The Clinical Trial Risk Tool has been featured in a guest column in Clinical Leader, titled A Tool To Tackle The Risk Of Uninformative Trials, in cooperation with Abby Proch, Executive Editor at Clinical Leader.
In the article, Thomas Wood of Fast Data Science highlights the problem of “uninformative” clinical trials – those that don’t provide meaningful results, even if the drug being tested is effective or ineffective. He distinguishes these from simply “failed” trials and emphasises the ethical and financial waste they represent. Wood explains that while “uninformativeness” lacks a formal definition, it can be understood by examining the five conditions of an “informative” trial as outlined by Zarin, Goodman, and Kimmelman (2019): addressing an important question, meaningful design, feasibility, scientific validity, and timely, accurate reporting. Trials excluded from meta-analyses due to bias are often considered uninformative.
Wood describes how the Clinical Trial Risk Tool tackles this problem by assessing trial protocols against these criteria. He suggests expanding the tool to include a template clinical trial budget derived from real-world cost data (e.g., Sunshine Act disclosures). Further enhancements could include identifying endpoints and inclusion/exclusion criteria, then searching clinical trial registries (like ClinicalTrials.gov) for similar past trials to help users evaluate their planned trial’s design choices.
Wood also suggests tailoring the tool for different user profiles (patient advocates, financial planners, medical professionals) by providing personalised feedback and recommended actions for protocol improvement. The goal is not to replace human review, but to help users identify design gaps and high-risk indicators early in the process.
Fast Data Science is a leading data science consultancy firm providing bespoke machine learning solutions for businesses of all sizes across the globe, with a concentration on the pharmaceutical and healthcare industries.
Estimating the total cost of a clinical trial before it runs is challenging. Public data on past trial costs can be hard to come by, as many companies guard this information carefully. Trials in high income countries and low and middle income countries have very different costs. Upload your clinical trial protocol and create a cost benchmark with AI Protocol to cost benchmark The Clinical Trial Risk Tool uses AI and Natural Language Processing (NLP) to estimate the cost of a trial using the information contained in the clinical trial protocol.
You can download a white paper about clinical trial cost benchmarking here Estimating the total cost of a clinical trial before it runs is challenging. Public data on past trial costs can be hard to come by, as many companies guard this information carefully. Trials in high income countries and low and middle income countries have very different costs. Clinical trial costs are not normally distributed.[1] I took a dataset of just over 10,000 US-funded trials.
Guest post by Safeer Khan, Lecturer at Department of Pharmaceutical Sciences, Government College University, Lahore, Pakistan Introduction The success of clinical studies relies heavily on proper financial planning and budgeting. These processes directly impact key factors such as project timelines, resource allocation, and compliance with regulatory requirements. The accurate forecasting of costs for clinical trials, however, is a highly complex and resource-intensive process. A study by the Tufts Center for the Study of Drug Development found that the average cost of developing a new drug is approximately $2.
