Translation of Digital Health Technologies to Advance Precision Medicine: Informing Regulatory Science

Abstract

The proliferation of digital technologies and the application of sophisticated data analysis techniques are increasingly viewed as having the potential to transform translational research and precision medicine. While digital technologies are rapidly applied in innovative ways to develop new diagnostics and therapies, the ultimate approval and adoption of these emerging methods presents several scientific and regulatory challenges. To better understand and address these regulatory science gaps, a working group of the Clinical and Translational Science Awards Program convened the Regulatory Science to Advance Precision Medicine Forum focused on digital health, particularly examining gaps in the use, validation, and interpretation of data from sensors that collect and tools that analyze digital biomarkers. The key findings and recommendations provided here emerged from the Forum and include the need to enhance areas related to data standards, data quality and validity, knowledge management, and building trust between all stakeholders.

The Constrained-Disorder Principle Assists in Overcoming Significant Challenges in Digital Health: Moving from “Nice to Have” to Mandatory Systems

“…Modern AI systems, including second-generation and beyond, are more flexible and can learn and adapt over time, which could make them more useful in medicine. To provide high-quality patient care, digital systems must provide a holistic approach that uses robust data and personalized parameters relevant to their healthcare needs [ 91 ].…”

“…Eighty percent of data remains silent as, in many cases, it is hard to take the data to the last mile toward the patient [ 145 ]. To provide meaningful information, the data must be translated into precision health [ 91 ]. It is possible for vulnerabilities, such as adversarial attacks and a lack of tools to regulate the quality of information and cybersecurity, to affect results negatively.…”

Tackling the translational challenges of multi-omics research in the realm of European personalised medicine: A workshop report

“…Additionally, general concerns around data privacy and regulatory compliance-related restrictions as well as ethical and legal aspects must not be overlooked. When working with multi-omics and/or clinical data there are multiple data security, ethical, and personal information barriers that can present potential roadblocks ( Knowles et al, 2017 ; Adamo et al, 2018 ; Adamo et al, 2020 ). Moreover, each European country has its own national implementations of General Data Protection Regulation (GDPR) for processing personal data ( Vlahou et al, 2021 ).…”

Digital Biomarkers in Psychiatric Research: Data Protection Qualifications in a Complex Ecosystem

“…Digital biomarkers, i.e., “consumer-generated physiological and behavioral measures collected through connected digital tools” ( 11 ) or “objective, quantifiable, physiological, and behavioral measures collected by means of digital devices that are portable, wearable, implantable, or digestible” ( 12 ), arguably have the potential of addressing at least some of the traditional biomarkers' limitations ( 13 , 14 ). Improvements in sensors, software, and algorithms, together with the increasingly widespread adoption of digital technologies in daily life, enable the gathering of key health-related data remotely, in non-invasive and seamless ways, blurring the boundaries between biomedical research and research participants' daily life ( 15 , 16 ). In other terms, digital devices enable “continuous measurements outside the physical confines of the clinical environment” ( 17 , 18 ).…”