December 9, 2020 PAP-Q4-20-NI-004
Patient behaviors and key biological metrics are significantly easier to track with the multitude of wearables at the disposal of clinical researchers. The most frequently used consumer wearables include ActiGraph, Apple Watch, and Fitbit.1 By February 2020, clinicaltrials.gov showed that ~460 wearables studies were underway,1 and, according to Kaiser Associates and Intel, 70% of clinical trials will incorporate some type of wearable sensors by 2025.1
Pharmaceutical and medical device companies are empowered to take advantage of robust data sets to optimize trials and products to improve treatment efficacy. Wearable data can provide profound insights that can be leveraged in product development owing to the depth and breadth of the information that can be collected. Theoretically, wearables can be used across therapeutic areas for deep phenotyping, detection, and interpretation of adverse effects and for clinical trial recruitment.1 Clinical trials depend on rich patient data, and collection in a physician’s office captures only a snapshot of a participant’s data, (e.g., one ECG or phenotype analysis). Conversely, wearables constantly track consumer and patient data over large periods of time, with the potential for real-time feedback, resulting in rich data sets and opportunities to gain more meaningful insights.
Personal data collected in EHRs, as well as biological data collected via personal wearables and medical devices, are critical components in the success of clinical trials. AI tools can support analysis before and during a trial, and many life science organizations have started to see their value. Novartis has created a proprietary machine learning predictive analytics platform called Nerve Live. Novartis partnered with QuantumBlack, known for collecting data from Formula One races and using machine learning to optimize race operations. With QuantumBlack’s help, Novartis piloted the platform to support its global drug development team’s plan to simulate country allocation scenarios for clinical studies. The platform tracks all data points of the 550 clinical studies running in parallel and uses analytical software to predict issues in clinical trial execution.
Janssen Pharmaceuticals and Apple announced a collaboration in January 2019, culminating in the launch of a research study that focuses on the use of the Apple Watch’s irregular rhythm notifications and the ECG app to improve AF outcomes and early detection.
Verily, a sister company of Google, kicked off Project Baseline in 2017. This was a collaboration with Duke and Stanford universities to collect health data of participants over a four-year timeline. The collection of clinical consultation and survey data produced a large data set, creating a baseline for what it means to be healthy and the transition to disease. The success of the project resulted in a partnership between Verily, Pfizer, Sanofi, Novartis, and Otsuka in mid-2019. Using Verily’s platform, patients and clinicians can actively engage in clinical trials that will increase the speed of clinical research. The program aims to map out the human health baseline and carry out clinical studies using technology developed under Verily to research a variety of diseases, including cancer, diabetes, and heart, dermatologic, and mental health diseases. The American Heart Association is using Verily’s platform for the “Research Goes Red” registry, an initiative soliciting women across the country to participate in health research, particularly for heart disease. After launching its marketing campaign, it received more than 26,000 registrations, including 8,500 people who provided consent for specific clinical trials and are open to joining additional research opportunities through Project Baseline.1
Recruitment and retention in clinical trials can specifically benefit from AI tools, such as machine learning and natural language processing. These tools can find matches between specific patients and trials that are recruiting through integration with electronic health records (EHRs), medical devices, and wearables and recommend these matches to doctors and patients (either in real time at the clinical consultation or as a notification on the patient’s wearable). In addition to recruitment, participant retention is a formidable challenge. The application of AI to rich patient data presents the opportunity to track a patient’s compliance with a clinical trial’s adherence criteria. The data can be presented to clinical trial administrators, allowing them to notify the patient of retention risks and take predictive and preemptive measures rather than practicing reactive management.
AbbVie, a biopharmaceutical company specializing in oncology, immunology, neuroscience, virology, and eye care, began integrating wearables into clinical trials in 2016.2 The company wanted to deploy digital technologies but also wanted to improve the way it designed clinical trials to make them more data-driven. A center of excellence was created for clinical trial design that focused on using large data sets to help teams visualize the required patient population, the impact of their design decisions on patients, and the expected impact of geography and epidemiology. One trial was conducted using the Philips Actigraphy watch to measure sleep quality and itching in patients with atopic dermatitis. In another trial, patients with Parkinson’s disease wore wearable devices that measured gait and sleep, which can be more difficult to measure using traditional methods with pen and paper. Patients wore sensors on their arms and legs that continuously and objectively measured Parkinson’s motor symptoms and measured the quality of their sleep — something that greatly affects overall quality of life for patients who suffer from the disease. AbbVie subsequently replaced those devices with a wireless patch worn on an arm and leg. The patches are more comfortable and less intrusive for patients.
