Commanders and troops used hand-sent Morse codes to communicate throughout WWII. Telegraph operators had to stay nameless in order to prevent being discovered by opponents. Any information regarding the identity or position of the operator might have an impact on the result of the conflict.
The sender of communication may be identified using the small temporal discrepancies between the dots and dashes in the transmission, according to US military intelligence.
Because the typing patterns were so unique, the military devised a mechanism dubbed “The Fist of Sender” to discern between communications sent by allies and those delivered by foes. The signatures of code operators might be used by intelligence personnel to trace enemy unit movements.
People’s typing patterns from keyboards or cellphones might disclose a lot more than, as we now know. These signals can also tell us how healthy people are if they have particular diseases, and how far the condition has progressed.
Keystrokes are digital signals that are currently being used as digital biomarkers or indications of biological health. We now have access to numerous digital signals to measure health, thanks to an explosion of smart gadgets and sensors around us, as well as developments in AI to recognize trends.
Patients may forget to take their medication, but they will not forget to put on their Apple watch every morning. Some people even take it to bed with them. Researchers discovered that a large amount of data gathered passively throughout the day from a variety of devices might provide health information that users would overlook.
By tracking patient recovery, digital biomarkers can now assist diagnose illnesses and analyzing the efficiency of medical therapies. “They may be able to detect a dangerous medical problem before physical signs appear in the future,” says Shwen Gwee, Vice President and Head of Global Digital Strategy at Bristol Myers Squibb.
What are biomarkers, exactly? They are medical signals that can be used to monitor health in a precise and repeatable manner. Blood pressure measurements, heart rate, and even genetic test findings are common examples.
Several health markers are measured by modern digital gadgets. Fitbit trackers utilize accelerometers and other sensors to detect how many steps we take in a day and how quickly we walk. When may these new health indicators be used as medical biomarkers?
Objective, quantitative, and repeatable metrics are required. Furthermore, scientific data must demonstrate that the health attribute evaluated by the technology corresponds to a clinical result consistently and reliably. For example, speech signals using a smartphone’s microphone can identify Alzheimer’s disease-related moderate cognitive impairment.
“Today, we have many such digital biomarkers emerging for research and clinical use, such as keystroke dynamics, voice, eye tracking, facial recognition, smell, and gait,” says Richie Bavasso, Co-Founder and CEO of nQ Medical.
Four reasons why digital biomarkers are game-changers
Assume that a clinical study obtains blood sugar measurements from individuals who attend the clinic on a monthly basis. It would be difficult to gather enough evidence for pharmacological approval based on such a limited set of criteria. Patients’ data can be collected passively and remotely using digital biomarkers.
“Passively collected measures are powerful because nobody wants to fill in a survey,” says Andy Coravos, CEO of HumanFirst. “Imagine a patient with a gastrointestinal condition running to the bathroom in the middle of the night. The person is unlikely to note the frequency of occurrence or intensity of these symptoms.” Sensors and wearables collect data passively, around the clock, removing the burden of patient reporting.
Here are four ways digital biomarkers are revolutionizing healthcare today:
1. Helping detect diseases early
In many cases, by the time patients report the first symptoms of neurological diseases such as Parkinson’s, they may have had the condition for over ten years, thereby limiting treatment options. “We are more likely to detect a disease early while someone is using their phone or laptop every day than waiting for the disease to be detected in an annual office visit,” adds Bavasso.
2. Assessing the effectiveness of treatments
By collecting digital biomarkers over time, scientists could measure disease progression and demonstrate the effect of treatments on diseases. When a person takes blood sugar readings every 90 seconds, the measures are likely to be highly accurate over weeks or months. This can help assess the impact of therapy
3. Identifying and resolving clinical trial recruiting challenges
Around the world, 80 percent of clinical studies miss their patient recruitment targets. “One of the major reasons why people decline to enroll is travel,” says Coravos. “To solve this recruitment difficulty, we’re aiming to deliver healthcare closer to home.”
4. Slashing the cost of drug discovery
Digital biomarkers make decentralized clinical trials (DCTs) a reality. “DCTs reduce trial timelines across Phase 2 and Phase 3 studies by enabling remote monitoring of patients and virtual care delivery,” says Coravos. Recent research shows that a typical DCT deployment could shave one to three months off each phase. This represents substantial savings given that clinical trials cost up to $8 million per day.
