The landscape of consumer wearables has significantly grown over the last decade, transforming from simple fitness trackers into sophisticated health monitors. Popular devices like the Apple Watch, Fitbit Tracker, Whoop band, and Oura ring now provide users with a wide range of data points, from step counts to heart rate, sleep cycles, and even body temperature. The growth in the wearable market is impressive, with projections valuing it at €34.15 billion ($37.37 billion) in 2024. These wearables are not just fashion accessories; they motivate individuals toward better wellness habits. However, as the demand for more meaningful health insights grows, companies face a new challenge: transforming raw wellness data into clinically relevant digital biomarkers.
Challenges in Developing Digital Biomarkers
Consumer wearables were initially designed to track simple metrics like step counts, a function that was primarily for user motivation rather than health diagnostics. Over time, these devices have incorporated more advanced sensors, allowing users to monitor their sleep quality, heart rate, and other metrics through sleek and intuitive interfaces. While this data is valuable for personal wellness management, it is not yet considered clinically valid. The leap from wellness tracking to health diagnostics introduces various challenges, the first of which is the development of digital biomarkers.
A digital biomarker refers to a quantifiable health metric collected through digital devices, which is then validated for clinical use. For wearable companies to introduce such biomarkers, extensive research must ensure that the sensor data accurately reflects meaningful health states. Unlike wellness data, which can be used for personal insights, clinical data must adhere to stringent standards of accuracy and reliability. However, many wearable companies rely on their existing user base to collect data for research, which poses significant challenges. Convenience sampling—using data from individuals already using the devices—may not comprehensively represent the broader population. This limits the findings, and results based on such data may be skewed, undermining their clinical relevance.
Role of Research and Algorithm Development
To truly integrate digital biomarkers into wearables, companies must invest in high-quality research. The example of Whoop’s study on heart rate variability (HRV) as an indicator of preterm birth illustrates how promising insights can emerge from wearable data. However, upon closer examination, the study lacked important demographic information such as race, socioeconomic status, and comorbidities, limiting the findings' generalisability. Additionally, the participants were already health-conscious individuals, introducing potential bias into the results.
For digital biomarkers to become clinically useful, rigorous validation processes are necessary. This includes large-scale studies with diverse and representative populations. Furthermore, the algorithms built to interpret the data need to be continuously trained and improved as more data is collected. Engineers like Brandon Mathis explain that while it is technically feasible to deploy algorithms based on small datasets, it is essential that these algorithms evolve over time to provide accurate predictions. Continuous learning models that update with additional data and outcomes are crucial in ensuring the long-term validity of digital biomarkers. Additionally, research must go beyond incidental findings—correlations found in data—that often serve as marketing material but lack substantial clinical backing.
Importance of Regulatory and Validation Frameworks
One of the biggest hurdles in turning wellness data into clinically validated biomarkers is the lack of regulatory oversight in wearable technology. As Dr Brinnae Bent from Duke University points out, there is currently no formal requirement for how large or representative a study must be before a new feature can be integrated into a wearable device. This absence of regulation allows companies to fast-track new features based on limited research, potentially delivering invalidated health insights to millions of users.
The Digital Medicine Society (DiMe) has made significant strides in addressing this gap with its V3 Framework, which provides guidelines for verifying sensor performance and validating the algorithms that drive digital biomarkers. This framework ensures that the data collected from wearables is both accurate and relevant in a clinical context. By adhering to such standards, companies can move beyond wellness tracking and offer meaningful health insights that meet the rigorous demands of healthcare providers and patients alike. The V3 Framework represents an essential resource for companies looking to add actual clinical value to their wearable devices, offering case studies and best practices that guide the development of new digital biomarkers.
The journey from wellness tracking to the integration of clinically validated digital biomarkers in wearables is fraught with challenges but holds immense potential for the future of healthcare. As consumer demand for more meaningful health insights grows, wearable companies must invest in high-quality research beyond convenience sampling and incidental findings. By adhering to established frameworks like DiMe’s V3 Framework and continuously improving algorithms with larger and more diverse datasets, wearable companies can unlock new health insights that are both clinically relevant and valuable to consumers. For wearables to provide true healthcare value, they must transition from personal wellness tools to validated medical devices capable of delivering accurate, actionable health information. This shift requires ongoing investment in research, data validation, and regulatory adherence, but the potential benefits for both individual users and the broader healthcare system are profound.
Source: Digital Health Insights
Image Credit: iStock
