What does it mean to have the ability to quantify patient behavior in daily life? How should it change our view of health outcomes and how to quantify them? Given how fast these capabilities have developed thanks to technology, the market will increasingly demand that therapeutics companies prove product impact outside clinic walls. Whether it is in type 2 diabetes or multiple sclerosis or heart failure, the ability to quantify outcomes from real life patient data is going to change the way we think about the volume-to-value transformation.
In recent years, discussions about digital health have generally focused more on promise than proof of impact. However, this is changing rapidly because technologies are now helping close the gap between old processes and new expectations. These new technologies are enhancing our understanding of disease progression and intervention impact. Traditional, pivotal clinical trials remain essential to prove the efficacy and safety of new healthcare solutions, but real world evidence across broader populations is what payers and regulators are increasingly demanding of the therapeutics industry.
Given the widespread adoption of mobile technologies and digital health apps by patients, we now have a view into the continuous patient journey like never before. We can now “quantify real life” of patients and measure health outcomes beyond traditional clinical trials, at scale. And in this digital era of medicine, we have more robust analytical tools that can sift through massive, complex datasets faster and more reliably. Therapeutics industry leaders can now address some direct drivers of the historical gap between trial efficacy and post-launch effectiveness with solutions that enable:
1. Access to broader connected populations
2. Collection of novel real life data from patients
3. Quantification of real life outcomes
1. Access to Connected Populations
Clinical development strategies for drugs and devices include fundamentals ranging from recruiting eligible patients to capturing data at various timepoints according to a prespecified protocol. None of these steps go away in the digital era, but the tactics for getting them done are undergoing truly revolutionary change.,
Digital technologies provide new channels for accessing target patient populations. In connecting with patients outside of traditional clinical settings, we are able to recruit patients for studies much faster, discover patterns across segments, and support patients in their everyday lives.
Equally important, the benefits are not limited to the number of patients recruited or the improved efficiencies of the process. Digital technologies fundamentally expand the datasets we can use to quantify outcomes in the real world — That means we can more accurately correlate outcomes with patients’ daily lives and behaviors.
2. Collection of Novel Real Life Data
The most important expansion of our clinical development data universe is arguably our new ability to continuously and passively measure patient behaviors upon informed consent. For example, tracking sleep, physical activity, social media activity, and wireless sensor data all enhance the context available for analysis.
In the near term, this new information can shed light on the efficacy-effectiveness gap between phase III trial results and what happens in post-launch settings. When combined with medical information including EHRs, claims data, and genomics, this new understanding of how patient behaviors drive health outcomes creates a direct path to precision medicine solutions.
3. Quantification of Real Life Outcomes
Gathering novel data from more people, more efficiently, is only helpful if it leads to scientifically valid conclusions that prove outcomes. We have always known that patient behaviors directly influence symptomology and disease progression/regression in many therapeutic areas, but quantifying the impact has traditionally been an elusive goal. That has changed.
Therapeutic areas that are benefiting most from this new approach are those where patient behaviors outside the clinic walls disproportionately impact health outcomes. In our experience to date, the use cases for quantifying how real life patient behaviors drive health outcomes are now quite broad and accessible. For example:
Pharma Company Puts It All Together to Quantify Impact
Connecting with patient populations, collecting continuous behavioral data, and quantifying health outcomes on large behavior datasets all benefit from digital tools — but the greatest benefit is realized when the three tactics are combined.
For example, a top global pharma company worked with Evidation Health with the goal of improving patient adherence to medication and lifestyle modification in the diabetes market. The project started by connecting with 300,000 patients and segmenting that population into clusters. The platform collected real life behavioral data across well over 6 months of observation and linked relevant behavioral activity (diet, sleep, etc.) to medical adherence.
Ultimately, this enabled a top global pharma company to quantify health outcomes and leverage behavior-driven insights for dynamic intervention targeting.
The Ecosystem for Quantifying Real Life Outcomes
To fully realize the potential of these new approaches for measuring real life health outcomes, several constituencies have to come to the table. First and most importantly, are patients themselves, who must be able to access their own medical data for integration with their behavioral data for participation in studies.
Second, industry players have a critical role for providing the enabling technology for direct patient participation and multi-channel data collection, at scale, outside brick and mortar walls. Finally, public entities such as NIH and the academic medical institutions that drive translational research collaborations and clinical care innovations in the U.S. have an important role.
We might not have imagined a decade ago that we’d be here so quickly. But suddenly we find ourselves able to quantify health outcomes like never before, in settings we never imagined, in populations we might not have ever reached—in their real lives. This is indeed an idea whose time has come.
 Kuehn BM. Is There an App to Solve App Overload? JAMA. 2015;313(14):1405-07.
 Rosa C, Campbell AN, Miele GM, Brunner M, Winstanley EL. Using e-technologies in clinical trials. Contemp Clin Trials. 2015;45(Pt A):41-54.
 Juusola JL, Quisel TR, Foschini L, Ladapo JA. The Impact of an Online Crowdsourcing Diagnostic Tool on Health Care Utilization: A Case Study Using a Novel Approach to Retrospective Claims Analysis. J Med Internet Res. 2016;18(6):e127.
 Kumar S, Oley L, Juusola JL. Efficiency of Virtual Recruitment Methods for Broad and Specific Study Populations. 38th Annual North American Meeting of the Society for Medical Decision Making, October 23 – 26, 2016.
 Pourzanjani A, Quisel TR, Foschini L. Adherent Use of Digital Health Trackers Is Associated with Weight Loss. PLoS ONE 11(4): e0152504.
 Rock Health. The Emerging Influence of Digital Biomarkers. 2016. Available at https://rockhealth.com/reports/the-emerging-influence-of-digital-biomarkers-on-healthcare/.
Originally posted on LinkedIn