Artificial intelligence (AI) technology, combined with automatically collected big data hold the potential to solve many key clinical trial challenges. These include increasing trial efficiency through better protocol design, patient enrollment and retention, and study start-up, which were each named as prime candidates for improvement by nearly 40% of sponsors in a recent ICON-Pharma Intelligence survey.1 With clinical trials accounting for 40% of pharma research budgets2, sponsors need new ways to accelerate timelines and reduce costs.
Data-driven protocols and strategies powered by advanced AI algorithms processing data automatically collected from mobile sensors and apps, electronic medical and administrative records, and other sources have the potential to significantly cut trial costs. They achieve this by improving data quality, increasing patient compliance and retention, and identifying treatment efficacy more efficiently and reliably than ever before.
As a result, fewer patients are needed to generate statistically significant study data, and fewer patients drop out. Adopting these novel innovations does present challenges, with developing analytics that generate actionable clinical insights from big data high among them. Nonetheless, there exists significant potential for transforming trials -- for example, by potentially uncovering new biomarkers and routes to new therapeutic options in masses of data that may not be found by humans alone.3
Advancing clinical trials
The AI transformation of clinical trials starts with protocol development. In traditional trial models, clinicians often develop protocols based on past expertise, relying on repetition of previous trial designs or even unproven strategies. As a result, enrollment criteria often specify combinations of clinical inclusion and exclusion criteria that can make it difficult to find qualified subjects. Poor protocol design can slow enrollment and lead to poor patient retention, driving up trial costs or even dooming a program.
Applying AI to big data has the potential to shape insights from masses of real-world data (RWD) into protocol designs. Actual information from real patients can be used to assess and develop trial objectives, inclusion and exclusion criteria, endpoints and procedures that will work in the real world.
AI and big data help gather and monitor data more accurately as well. In the past, researchers relied heavily on verbal or written evidence from patients at clinical visits and direct clinic observations to assess patient progress. This subjective evidence can be unreliable and not provide enough information for analytics and decision making. Moreover, frequent clinic visits can add to patient burden, causing dropouts.
Gathering real-time, real-world patient data with wearable devices, on the other hand, can help produce consistent, objective evidence of actual disease states and impacts of treatment symptoms. This data includes heart rate, blood pressure and movement collected 24/7. It is much richer and more detailed than data collected in the clinic, making it much more reliable.
AI analysis of live remote data also can detect when patients may not be compliant, allowing clinical personnel to intervene before a patient’s data must be excluded. Sponsors already recognize big data can help solve these kinds of problems -- 28% of the ICON-Pharma Intelligence survey respondents reported that big data will help clinical trial operations.
Engaging patients and finding new insights
AI-enabled trial management systems can help keep patients engaged. Technologies such as telehealth and digital reporting apps as well as wearables, allow for real-time engagement and communication, and support patient-centric trials. Patients can send feedback on treatment symptoms and manage medication intake, and can share information with researchers, reducing or eliminating the need for patients to travel to sites, which increases patient adherence and compliance. Moreover, reducing the frequency of clinical visits can lower site costs and improve the quality of patient experience, for example by reducing the number and length of clinic visits.
AI analysis of RWD-generated by mHealth and wearables not only allows for the monitoring of objective high-quality data in real-time as patients live their lives, but also helps find relationships among masses of data not possible using human interpretive skills alone. With advanced analytics, researchers can gain deeper insights into how a treatment affects symptom progression or quality of life. Moreover, expertise in machine learning can help to develop novel endpoints.
AI analyzing big data will even generate new insights into disease processes that could open up unsuspected new treatment avenues. It also will help identify patients most likely to respond to specific treatments based on their individual characteristics and responses to previous treatment. This will reduce the risk of drug development by creating predictive models that are much more powerful, increasing chances that a given therapy will work in clinical trials. More importantly, it will bring more innovative products to patients sooner, transforming not only clinical trials, but also the health and lives of millions of patients as well.
To learn more about the role of AI, big data and mobile sensors in transforming clinical research, download our whitepaper ‘Improving Pharma R&D Efficiency.’
1 Transforming Clinical Trials Industry Survey. ICON-Pharma Intelligence. November 2017.
2 Nuttall, Aidan. RDP Clinical Outsourcing: Considerations For Improving Patient Recruitment Into Clinical Trials (2012). http://vertassets.blob.core.windows.net/download/64c39d7e/64c39d7e-c643-457b-aec2-9ff7b65b3ad2/rdprecruitmentwhitepaper.pdf
3 Brazil, R. Artificial Intelligence: will it change the way drugs are discovered? The Pharmaceutical Journal, December 7, 2017. https://www.pharmaceutical-journal.com/news-and-analysis/features/artificial-intelligence-will-it-change-the-way-drugs-are-discovered/20204085.article