While wearables and AI tools create opportunities to simplify and streamline clinical research, they also elucidate the need to simplify existing processes, roles, and systems in life science companies. In advance of the broad adoption of wearables in clinical trials, researchers will continue to test and validate the feasibility of wearables in studies. Sponsors should also continue to partner with device makers to evolve endpoint data collection and validation. Studies have found that having clinical scientists directly involved in clinical study design and conduct is highly beneficial.1 However, R&D scientists are generally not familiar with wearable devices, creating barriers to the adoption of wearable technologies in drug development clinical trials. Juxtapose this with the fact that device engineers lack knowledge and expertise as it pertains to drug development process and regulatory requirements for drug approvals, and collaboration seems necessary to streamline adoption and make wearable technology a standard in clinical studies.
Successful integration of wearables into clinical studies also hinges on meaningful collaboration with regulators to ensure that the scope of the clinical study is well defined and that outcomes can be achieved and implemented. Guidelines such as the Clinical Trials Transformation Initiative support such collaboration through recommendations for the use of mobile technology like wearable devices. One of its first recommendations is for R&D departments to start with a clinical trial endpoint and work backward to ensure that investigators select the right device. Consumer and medical device makers, researchers, technology data platform companies, and regulators must coordinate efforts in order to realize the full potential of this technology.
A multitude of wearable devices are currently available for market consumption, and even more are in development, with promising implications for both overall health and cost efficiency. The global wearable computing devices market accounted for 181.5 million units in 2019, and it is expected to reach 520.1 million units by 2025, registering a compound annual growth rate of 19.9% over the forecast period between 2020 and 2025.3 The product categories within the wearable tech market exhibit considerable diversity.
Smart clothing, including smart vests, smart bras, smart shoes, smart socks, and smart tights have a multitude of potential applications, including protecting the wearer from environmental hazards. Additionally, with an increase in the cases of chronic diseases worldwide, such as diabetes, cancer, respiratory disorders, and heart diseases, combined with the increase in the number of surgeries performed, the demand for smart fabric in the healthcare sector is expected to increase exponentially.3 Edema ApS is developing a washable stocking to monitor and measure changes in leg volume for patients suffering from edema in lower limbs. Similarly, in March 2020, Powercast and Liquid X entered a joint venture to help manufacturers implement wearable sensors directly into garments, with potential applications for monitoring patients and athletes.3
According to Infopulse, over 80% of consumers are eager to wear fitness wearables, indicating interest and concern for monitoring various aspects of their health.3 Augmented demand will also accelerate the development of personalized healthcare services, smart hospitals, and remote healthcare. In 2019, the FDA authorized the first wearable for hospital use, an AI-powered solution by Current Health.3 This device traces a patient’s health indicators with ICU-level accuracy and indicates threatening conditions, assisting healthcare providers in identifying deteriorating states and facilitating immediate provision of lifesaving services and procedures. Use of exoskeletons is anticipated to increase, as the North American population is slowly aging. In 2018, 16% of the U.S. population was 65 years or older, and by 2050 this number is expected to increase 20%.3 The growing older population is expected to influence the demand for rehabilitation robots in the form of exoskeletons, something that once sounded like science fiction.
As the healthcare industry focuses increasingly on outcomes, pharma companies are looking to sources beyond randomized clinical trials (RCTs) to measure and demonstrate the value they bring. Real-world evidence (RWE) has been in use for decades, but recent advances in technology and advanced analytics allow it to be employed in new ways. It allows for a better understanding of how patient characteristics and behaviors affect health outcomes, thereby helping to predict disease progression, patient response to therapy, and risk of adverse events — while also increasing the efficiency of R&D investments and accelerating time to market.
Cost and competitive pressures, scientific advances, digitally savvy stakeholders, progressive regulatory shifts, and the increasing breadth and interoperability of data and technologies are among many trends driving participants in the healthcare ecosystem to intensify their focus on value and patient outcomes.
