Oncology Therapy-Focused RACT Emerges

In 2015, we reported on how RACTs were moving from Excel-based forms into cloud-based technology applications that leverage workflows in RACT development, and in 2017 we explained, in academic settings, how professionals with minimal experience in clinical trial risk management can partake in risk management plan development through leveraging RACT technology. Newest revelations suggest Risk Assessment Categorization Tools (RACTs) are now becoming therapeutic area-specific, as an oncology-based risk library (OncoRACT) is now surfacing.

The Materialization of OncoRACT

The OncoRACT library has emerged because the existing universal RACT library (i.e., TransCelerate RACT) does not cover areas critical to oncology, especially pertaining to subject safety risks, impact of staff-turnover, oncology-specific outcomes, and subject recruitment. For example, OncoRACT safety risks include drug tolerability, impact of cancer death rates on study outcomes and drug interactions; study complexity risks include subject burden, and biomarker collection; and endpoint risks include oncology primary and secondary endpoint collection, which can focus on survival outcomes, to name a few. 

Use of MCC’s Methodology

OncoRACT has leveraged risk assessment methodology from Metrics Champion Consortium, which evangelizes the event, cause, impact approach. This process allows study teams to measure risk probability, enables the planning of risk mitigation actions, and empowers impact measurement properties (i.e., high, medium, low impact). 

Additionally, utilizing this methodology facilitates a dynamic technique towards risk identification and mitigation by not only enabling qualitative risk conceptualization, but also transforming those risks into quantifiable risks, which are compatible with KPI/KRI generation and implementation in risk-based monitoring (RBM) plans. Furthermore, this approach supports risk categorization, as study teams can easily visualize critical and noncritical study risks.

Artificial Intelligence in RACT

The challenge with any manual process involves in efficiency and repetition. OncoRACT uses artificial intelligence (AI) to suggest qualitative risk identification for specific RACT categories. The deep machine learning algorithm suggests the most commonly used and most relevant risks that other study teams within a sponsor organization have used in previous RACTs. This approach not only improves efficiency of qualitative risk identification, but also incorporates perspectives and previously explored hurdles, hence, improving risk identification efficiency, risk assessment quality, and saves project teams time with setting up their RBM plans.

Efficiency in RBM Planning: Risk Mitigations

OncoRACT has taken risk management planning and convenience to another level by encouraging study teams to plan risk mitigations for identified study risks. This includes functionality to create associations between other study risks, identifying mitigation goals and actions, and producing timeline review settings to encourage ongoing risk mitigation review. Study teams can, correspondingly, leverage this system as an eRBM plan, and integrate the plan into their EDC systems to access notifications, should KPI/KRI deviations occur.

Summary

The evolution of OncoRACT demonstrates that RBM and risk-based quality management (RBQM) methods are now targeting therapeutic area-specific risks and including novel technologies (i.e., AI) are improving qualitative risk identification and quantitative risk transformation. “OncoRACT was developed because the risks of oncology studies are unique compared to other therapeutic indications. Standardizing the risk assessment process and enabling study teams (especially those with lower experience) to address critical risks help them better navigate study operations and mitigate risk management in oncology trials,” said Johann Proeve, Chief Scientific Officer at Cyntegrity. This movement demonstrates that TransCelerate RACT can be modified to address other therapeutic indications, and it is likely that we will see the emergence of therapeutic-specific RACTs that focus on areas such as diabetes, medical devices, and cardiology.

Moe Alsumidaie, MBA, MSF is Chief Data Scientist at Annex Clinical, and Editorial Advisory Board member for and regular contributor to Applied Clinical Trials.