How data analytics is used by digital biomarkers to identify and track illnesses
Sensors like accelerometers, gyroscopes, and pedometers make it simple to track body motions and sleep patterns. “By assessing tiny indicators of cognitive and motor impairment, they can follow neurological illnesses including Huntington’s, Alzheimer’s, multiple sclerosis, and weariness,” affirms Bavasso.
To quantify brain activity, Bavasso’s team combines sensor-driven metrics with the study of passive activities conducted on computers or cellphones. But how can someone’s cognitive health be determined by typing on a keyboard or pressing buttons on a touchscreen?
“We monitor the exact time when your brain and finger interact with the gadget in milliseconds,” adds Bavasso. “Assume your finger is on the ‘L’ key, and your brain sends a signal to your finger to go to the ‘P’ key. Patients with Parkinson’s disease will have a delay in this signal, which will result in a lag in keystrokes.”
Many forms of device interactions, such as how hard a person punches buttons, their response time to graphics on a touchscreen, and how often they use the backspace, may be used to uncover such patterns using machine learning algorithms. “Because we use our gadgets for eight to ten hours a day, a brain health score iterated every 90 seconds is refined over weeks or months, resulting in rather high levels of brain health.”
What are the differences between these digital and sensor-based ratings and traditional manual measures? Bavasso discusses the findings of a research on amyotrophic lateral sclerosis (ALS), a neurological condition that affects muscular and physical function that has yet to be published. The nQ Medical solution improved accuracy by 33% over the current gold standard, the ten-second finger-tapping test.
Researchers are fast adopting digital biomarkers to disorders including post-surgical brain fog, Covid-19-related cognitive dysfunction, cardiovascular diseases, and cancer-related impairments because they give amazing precision compared to conventional assessments.
This acceptance has been expedited by the epidemic. Faced with the risk of having to halt all clinical studies owing to Covid-19, pharmaceutical corporations welcomed remote patient monitoring. “Take, for example, the Digital Medicine Society (DiMe), which keeps track of industry-sponsored research on digital medicine.
Challenges that could stall the adoption of digital biomarkers
Despite the promise of digital biomarkers, we must overcome three challenges to see their mainstream use.
1. Privacy concerns
A key concern about digital biomarkers is that they snoop on our activities. Companies working on digital biomarkers are tackling privacy concerns by minimizing the identifiable details they capture about individuals.
For example, “nQ does not record what you type but only how you interact with the keyboard and touchscreen,” clarifies Bavasso. He adds that the data ownership and sharing options lie entirely with users.
2. Adoption difficulties
“While health monitoring gadgets like your Apple Watch or iPhone are growing more popular, there is still significant doubt and suspicion of their clinical validity,” Gwee warns. “Additionally, the data quality of many of the consumer digital gadgets we use may not be similar, adding to the uncertainty.”
In order to overcome this aversion to change, not only educating but also incentivizing is required. “Incentives aren’t necessarily about money,” Bavasso argues. “It ought to be simple for patients to use and deliver true personal value.” It should be simple to prescribe and trustworthy for practitioners, with some financial incentives included. When payers witness improved patient outcomes and cost savings, they will be convinced.”
3. Regulatory hurdles
“Digital medicine products are held to much higher accuracy levels than traditional gold-standard tests largely because these novel products are objective and can be measured precisely,” shares Bavasso. “For example, MDS UPDRS – III is a traditional clinical standard for assessing motor impairment in Parkinson’s disease. While it has been clinically validated over decades iteratively, it hadn’t been required to pursue regulatory clearance” he adds.
nQ’s software as a medical device (SaMD) received breakthrough designation from the FDA in 2019. As part of its pivotal trial for approval, the US Food & Drug Administration (FDA) recommended that nQ Medical compare their study results not just to the gold standard UPDRS – III test; instead, they were also required to find other measures of comparison given the subjectivity of the legacy tests.
What does the future hold for digital biomarkers?
We’re on our way to a world where digital biomarkers make clinical measurements less intrusive, enable value-based treatment, and even anticipate illnesses.
Let’s pretend a shopper at the supermarket gets a cart and wanders around the store. They are given a health report at the time they check out and pay the cost. The person’s walking stride, how their eyes scan the shelves, and how their hands pick up and handle the objects are all recorded by video cameras and sensors (hopefully with consent from the individual). Algorithms examine these signals to determine the possibility of significant health problems.