Digital biomarkers are healthcare’s next frontier

Blood pressure, body temperature, hemoglobin A1c levels and other biomarkers have been used for decades to track disease. While this information is essential for chronic condition management, these and many other physiological measurements are typically captured only periodically, making it difficult to reliably detect early meaningful changes.

Moreover, biomarkers extracted from blood require uncomfortable blood draws, can be expensive to analyze, and again, are not always timely.

Historically, continuous tracking of an individual’s vital signs meant they had to be in a hospital. But that’s not true anymore. Digital biomarkers, collected from wearable sensors or through a device, offer healthcare providers an abundance of traditional and new data to precisely monitor and even predict a patient’s disease trajectory.

With cloud-based servers and sophisticated, yet inexpensive, sensors both on the body and off, patients can be monitored at home more effectively than in a hospital, especially when the sensor data is analyzed with artificial intelligence (AI) and machine-learning technology.

Opportunities for digital biomarkers

A major opportunity for digital biomarkers is in addressing neurodegenerative diseases such as mild cognitive impairment, Alzheimer’s disease and Parkinson’s disease.

Neurodegenerative disease is a major target for digital biomarker development due to a lack of easily accessible indicators that can help providers diagnose and manage these conditions. A definitive diagnosis for Alzheimer’s disease today, for example, generally requires positron emission tomography (PET), magnetic resonance imaging (MRI) or other imaging studies, which are often expensive and not always accurate or reliable.

Cost savings and other benefits

Digital biomarkers have the potential to unlock significant value for healthcare providers, companies and, most importantly, patients and families, by detecting and slowing the development of these diseases.

Identifying early signs of these neurodegenerative conditions and limiting or preventing progression through cognitive rehabilitation — which has been shown to be effective — could improve outcomes and quality of life for patients and families. After all, mild cognitive impairment (MCI) emerges before Alzheimer’s disease in about 33% of cases, typically several years earlier. Developing accurate digital biomarkers associated with the type of MCI that leads to Alzheimer’s disease could start an individual on a treatment path earlier.

There has been encouraging progress in developing digital biomarkers based on patients’ eye movement, drawing with digital pens, card-game performance and walking movements to detect early signs of Alzheimer’s disease. While more clinical trials and peer-reviewed studies need to be completed to verify their accuracy and reliability, adoption of these biomarkers seems likelier than ever.

Mental and behavioral health

Similarly, the tracking and diagnosis of mental and behavioral health conditions is a challenge. There is no blood test for major depressive disorder or generalized anxiety disorder, and while numerous diagnostic tools exist for schizophrenia, no validated physiological biomarker exists.

Digital tools could again fill the gap. With consent, healthcare technology companies can use smartphones to passively and continuously collect data that, along with periodic patient surveys, help providers measure the effectiveness of therapies and predict patients’ conditions.

Research led by the University of California in Los Angeles, for example, found that AI-powered technology was able to accurately analyze an individual’s voice responses to questions to identify signs of a worsening condition.

How AI changes the game

The evolution of digital biomarkers is particularly compelling for healthcare stakeholders for two reasons:

  1. Data can be largely collected remotely, routed through a cloud-based server and then analyzed by healthcare providers at a medical facility. This can eliminate costly and time-consuming office visits while improving patient engagement. When combined with engaging, interactive mobile activities, truly passive data collection makes it more likely that patients will continue with a management program.
  2. Digital biomarkers are personalized. All of these biomarkers can be analyzed by an AI-powered data engine that factors in the patient’s medical history, demographics and data from millions of similar patients. The result is a highly personalized, real-time evaluation of the patient’s status and trajectory, which can increase the accuracy of predictions.

Together, these factors mean digital biomarkers can be deployed in a fully scalable manner.

Limitations and challenges

Advances in technology sometimes happen too quickly. Numerous questions and concerns around digital biomarkers need to be addressed.

For example, how can a health tech company ensure the free flow of data between the patient and provider is protected from cyberattacks, maintain HIPAA compliance and appropriate patient privacy?

Patient data privacy and security laws were not designed for an ecosystem in which a patient shares protected health information directly with a technology company. Uncertainty around privacy and security will have to be resolved before providers can comfortably study digital biomarkers.

Another challenge is reliability. Traditional biomarkers have been developed and refined since the advent of medicine, while digital biomarkers are a 21st century concept. Although COVID-19 has forced healthcare to embrace change faster than it has in the past, digital biomarkers will require a deeper evidence base before they are widely adopted and accepted by providers, pharmaceutical developers and regulators.

Lastly, since digital biomarkers are still evolving, there is not yet a firm reimbursement structure or financial incentive to use them. Certainly, the value they deliver to clinical research and remote patient monitoring are worth paying for, but questions such as how much and when and who should pay will need to be resolved.

For example, the CMS, FDA and research institutions are trying to answer questions such as how much a health insurer should pay for the collection and tracking of digital biomarkers in Alzheimer’s disease, or how much value should be ascribed to improvements in digital biomarkers tied to chronic diseases such as diabetes.

The future is at home

If there is one thing the COVID-19 pandemic has taught us, it is that more healthcare can be safely and effectively delivered to patients in their homes. With the advent of evidence-based and reliable digital biomarkers, the care-at-home evolution will continue, freeing up hospital beds for the very sick, lowering costs for the healthcare system and greatly improving the care experience for patients and their families.