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.
Clinical trial designs vary considerably, impacting study execution, patient recruitment, endpoints, and treatment delivery. Here’s a brief summary of some common designs: First-In-Human (FIH) Studies These are the initial human trials for a new drug, procedure, or treatment, focusing primarily on safety. Cohort Studies These observational studies follow a group of individuals over an extended period to assess risk factors associated with developing specific conditions. Case-Control Studies These studies compare individuals with a particular disease or condition (cases) to similar individuals without the disease (controls) to identify potential risk factors.
This post originally appeared on Fast Data Science’s blog on LinkedIn. The Growing Role of AI in Clinical Trials Clinical trials are vital for advancing medicine, but managing them efficiently is a constant challenge. Traditional methods for assessing risks and estimating costs often miss the mark, leading to delays and unexpected expenses. This is where Artificial Intelligence (AI) and Natural Language Processing (NLP) come into play, offering smarter, data-driven solutions to streamline trial planning and management.
This post originally appeared on Fast Data Science’s blog on LinkedIn. Budgeting is one of the most critical steps when planning a clinical trial. Clinical trials are complex, multi-phase studies that require significant resources, and understanding the costs associated with each phase is crucial for an accurate clinical trial budget. In this post, we’ll explore the different phases of clinical trials and the key factors that influence their costs, providing insights into how to prepare a comprehensive budget that aligns with your trial’s needs.
