Where Two Technologies Intersect Marks a Clinical Research Turning Point
Contributed Commentary By Nick Moss
October 8, 2020 | The global AI healthcare market is projected to hit $13 billion by 2025. And, according to a survey of more than 300 biopharma and medical device development executives, nearly 80% said they plan to use, or are using, AI to improve R&D performance. At the same time, the COVID-19 pandemic has accelerated the industry’s adoption of Decentralized Clinical Trials (DCTs). More than 82% of clinical trial professionals polled this spring stated that their organizations are decentralizing elements of studies and incorporating some virtual trial technologies as a result of the pandemic.
As these two burgeoning technologies continue to mature, there is an opportunity for transformation in clinical research where AI and DCTs intersect. Already, life sciences companies that are marrying DCT methodologies with AI in innovative ways have reshaped workflows across the clinical lifecycle, from trial design and patient recruitment to evidence generation—and are seeing striking decreases in both the time and cost of clinical studies.
Here is where they meet. AI is fueled by massive amounts of data, and there are at least 25,000 clinical trials offering a form of open-source data. DCTs fuel AI engines, too, since they inherently capture real-world data from diverse patient populations more representative of the real world. Using AI, companies can take advantage of all this rich data to optimize patient recruitment, increase patient retention, reduce timelines, and maximize study results in future trials.
DCTs also reduce the time and cost of clinical studies by expanding patient access and retention by allowing patients to participate safely and conveniently in their homes. Further, DCTs minimize geographic costs and other barriers that can improve the diversity of participants. The net effect is an improvement in data quality as site-based transcription is eliminated plus an increase in efficiency for patients, sites, and study teams.
Together, AI and DCTs can be a powerful force to improve three crucial areas of clinical trials—trial design, patient recruitment, and evidence generation.
Machine Learning Customizes Trial Designs
While there are various applications of AI, one of the most disruptive is machine learning, where the computer uses complex algorithms to learn and improve its performance based on experience, rather than being continually programmed. It can significantly improve trial design in a host of ways—from identifying the ideal sample size to what data should be experimentally generated, to target validation and trial execution. Machine learning quickly finds patterns and makes predictions about future state.
Vaccine research provides an example of AI’s impact on trial design, especially in light of the race for a COVID-19 vaccine. As the vaccines for COVID-19 progress to late stages, AI can help identify signatures of vaccine response. Similar to the adoption of viral load as a surrogate endpoint, which drastically reduced HIV trials from four years to six months, understanding immune signatures of vaccine response can accelerate vaccine trials.
Recognizing the critical role of adjuvants in the efficacy of vaccines, a 2019 malaria vaccine study by a group from U.S. Army Medical Research and the Walter Reed Army Institute demonstrated that the combination of machine learning with immune-profiling could most likely identify adjuvant-specific immune responses that can serve to inform decisions on adjuvant selection. The method can also enhance vaccine safety by providing valuable insight regarding which immune profiles are associated with reactogenicity.
In addition to improving safety and efficacy, machine learning can expedite product development. For example, a 2016 collaborative effort of the Georgia Institute of Technology, Emory University, and the Centers for Disease Control and Prevention utilized DAMIP, a machine learning method, to predict the ability of a vaccine to provide effective immunity within just one week of administration. More recently, a group at the University of Michigan employed Vaxign (reverse vaccinology tool) and a corresponding machine learning tool to identify the most appropriate targets for a COVID-19 vaccine.
Not only has machine learning been deployed in other vaccine trials to understand critical success factors for COVID-19 vaccine trials, it has also been employed to identify sites with non-COVID-19 trials that would benefit most from decentralization. This data has proven essential to proper planning and COVID mitigation. Machine learning has even predicted future outbreaks, providing key insights into which future trials and sites would be most impacted and best suited for DCTs.
Expediting the Speed and Diversity of Patient Recruitment
Patient recruitment remains one of the largest obstacles in drug development. Broad marketing campaigns are expensive and largely ineffective since it is nearly impossible to identify participants that meet clinical criteria at the right time and in the right place. For rare diseases specifically, it is difficult to meet minimum patient enrollment targets within specified timeframes.
