The integration of real-world data (RWD) into protocol feasibility and site selection has emerged as a clinical trial game-changer in recent years. Traditionally relying heavily on data from carefully controlled environments, which may not always reflect the diversity and complexity of real-world patient populations, biopharmaceutical organizations are now looking to RWD and the impact it can have on the design of protocols and their decisions about site selection — resulting in more efficient, inclusive, and impactful trials.
Improving Protocol Design with RWD
Protocol design is the backbone of any clinical trial, outlining study objectives, patient selection criteria, endpoints, and procedures. One of the most significant challenges in clinical research is ensuring that trial participants are representative of the population for whom the treatment is intended.
It’s no secret that clinical trials have suffered from underrepresentation of specific demographic groups, including older adults, racial and ethnic minorities, and patients with comorbidities. This limited representation can undermine the generalizability of trial results.
RWD offers a pathway to overcome these limitations. By analyzing large and diverse patient populations, researchers can gain insights into disease epidemiology, treatment patterns, and unmet needs across different demographic groups. These insights can inform the development of eligibility criteria that are more inclusive and reflective of the patient populations seen in clinical practice.
Another key advantage of RWD is its ability to streamline feasibility assessments during protocol design. By analyzing data from electronic health records (EHRs) and claims databases, sponsors can assess the likelihood of enrolling enough patients who meet the trial’s criteria. This reduces the risk of under-enrollment, a common challenge that can delay trial completion and increase costs.
Maximizing Site Selection with RWD
Site selection is another critical aspect of clinical trial planning, significantly impacting both the speed and success of a trial. Oftentimes, site selection is based on a site's past performance in similar studies, relationships with investigators, or geographic convenience. However, this approach can be inefficient and may overlook sites that could potentially enroll large numbers of eligible patients.
RWD allows for a more data-driven approach to site selection. By examining data from EHRs, registries, and claims databases, sponsors can identify sites where eligible patients are already being treated. This strategy can improve enrollment rates by selecting sites with access to a larger pool of patients who meet the trial's criteria.
For instance, if a RWD analysis reveals that a certain healthcare organization (HCO) has a high concentration of patients with a specific condition or comorbidity, sites within that HCO where these patients are receiving care can be prioritized for inclusion in the trial.
By analyzing past RWD on treatment outcomes and adherence patterns, sponsors can assess the quality of care at potential sites and choose those with the highest likelihood of successful trial execution.
The Intersection of RWD and Artificial Intelligence (AI) Technologies
By incorporating AI technologies like machine learning (ML) into RWD, researchers can gain significantly deeper insights and unlock new possibilities for analysis, essentially creating a much more advanced and impactful way to utilize RWD compared to traditional methods.
ML-trained predictive models can analyze diverse RWD to identify clinical patterns indicative of candidate eligibility for a particular trial. In aggregate, these patterns inform a scoring algorithm that assesses participant pools both now and in the future. Based on their clinical factors, patients could progress into a certain outcome where they might become a candidate for that trial in the near term. By tracking those patients with real-time data, as soon as their condition changes, sponsors can then work with the site to recruit them.
The Road Ahead
The potential of RWD to revolutionize clinical trial protocol design and site selection is undeniable. As healthcare data becomes more standardized and accessible, the role of RWD in clinical research will continue to grow. With advances in data analytics and ML, RWD can be leveraged to make trials more adaptive, patient-centric, and efficient.
By embracing a real-world approach, researchers can design more pragmatic trials that truly reflect the complexity of modern healthcare. As a result, clinical trials will not only become more efficient and cost-effective but also more meaningful to the patients they are meant to serve.
For more, get a complimentary copy of the TriNetX clinical trial playbook, Beyond Tradition: Rethinking Clinical Trials with Real-World Data.