The breadth of healthcare data available to researchers is continuing to expand. With more insights to dive into, machine learning capabilities have more potential than ever to enable clinical trial sponsors and study teams to make case-by-case decisions about trial design and execution and better predict outcomes for individual trials. However, sponsors should note that ML predictive algorithms can power a wide range of development activities, including risk-based monitoring, ongoing medical monitoring, disease detection, biomarker identification, portfolio optimization and electronic trial master file document language translations. Highlighted further below are several specific examples of the use of ML to enhance outcomes in drug development.
 
To get medical treatments to market faster while successfully working through regulatory updates and other challenges, sponsors are increasingly relying on innovative approaches and technology solutions to overcome long-standing challenges in drug development as well as new ones brought about by the pandemic. As such, sponsors are equipping their solutions toolboxes with machine learning capabilities to enhance predictive modeling activities that can help improve trial operations at any stage of development.
 
Data-driven trial decisions
We know that even prior to COVID-19, the clinical development landscape has increased in complexity in recent years. But the global pandemic brought long-standing challenges in clinical trials to center stage — making sponsors face an influx of difficult choices as they looked for ways to start trial planning or maintain successful trial continuity at the height of COVID, now and in the future. Those who have access to ML-based technologies and related expertise have been able to build effective algorithms to take a deeper look into the predictors that lie in the expansive level of human data insights available and optimize various stages of trial operations.
 
Trial outcome predictions
A poorly designed study or a sub-optimally positioned molecule can make or break the success of a trial and create additional costs and inefficiencies for sponsors. Leveraging healthcare data sets, ML tools can help assess and optimize compound positioning as well as optimize primary and secondary endpoints in study design. Ultimately, through better study design, sponsors and study teams are setting themselves up for more realistic outcomes and potentially less time spent on protocol development and related amendments. 
 
For sponsors who must consider abandoning or deprioritizing a treatment based on failure to meet Phase 2 or 3 endpoints, these technologies can help responding sub-groups or even completely repurpose the molecule, providing a new approach to portfolio rescue. This opportunity is evidenced by the explosion of companies using AI to identify portfolio inefficiencies.
 
Site selection
To highlight how we can use modern data science to drive better site selection, think about how critical it was at the start of the pandemic for sponsors to determine sites where there was access to enough target patients who met inclusion/exclusion criteria, especially given limited site accessibility and the heightened focus on patient safety during site visits. 
 
Decentralized trial solutions, such as telehealth and mobile research nurses for at-home labs and other procedures, greatly helped with remote patient participation. However, for site teams and staff, it was still critical to mitigate risks of increasing cost and time for patient recruitment, especially with limited staff, and potential failure all together.
At IQVIA, we aimed to decrease these risks by using ML-based algorithms based on real-world evidence, including claims data and COVID-19 case surveillance data, to map patient populations and identify sites with the highest recruitment potential as well as to provide insights into what recruitment strategies may have been best for the study and patients at hand. This helped sponsors potentially fine tune their strategies and focus on the right sites, thereby reducing the number of sites involved and the related risk of under-enrollment. 
 
Just as importantly, using these ML models can help locate sites that will improve patient racial and ethnic diversity in trials. IQVIA’s methodology to use machine learning to better recruit diverse patient populations focuses on reviewing trial protocol details, such as the condition, trial site features, past performance, claims data and patient demographics at the trial sites, to rank sites accordingly. The ML-based algorithm learns to associate these features as the desirable traits for trial sites and then extract or pinpoint optimal trial sites. 
 
Patient population discovery
By mining granular healthcare data that is de-identified at the source (e.g., retail pharmacies, insurers, electronic medical records), healthcare technology experts can apply ML-based algorithms to better predict patient segments of interest. By helping to identify patients who are undiagnosed, untreated, or at-risk for the studied disease or condition, the resulting improved outcomes help ensure that the right therapies reach the ideal patients. 
 
Machine learning models make it possible to examine patterns in patient electronic health records that may not be detected through more traditional approaches. One specific way technologists do this is to identify and use a sample group or “training cohort” of patients who exhibit the specific characteristics of interest to train the ML model and then apply the process to the full data set to identify patients predicted to display those same characteristics. For some with rare diseases, it can take years to be diagnosed. By the point of diagnosis, there may be significant health deterioration and reduced quality of life. It is a prime example of how machine learning can help understand complex patterns, treatments, and more to make connections toward patient identification earlier. 
 
Humanizing decision intelligence 
As industry experts work to enhance ML solutions to accommodate the needs of tomorrow’s drug development, it is critical to first address any roadblocks to further use. It is safe to say that there is a bit of skepticism among clinical trial professionals, investigators and others in the industry about bringing in machine learning solutions to enhance ways of working they are comfortable with and know to be effective. It is the job of data scientists and technologists to have realistic expectations of the end-user and help alleviate their skepticism by considering the human side of our work when developing tech-enabled solutions. Users of ML-based predictive algorithms and their recommendations are people, and it is critical to keep in mind that people do not make decisions like machines. Leaning into the psychology of decision making and how decisions are made and creating a comfortable user experience can help make decisions made by using ML-based predictors more palatable. By applying decision intelligence, technologists aim to understand the how’s and why’s of users’ decisions so they can augment approaches to ensure insights needed to make optimal decisions are used. Decisions made in clinical research are critical and potentially life-saving. It’s very important to help ensure decisions are well-informed for the best outcomes possible. 
 
From creating efficiencies to enhancing patient-centricity, predicting complex trial outcomes and more, effective ML-based algorithms and applications are allowing clinical trial sponsors to navigate a complex landscape with smarter decisions across the spectrum of trial activities. As key industry stakeholders better understand the varying benefits of these predictive-outcomes solutions, the potential for further use in vital drug development will get stronger by the day. That said, it is equally important for those on the forefront of development to help ensure growing acceptance of these solutions by always taking the human factor of decision making — even in those decisions involving ML — into consideration.