CluePoints Launches Intelligent Statistical Solution to Risk-Based Monitoring

A new software and service provider of Intelligent Statistical Monitoring solutions – CluePoints – has been launched to allow biopharmaceutical sponsors and CROs to identify signals in a clinical trial data set and make timely decisions about which sites to target for monitoring activities and Source Data Verification (SDV). As a result, corrective action can be taken early and sites reassessed periodically throughout the course of a study to ensure the quality and integrity of the data, enhance patient safety and, ultimately, reduce regulatory submission risk.

The launch is in response to recent industry guidance from the FDA and a reflection paper from the EMA encouraging sponsors to embrace an alternative to traditional on-site monitoring techniques and to explore reduced Source Data Verification (SDV) using a risk-based approach to monitoring.

The FDA’s “Guidance for Industry Oversight of Clinical Investigations — A Risk-Based Approach to Monitoring” calls for sponsors to “replace on-site monitoring activities for monitoring activities that can be done as well or better remotely” and to “target on-site monitoring by identifying higher risk clinical sites… by performing monitoring activities that can only be accomplished using centralized processes [and to] conduct aggregated statistical analyses of study data to identify sites that are outliers relative to others and to evaluate individual subject data for plausibility and completeness”.

Francois Torche, CEO of CluePoints, comments: “It has taken a considerable amount of time to build the CluePoints solution due to the complex array of statistical algorithms used but the result is a powerful engine that can be used in all late-stage clinical trials. Not only does CluePoints help improve data quality and integrity, it also has the potential to act as the engine to drive millions of dollars in cost savings via reduced monitoring and SDV.”

At the heart of the CluePoints solution is the SMART™ engine, comprising a comprehensive range of inter-connected statistical tests that make no distributional assumptions about the clinical data but, when aggregated together, highlight difficult to detect issues in the site results. The SMART™ processes all elements of the clinical data in a comprehensive manner, with no predetermination of risk. This results in an objective view of which sites exhibit outlying or discrepant data and, hence, allow on-site monitoring activities to be targeted to address those centers as a priority.

The brainchild of Harvard-trained biostatistician Marc Buyse, CluePoints has evolved from academic research to a full commercial entity over the course of the last ten years. Buyse is cited in the FDA’s Risk-Based Monitoring Guidance for his work in detecting fraud in clinical trials using statistical modeling techniques (The Role of Biostatistics in the Prevention, Detection and Treatment of Fraud in Clinical Trials. Statistics in Medicine 18, 1999). It has taken the International Drug Development Institute (IDDI) a decade to perfect the statistical algorithms that comprise the SMART™ engine underpinning CluePoints. This research is endorsed by a consortium comprising GlaxoSmithKline Vaccines, the Institute of Statistics at Université Catholique de Louvain, and the Artificial Intelligence Research Laboratory of Université Libre de Bruxelles. The powerful and sophisticated process used to detect anomalies in site data is currently pending patent protection with the United States Patent and Trademark Office.

Related ArticlesRisk-Based Monitoring Risky for Sponsors?

Low-Hanging Fruit in the Fight Against Inefficiency