Control placebo response and master data variability to drive stronger results and improve trial success.

Despite patient and site training, the placebo response remains a challenge for clinical trials.

By combining a proprietary questionnaire with a machine learning algorithm, Placebell predicts each patient’s placebo responsiveness to reduce the placebo barrier and demonstrate true treatment effect.

see fda feedback

Increase Study Power without Enrolling More Patients

Placebell, 2025 finalist for the Fierce Life Sciences Innovation Award, is a simple, cost-effective solution that mitigates data variability caused by factors like the placebo response.

Improve your ability to demonstrate statistical significance
Increase study power - without adding risk
Decrease your data variability
Reduce Type II error

see data

0%

Increase in study power

0%

Decrease in variability

0%

Reduction of type ll error

Treatment effect estimation precision improved by 40% in OA clinical trial

In osteoarthritis clinical trials, the placebo response can mask treatment effects. This phase II trial assessed the Placebell model’s ability to account for placebo response when testing the efficacy of single-dose intra-articular (IA) injection of UBX101 in patients suffering from painful OA of the knee.

27.7% of the variance in WOMAC-Pain scores was explained by the placebo response model.
p < 0.001 for all primary and secondary endpoints, confirming highly significant predictions.
40% improvement in treatment effect precision, equivalent to adding 72 more patients to the study.

view results

Proven & Translatable Effectiveness

Placebell has been successfully applied to many indications and can be applied to virtually any disease with significant placebo response rates.

Pain

Allergy

Osteoarthritis

Diabetes

Parkinson’s Disease

Other Indications

Regulatory & FDA Compliance

Regulatory compliance in clinical trials is critical.
Our prognostic covariate approach to quantifying patient personality traits and reducing clinical data variability is fully aligned with FDA and EMA guidelines.

GUIDANCE ON COVARIATES FDA FEEDBACK AI COMMITMENT

GUIDANCE ON COVARIATES

FDA Guidance on Prognostic Covariates

The FDA's guidance on adjusting for covariates in randomized clinical trials emphasizes the use of prognostic baseline covariates to improve statistical efficiency for estimating and testing treatment effects.

Placebell adheres to these guidelines, ensuring our methods meet the highest regulatory standards.

READ GUIDELINES

FDA FEEDBACK

FDA Feedback to Our Letter of Intent

Cognivia recently submitted an LOI outlining Placebell’s methodology and seeking to explore Placebell’s applicability within ISTAND (“Innovative Science and Technology Approaches for New Drugs (ISTAND) Pilot Program”) for a wide range of statistical models. In response, the FDA acknowledged that:

Placebell operates as a “special case” of covariate adjustment.
Its correct use might improve study precision and power.

This positions Placebell as a practical and scientifically grounded tool for enhancing the analysis of treatment effects in clinical trials.

READ FDA FEEDBACK

AI COMMITMENT

Our AI Commitment

Explainability is crucial for fostering trust in AI systems. Especially in high-stakes environments such as clinical trials, researchers need to understand the rationale behind AI decisions.

The FDA released a draft guidance "Considerations for the Use of Artificial Intelligence to Support Regulatory Decision-Making for Drug and Biological Products," outlining that AI models should have a clearly defined context of use, and sponsors should engage with the FDA early to discuss AI credibility assessments.

Placebell adheres to the FDA's recommendations through:

Transparency: The Placebell algorithm will be made available to regulatory bodies when submitting a trial using the Placebell algorithm. This transparency allows for better governance and compliance with regulations, ensuring that AI systems operate ethically.
Trust: Placebell does not put trials at risk as it is a simple covariate. The statistical analysis can be performed with and without the Placebell covariate.
Understanding: The Placebell model is robustly defined (features, weights).

TAKE A DEEP DIVE INTO THE MODEL

How Placebell Works

STEP 1

Assess patient traits & characteristics

Patients complete the MPsQ post-screening and before the first dose of either an active agent or placebo. The MPsQ 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 for each patient.

STEP 3

Use Covariates in alignment with regulatory requirements

Placebell Prognostic baseline Covariates for each patient are implemented to adjust statistical analyses, reducing variance and increasing study power – more than usual baseline or prognostic covariates.

Need help analyzing your clinical trial data?

In addition to helping researchers characterize the placebo response, Cognivia can help you detect and explain sources of clinical site variability and adjust data for a cleaner, better understanding of study results.

In multicentric clinical trials, the variability of patient outcomes between sites and geographies is a prevalent challenge. Understanding this variability starts with collecting patient-specific information that may influence their responses to treatment depending on the specific study setting applying to them (for example, how they interact with the sites, their expectations, etc).

By analyzing these data, Cognivia can help understand if some differences were more related to the intrinsic property of each subject or to a common effect of a site or country.

TELL US ABOUT YOUR TRIAL

Resources about clinical trial data variability & the placebo response

Clinical Trial Statistical Analysis: How to Minimize Noise

Statistical analysis of clinical trial data is a necessary component of a well-designed study. In this blog, we provide an overview of how it works—and how statisticians can minimize noise related to each patient’s individual characteristics and placebo responsiveness.

How to Increase Clinical Study Power with Covariate Adjustment

Adjustment for covariates helps clinical trial statisticians demonstrate differences in drug effect between groups of people. In this blog, we discuss what this means and how it can help improve analysis and interpretation of clinical trial data.

How Much of the Measured Treatment Response Is the Placebo Response?

While the placebo response has long been recognized as a significant issue in clinical trials – and a major cause of clinical trial failure – this study provides quantitative evidence of its significance across indications.

Understand patient differences in your next clinical trial

Increase your trial’s success rates and bring new therapies to patients faster.

Tell us about your clinical trial below, and our team will be in touch.

"*" indicates required fields