FASTER, BETTER AND CHEAPER CLINICAL TRIALS WITH REAL WORLD DATA (RWD)
SYNTHECTIC CONTROL ARM
OPTIMAL TRIAL DESIGN
POWERED BY OSCAR ML©
Using the power of a statistically rigorous machine learning analytical platform OSCAR ML© through REAL-WORLD & PREVIOUS STUDY DATA we
- Generate reliable synthetic external data to be used as a comparator of a single arm trial.
- Identify predictive parameter(s) and/or biomarker(s) in treatment populations who are experiencing stronger outcomes or better safety.
- Ultimately we help to obtain meaningful results even in small patient populations, particularly in the rare disease and oncology space and in better designing data-driven adaptive trials, focusing on those patients most likely experience positive outcomes and improved patient safety for a successful regulatory approval.
Challenges + Opportunities
The drug development process faces a triple challenge:
- rising complexity;
- rising costs;
- growing pressure on drug prices.
Artificial intelligence and other analytics tools are accelerating drug discovery, diagnosis, and other aspects of healthcare. Expedited regulatory pathways are helping shorten new drugs’ path to patients. Still, they then post-marketing studies to confirm efficacy and safety are required.
The challenges and opportunities in drug development
Clinical Trials remain the most expensive, risky, ethically debatable, and time-consuming aspect of drug development. Therefore, more improvement is needed in clinical trials.
The challenges in clinical trials
Randomized controlled trials are the gold standard to investigate efficacy and safety of new treatments In certain settings, however, randomizing patients to control may be difficult for ethical or feasibility reasons. Therefore we should consider the possibility to use relevant individual patient data derived from external trials or real world data sources to reduce, or even eliminate, the concurrent control group.
The alternative when RCTs are not possible
SCAs can be particularly useful in the rare disease and rare oncology spaces. Because these disease types have very small patient populations, it can be impractical or prohibitively difficult to find enough patients to enroll in an RCT, which can lead to sample sizes too small to obtain meaningful results. In these circumstances, using relevant individual patient data on control from external trials or real world data sources allow to reduce, or even eliminate, the concurrent control group with an External Control Arm or Synthetic Control Arm (SCA), so that the placebo or standard of care group is not an issue because the comparison group is outside of the study and there are no patients in the study who miss out on active treatment.
Digital Twin Trial
The aim of a clinical trial is to measure the difference between what happens when a patient receives the experimental treatment and what would happen if they did not. However, both outcomes cannot be observed in one patient. Digital twins allow researchers to ask what-if questions about real people in clinical trials. The machine learning algorithm is devised to integrate patient’s multi-dimensional data and to accurately predict personalized outcome responses with and without the experimental treatment.
How is our SCA generated?
SCA is generated through a Machine Learning method (OSCAR) of real-world data (RWD) collected from existing medical records (HER), disease registries, patient-generated data, claims forms or other clinical trial data sets. These RWD and/or other clinical trial data will refer to patients with the same clinical diagnosis and characteristics and follow-up of those of the single arm in the trial.
Optimal Trial Design
Identifying the appropriate patient populations and the most suitable biomarkers and endpoints allows to optimize the trial design accordingly, can reduce the rate of trial failure, rescue a promising molecule for further development, and capture better primary and secondary endpoint data to support approval and payer valuations.
TRANSFORMING AND ACCELERATING CLINICAL TRIALS
WHAT IS OSCAR ML?
SYNTHETIC CONTROL ARMS
It’s a cloud-based, validated AI/ML application for creating synthetic data from real-world data (RWD) collected from existing medical records, disease registries, patient-generated data, claims forms or from other clinical trial data sets, to be used in single-arm studies as a Synthetic Control Arm (SCA) to substitute a traditional placebo or standard of care control group or to be used for the generation of digital twin patients on which to predict the investigational drug or standard of care effect.
The connection to external data sources is via a FHIR protocol, an interoperability standard for electronic exchange of healthcare information. OSCAR ML offers many interesting features.
WAITING FOR YOU
We can help you with the evaluation of the most appropriate trial design in order to maximize the chance of success while significantly reduce the overall project timelines and costs.
OUR FREE WEBINAR
NO WEBINAR AVAILABLE AT THE MOMENT
22th, December – Closed
TRANSFORMING CLINICAL TRIALS WITH REAL-WORLD EVIDENCE – THE SYNTHETIC CONTROL ARM