Medidata AI Research Review Vol 1 Issue 1
Welcome to the Medidata AI Research Review. Our team has had a busy Q1 attending conferences and speaking about the latest research and improvements surrounding clinical trials using AI. Here’s what our team has been up to:
Journal of Biopharmaceutical Statistics:
Utility of propensity score-based Bayesian borrowing of external adult data in pediatric trials: A pragmatic evaluation through a case study in acute lymphoblastic leukemia (ALL) (Jan 2023)
A fully powered randomized controlled cancer trial can be challenging to conduct in children because of difficulties in enrollment of pediatric patients due to low disease incidence. One way to improve the feasibility of trials in pediatric patients, when clinically appropriate, is through borrowing information from comparable external adult trials in the same disease. We examine the utility of propensity score matched mixture and power priors in bringing appropriate external adult efficacy information into pediatric trial efficacy assessment, and present considerations for scaling fixed borrowing from external adult data.
JCO Clinical Cancer Informatics - An American Society of Clinical Oncology Journal:
Historic Clinical Trial External Control Arm Provides Actionable GEN-1 Efficacy Estimate Before a Randomized Trial (Jan 2023)
Medidata and Imunon Corporation—a clinical-stage company focused on DNA-based immunotherapy and next-generation vaccines—published their findings on the use of a Synthetic Control ArmⓇ (SCA) in a completed Phase Ib dose-escalating study of GEN-1 in the neoadjuvant treatment of patients with Stage III/IV ovarian cancer (the OVATION 1 Study).
PMWC 2023: Methods to Accelerate Technical and Regulatory Success (Jan 2023)
Insights generated from patient-level historical clinical trial (HCT) data, or linking contemporaneous patient-level clinical trial data to real world data (RWD), has demonstrated meaningful improvement to sponsors' better asset strategies, optimizing trial operations, and generating evidence for regulators and payers. These insights have the potential to de-risk drug development by accelerating timelines, increasing patient centricity, lowering costs, and ultimately improving probability of regulatory success.
EHA 2023: Cooccurrence patterns of CRS and ICANS in patients undergoing autologous CD19-targeted CAR T-cell treatments (Jan 2023)
Colleagues from Medidata and Stanford presented findings where ICANS occurrence and severity appears to be driven by CRS occurrence.
However, while CRS incidence can be decreased with a preemptive treatment with IL6R blockade or corticosteroids, these treatments do not directly target pathways underlying ICANS and therefore doesn’t lead to preventing incidence of ICANS. ICANS management requires a distinct therapeutic approach.
Phuse US Connect 2023: A Road Map to standardize Historical Clinical Trials for Synthetic Control Arm (Feb 2023)
Randomized clinical trials cannot always be accomplished due to unique circumstances, such as rare or pediatric diseases and ethical reasons in settings where the control therapy is inadequate. External controls, created from patient level data from Historical Control Trials (HCT) in the form of Synthetic Control Arm (SCA) can help fill the gap where randomized controls are not feasible and aid in critical ‘Go-No Go’ decisions.
Creation of an SCA is complex, requiring attention to data privacy, aggregation, de-identification, and methods to address gaps in access to CRF annotations, protocols or SAPs. We shared how we have overcome these challenges including creation of ‘Study Summary Report’, our take on ‘annotated CRF’.
Synthesize 2023, powered by gretal: Synthetic data revolutionizing clinical trial data collaboration and research (Feb 2023)
Synthetic data is revolutionizing AI across industries where the impact of this technology has resulted in enhancing training data resulting in building better machine learning models, solving problems such as under-representation, lack of diversity and limitations in sample size. It has been predicted that by 2030, synthetic data will completely overshadow real data, a prediction that has a real impact on how we build current and future machine learning technology.
ACC.23: Enhancing Clinical Trials By Linking Them to Real-World Data (March 2023)
Patients who participate in clinical trials (CTs) continue generating a wealth of real-world data (RWD) before, during, and after a trial through routine interaction with the healthcare system. RWD, including insurance claims data, electronic health records (EHR), and disease registries, contain valuable information about trial patients’ clinical events, diagnosis, procedures, and health resources utilization.
However, the disconnect between trial data and RWD delays access to critical data, ultimately becoming a detriment to patients. We observed a high success rate in obtaining IRB approvals for trial linkage, seamless integration into standard EDC systems, easy adoption by clinical site investigators/staff, and high patient consent rates for linkage that reached up to 94%.
ASCO Education Podcast - Cancer Topics: Racial Disparities in Clinical Trial Participation (Mar 2023)
Clinical trials are essential to progress in medicine, but racial and ethnic minorities are frequently underrepresented in such studies. In this ASCO Education podcast episode see how diversification of clinical trials contributes to health equity, barriers to participating in clinical trials, and what clinicians and trial sponsors can do to improve participant diversity in clinical trials.
Awards & Events
Medidata is the 2022 Innovation Award Winner of the Reagan-Udall Foundation from the FDA Award.
Medidata Link Honored for Bridging the Gap Between Clinical Trial and Real World Data, Advancing Regulatory Science and Improving Public Health.
Medidata received the Real-World Evidence Best in Stream Presentation awarded by Phuse 2023 Conference.