PhaseV develops a machine learning-based platform that utilizes causal inference and multi-arm bandit algorithms to optimize adaptive clinical trial design and execution. This technology enhances decision-making and resource allocation, increasing the success rates of clinical trials by providing real-time, data-driven insights throughout the trial process.
Funding
$15M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
EVVVFounders
Product
Problem
Clinical trials often suffer from inefficient designs and suboptimal resource allocation, leading to increased costs and lower success rates. Traditional trial designs may not adapt to accumulating data, hindering the ability to identify effective treatments or patient subgroups during the trial.
Solution
PhaseV offers a machine learning platform that leverages causal inference and multi-arm bandit algorithms to optimize clinical trial design and execution. The platform enables adaptive trial designs, allowing for real-time adjustments based on accumulating data. By detecting hidden signals and heterogeneous treatment effects, PhaseV helps clinical teams make data-driven decisions, optimize resource allocation, and increase the likelihood of identifying successful treatments and patient subpopulations. The platform's intuitive interface simplifies the implementation of advanced statistical methods, making adaptive trials more accessible to clinical teams.
Target Audience
PhaseV primarily targets clinical teams, pharmaceutical companies, and research institutions involved in designing and executing clinical trials, particularly those seeking to improve trial efficiency and success rates.
Features
- Adaptive trial design simulation to evaluate the benefits of adaptive designs
- Real-time optimization using multi-arm bandit algorithms for efficient exploration and exploitation of treatment options
- Causal machine learning to detect hidden signals and heterogeneous treatment effects
- Identification of subpopulations and endpoints likely to succeed in subsequent trials
- Translation of complex machine learning insights into actionable recommendations
- Flexible, closed-loop software architecture for real-time adaptations and integrations
- Intuitive interface designed for clinical teams to simplify use and maximize efficacy