Advanced Solutions for Reducing Clinical Data Variability
Enhance Patient Trait Quantification for Better Insights
Patients are influenced by various factors, introducing variability into clinical data and complicating statistical analysis and interpretation.
Placebell© combines proprietary questionnaires and algorithms, enabling robust statistical analysis to increase study power and decrease risk without inflating the sample size.
Increase Study Power.
Quantify Patient Traits for Personalized Data-Driven Insights.
Placebell© provides a simple, cost-effective solution that mitigates data variability including placebo response and patient heterogeneity. By prioritizing patient-centricity and offering easy-to-implement user friendly technology, Placebell ensures a validated approach to addressing these challenges.
Placebell© collects unique patient psychological and demographic characteristics through its Participant Questionnaire (MPsQ) and uses advanced statistical methodologies and machine learning algorithms to enhance study power, reduce clinical development risk, and improve portfolio management.
Supporting Diversity in Clinical Trials.
Ethical clinical trials should reflect the ultimate patient population. Patients are influenced by their surroundings and experiences, which can significantly impact disease perception.
Cognivia offers machine learning solutions to help you comply with the FDA’s Diversity Action Plan goals by minimizing data variability caused by patient diversity.
0%
Increase in study power0%
Decrease in variability0%
Reduction of type ll errorPrediction of individual patient placebo responsiveness
The examples below present in a simple way (placebo responders versus non-responders) the accuracy of this prediction. When in the examples, PlacebellⓇ is presented as binary (placebo responders versus non-responders), in reality, PlacebellⓇ is a continuous score to be used as a baseline prognostic covariate to improve the study power.
Example of a subjective endpoint-Prediction of Womac pain improvement in osteoarthritis: Placebell can predict the placebo responders (Placebell high) who will have a higher pain decrease and non-responders (Placebell low) with a lower pain decrease. This prediction is highly statistically significant
Example of an objective endpoint-Prediction of the Corneal Fluorescein Staining and Scoring (CFSS) in dry eyes: Placebell can predict the placebo responders (Placebell high) who will elicit a higher CFSS decrease and non-responders (Placebell low) with a lower CFSS decrease. This prediction is highly statistically significant.
proven
Placebell has been deployed in more than a dozen studies across multiple indications.
low risk
Placebell poses no mathematical or operational negative impact on the trial or data.
powerful
Placebell uses advanced AI and machine learning to reduce variability in efficacy evaluation.
Step 1 Assess patient traits and characteristics
Patients complete the MPsQ post-screening and before the first dose of either an active agent or placebo, which measures traits, expectations, and other psychosocial factors.
Step 2 Apply Placebell Machine Learning-Powered Platform
Placebell© machine learning-based algorithms account for placebo response and patient heterogeneity, contextual factors resulting in Prognostic baseline covariates.
Step 3 Utilize Covariates in alignment with regulatory requirements
Individual Patients’ Placebell Prognostic Covariates are implemented to adjust statistical analyses, reducing variance and increasing study power more than usual baseline or prognostic covariates.
Placebell’s prognostic covariates adhere to regulatory requirements, specifically complying with the FDA’s guidance on “Adjusting for Covariates in Randomized Clinical Trials for Drugs and Biological Products - Guidance for Industry”.
Understand patient differences in your next clinical trial
Increase clinical trial success rates and get new therapies to patients faster. Tell us about your clinical trial below and we'll be in touch.
"*" indicates required fields