Payers are gradually shifting to outcomes-based contracts, providers are working to gain privileged status with them, and patients are taking more ownership of their own outcomes. In this changing environment, insights from RWE are becoming more important in providing the right treatment to the right patient at the right time, measuring outcomes, and demonstrating the value of interventions. Given the significant disruption to RCTs and the need to rapidly understand burden by patient phenotype, as well as finding potential therapies for COVID-19, RWE is more prominent than it has been in the past.
Pharma companies have been using RWE for decades to inform their decision-making, respond to requests from external stakeholders, and improve their therapies’ market positioning. More recently, growing regulatory acceptance, rising demand from payers and physicians, and increasing familiarity with digital and analytics have enabled some companies to derive much broader benefits from RWE.
An average top-20 pharma company that adopts advanced RWE analytics across its entire value chain for in-market and pipeline products could unlock more than $300 million per year over the next three to five years.4 A typical cost base offers scope to save $100 million in development spending through the optimization of RCT design, the use of RWE studies rather than RCTs in some cases, and the implementation of synthetic trial arms.4 Cost savings apart, the introduction of advanced RWE analytics could help companies identify new targets for molecules, accelerate time to market, improve formulary position and payer negotiations, and generate stronger evidence of differentiation and benefit/risk balance for in-market products. Analysis suggests that applying these actions to key assets could generate top-line value of $200 million or more.4
RWE may also support new uses for already approved drugs and/or help determine postapproval requirements for drugs. However, demonstrations of RWE from wearables are small in number to date. This is partially due to the deployment of digital and wearable technology remaining in the sphere of only a few multinational pharmaceutical companies.5 Health insurance companies do not typically pay for digital medicine technology, because their coverage is based on data on patients and their claims. Healthcare systems largely do not yet see the value of wearables in clinical practice. However, multinationals like GlaxoSmithKline, Novartis and Lilly have chief digital officers overseeing integration of mobile and wearable technologies into their clinical trial programs.
These market issues are compounded by issues related to data collection, hosting, sharing, and management. Healthcare systems silos simply cannot handle the continuous stream of real-world data coming from wearable devices. Astonishingly, according to the American Medical Informatics Association, 75% of U.S. clinical centers still use fax machines to share EHRs,5 and few are attempting to incorporate longitudinal real-world data from wearables with EHRs in a seamless environment.
Perhaps the biggest challenge to full wearable integration is data privacy and security. Strategies within the nascent direct-to-consumer wearables industry do not help. Although the American Medical Informatics Association has lobbied to update the 1996 U.S. Health Information Portability and Accountability Act to align wearables’ data privacy policies with those in healthcare systems,5 wearables companies are keen to protect their businesses. Consequently, their algorithms are proprietary, and their data cleanup is ill-defined or opaque, further exacerbating innate challenges with data privacy and perception of data security among users.
While wearable technology has seemingly limitless promise in potential applications for health awareness and medicine adherence, how it will be integrated into the provision of drug treatment and patient care in the future remains to be seen. However, despite a number of challenges, tech companies and life science researchers continue to innovate wearable tech solutions across all facets of the healthcare industry.
Jansen, Yvette; Thornton, Grant. “Wearables & Big Data in Clinical Trials—Where Do We Stand?” VertMarkets, Inc. 25 Feb. 2020. Web.
Miseta, Ed. “AbbVie Goes All-In On Wearables and Digital Technologies.” VertMarkets, Inc. 07 Aug. 2019. Web.
“Global Wearable Computing Devices Market (2020 to 2025)—Growth, Trends & Forecasts.” GlobalNewsWire. 24 Jun. 2020. Web.
Champagne, David, Alex Davidson, Lucy Pérez, and David Saunders. “Creating Value From Next-Generation Real-World Evidence.” McKinsey & Company. 23 July 2020. Web.
“Getting Real With Wearable Data.” Nature Biotechnology. 02 Apr. 2019. Web.
David is Scientific Editor in Chief of the Pharma’s Almanac content enterprise, responsible for directing and generating industry, scientific and research-based content, including client-owned strategic content, in addition to serving as Scientific Research Director for That's Nice. Before joining That’s Nice, David served as a scientific editor for the multidisciplinary scientific journal Annals of the New York Academy of Sciences. He received a B.A. in Biology from New York University in 1999 and a Ph.D. in Genetics and Development from Columbia University in 2008.