digital therapeutics where the device/app can be used as a treatment! Last year, Pear therapeutics obtained the first ever FDA clearance for a digital therapeutic. They demonstrated a clinically relevant outcome from using their app in substance use disorder as compared to face-to-face therapy. Similar results have also been obtained in various other disease areas.

Challenges

Digital biomarkers present a big opportunity for measuring endpoints in a remote, objective and unbiased manner that was largely difficult until now. However, there are still several challenges that need to be considered before developing and deploying them to measure endpoints in clinical trials. A risk-benefit analysis of the advantages and risks on a case by case basis can help to guide the development of this field.

What, according to you, are the biggest challenges in implementing digital biomarkers in clinical settings? Looking forward to your comments below!

I’m an Innovation Consultant & Business Analyst in Digital Health at Wega Informatik in Basel. Get in touch with me for consulting or project assignments in digital biomarkers or for other digital health projects.

The opinions presented here are my own and do not represent those of my employer.

Original Article