The diversity of trial participants is also a challenge that has generated a significant effort in the industry. Currently, trials do not adequately represent the population with respect to gender, race or ethnicity. For example, Nature published a 2018 study showing that while African Americans comprise 13% of the U.S. population, they only make up 5% of clinical trial participants.
The combination of AI and DCTs is key to overcoming bias challenges because, together, they can advance the identification, enrollment, and participation of underrepresented groups by removing selection bias, geography, transportation, and barriers to participation. AI can also better identify candidates who are most likely to respond to the intervention and even project which patients are least likely to drop out for improved retention rates. For instance, some organizations are using advanced neural networks and Bayesian algorithm-powered tools to find candidates.
Machine learning applied to clinical data, like that maintained in electronic health records (EHRs), can identify regions and individuals with higher pre-recruitment probability for screening success. For instance, Mount Sinai Hospital in New York applied an unsupervised deep learning method to EHR data of approximately 700,000 patients to determine patient representations that provide enhanced clinical predictions. The model tested over 76,000 patients, encompassing 78 diseases. It predicted future diseases from cancer to schizophrenia and showed consistently better results than other models.
These AI applications lay the groundwork to identify research participants at the most critical clinical juncture. Once potential participants are identified, the use of DCTs removes geographical and transportation barriers to screening and participation to speed study start-up and—long-term—improve participant retention and diversity.
Real-Time, Real-World: Enhancing Data Quality in Evidence Generation
DCTs require digital avenues for evidence generation in ways that traditional clinical trials do not. Evaluating the effects of an intervention requires digital endpoints as well as systems that can autonomously interpret physiologic data to detect side effects and monitor patient safety. Therefore, DCTs collect more data that require efficient and accurate analysis and management. AI can discriminate signal from noise and plays a critical role in the development of such digital biomarkers.
It is widely known that machine learning-generated biomarkers from preclinical datasets are crucial to drug discovery. Organizations are now developing cloud-based machine learning systems to identify new digital biomarkers. These informatics can also be used for patient identification, feasibility, and data source extraction. Data can be captured from smartphone sensors, surveys, devices, lab data, and more. For instance, companies monitor gait stability, fatigue, and cognition levels.
The value of digital biomarkers stretches beyond indicators of disease to applications in digital therapeutics. Digital therapeutics can shape patient behavior and treat various conditions through digital technologies. Using machine learning and other AI approaches with digital therapeutics to monitor and predict data of patient symptomatology creates digital biomarkers, resulting in a feedback loop which lends itself to precision medicine. DCTs provide for a much broader application of this method, culminating in voluminous data that makes the AI engines even smarter.
For example, in the trial setting, digital biomarkers can predict treatment response from a digital behavioral intervention at the participant level. The combination of AI and digital therapeutics also enable enhanced real-time clinical measurements without the bias of patient recall. In addition to monitoring patient symptoms and predicting outcomes, they allow for dynamic adaptation to individual needs, goals, and lifestyles through course correction—particularly important for patients in rural or underserved areas.
Necessity Breeds Clinical Innovation
The COVID-19 pandemic has driven the fastest adoption of technology and innovation in clinical trial history. As AI and DCT intersect, expect giant leaps of improvements particularly in trial design, patient recruitment, and evidence generation. The technologies’ continued maturation will expand its use across all stages of the patient journey, and ultimately lead to incredible breakthroughs in personalized medicine to cure cancers and rare diseases.
Nick Moss is a computer scientist who has been passionate about data science and machine learning for over 10 years. He previously worked in finance and investment banking, creating automated stock trading and big data systems and has also worked in high-performance computing on some of the largest supercomputers in the world. At Medable, Moss leads the data science team to create innovative and scalable technological solutions to promote increased efficiency in clinical trials. He can be reached at firstname.lastname@example.org.