Precision patient finding is an evolving field that is growing in line with the demands of precision medicine and rare disease research. Unlike traditional patient recruitment methods, it harnesses technologies such as data analysis and advanced analytics, and utilizes comprehensive patient data (including genomic profiles) to rapidly identify groups of patients who have an increased likelihood of study eligibility and enrollment. Here we’ll explore some of the key elements of precision patient finding and how they interlink.
Genetic and clinical profiling are core components of precision patient finding, enabling researchers to utilize detailed, comprehensive datasets to identify highly relevant patients and match them with appropriate research opportunities.
This advanced profiling involves using electronic health records (EHRs), genetic data (whether through providing sequencing or harnessing pre-existing genetic data) and health and lifestyle factors to rapidly establish if a patient is or is not a likely fit for a given study. Not only does this help reduce the cost and timeline of patient finding, but it helps identify the individuals who are most likely to benefit from the outcomes of the research.
Artificial intelligence (AI) assisted patient finding and trial matching has the potential to sift vast volumes of patient information, including genetic data and EHRs, to identify relevant individuals based on specific eligibility criteria. Such technologies enable identification of highly relevant patients at a speed which is not achievable with a manual, labor-intensive approach. Vitally, these technologies also enable a high level of accuracy when it comes to patient selection, trial matching and enrollment. For example, an Australian study published in 2020 was able to demonstrate a 91.6% accuracy for overall eligibility assessment for a lung cancer clinical trial when using AI technologies to identify patients.
AI is also helping to power tailored recruitment strategies by using predictive analytics to forecast behaviors, treatment responses and potential risks, contributing to creating trials which ensure higher levels of safety, efficiency and reduced risk of human error. For example, AI analytics softwares are able to identify high-risk patients who may be susceptible to complications (such as comorbidities or interaction of medications), and who are therefore unsuitable for participation despite initially appearing to be a good match with eligibility criteria.
Patient registries collect standardized information and patient data on specific diseases and conditions (such as the American Heart Association’s Get With The Guidelines registries). Registries often include information such as medical history, lifestyle data, treatment plans and patient outcomes.
Access to patient registries represents a key component of precision patient finding, as these databases provide a source of systematically collected, uniformly formatted data. Such data is highly searchable and ideal for the application of AI-assisted analytics queries. The systematized, longitudinal nature of patient registries provides high quality, reliable data points which enable increased accuracy and efficiency when it comes to patient identification and clinical trial matching. Some registries even include real-time or near real-time updates so that, when new information about a patient becomes available, the entry in the registry can be updated immediately - once more contributing to the accuracy of patient-finding efforts.
Now more than ever, healthcare providers (HCPs) and patient advocacy groups play a vital role in precision patient finding programs. Such groups provide a direct connection with large networks of patients living with specific conditions and who are highly motivated to support research efforts - as patients stand to directly benefit from therapeutic advances.
HCPs and advocacy groups can directly raise awareness of clinical trial opportunities with a high degree of efficacy and impact, as they represent trusted voices within patient communities. These voices are vital for increasing understanding of the benefits and potential of clinical trials, as well as willingness to participate and share data with researchers.
The contribution of patient advocacy groups also helps to reduce trial termination and drop out rates, as patient-informed recruitment and trial design take into account the specific needs of individual communities. A 2018 meta-analysis of 26 studies found that public and patient involvement “modestly but significantly increased the odds of participant enrollment” in clinical trials, especially in those that included input from people with lived experience of the relevant condition.
Vitally, such partnerships also support diversity of recruitment, helping to increase enrollment of individuals from underrepresented and marginalized communities and populations, ensuring they are effectively represented in clinical trials and research.
Precision patient finding is disrupting traditional recruitment approaches by leveraging new analytics technologies, unified data repositories, and partnerships with advocacy organizations to create a decentralized approach that streamlines patient finding efforts. Combined, these factors create a process that is not only significantly faster and more cost effective, but which also offers a high degree of efficiency and accuracy, increased patient engagement, and reduced chances of trial failure or termination.
To learn more, download our whitepaper: