How much does a clinical trial (RCT) cost?

How can we estimate the cost of a clinical trial from the protocol? Modelling RCT costs

Clinical trials are a cornerstone of medical progress, but their high cost can be a barrier to innovation. The price tag can vary widely depending on several factors, making it difficult to estimate the financial investment needed before diving into a trial.

Factors affecting clinical trial cost

Several factors can affect how much a clinical trial costs:

Trial design: Choices made during protocol development significantly impact cost. This includes the number of interventions (treatments) being tested, the types of interventions (gene and cell therapies are particularly expensive), and the number of participants, sites, and visits required.
Trial location: Trials conducted in high-income countries tend to be more expensive compared to those run in countries with lower healthcare costs.
Trial phase: Later-stage trials, typically involving larger patient cohorts, generally cost more than earlier-phase trials.

A study by Martin et al. (2017) explores the economic factors influencing clinical trial costs in more detail: https://doi.org/10.1038/nrd.2017.70

A histogram of costs of selected Oncology trials. A selection of data is shown in the table below.

Below you can see part of a public dataset of trials where the costs are known and available. We use data sources like these to train our models.

You can download the (public) dataset of cost data here and the original source online is here.

indication (longer)	Technology	CT.gov URL	Enrollment	Trial Phase	Total Cost	Per Patient Cost ($PP)
Advanced Myeloid Malignancy	biologic drug		30	Phase 1	328000	10933.3
Blood Cancer	biologic drug	NCT03483324	9	Phase 1	5000000	555556
Blood Cancer	biologic drug	NCT03925935	24	Phase 1	6192579	258024
B cell cancers, Leukemia	biologic drug	NCT03088878	156	Phase 1/2	18292674	117261
Blood Cancer	biologic drug	NCT02222688	26	Phase 1	4179598	160754
Colon Cancer	biologic drug	NCT02953782	112	Phase 1/2	10234048	91375.4
Leukemia, Acute Myeloid (AML)	biologic drug	NCT03248479	96	Phase 1	5000000	52083.3
Blood Cancer, Solid Tumors	biologic drug	NCT02216409	88	Phase 1	6505568	73926.9
Breast Cancer	biologic drug	NCT00781612&draw=2&rank=1	720	Phase 3	-	104186

Challenges in Cost Estimation for RCTs

Estimating clinical trial costs accurately can be challenging due to the variability in these factors. The complexity of protocols, often lengthy and written in technical language, makes manual analysis time-consuming and prone to error.

Machine Learning to the Rescue

Fast Data Science has developed a tool for the Gates Foundation that leverages machine learning to address this challenge. This Clinical Trial Risk Assessment Tool utilizes Natural Language Processing (NLP) to analyze clinical trial protocols.

We originally developed the tool to cover Tuberculosis and HIV trial cost estimation, and has since been extended to cover other disease indications including COVID, Cystic fibrosis, Enteric and diarrheal diseases clinical trials cost models, Influenza clinical trials cost modelling, Malaria clinical trials cost models, Motor neurone disease, Multiple sclerosis, Neglected tropical diseases clinical trials cost modelling, Oncology, and Polio clinical trials cost modelling.

How Does it Work?

Protocol Analysis: The tool processes lengthy PDF documents containing detailed information about the trial design, objectives, and methods.
Key Factor Extraction: Using NLP techniques, the tool extracts relevant data points such as the number of interventions, planned sample size, number of trial sites, and anticipated visit frequency.
Cost Prediction: Based on these extracted factors and historical cost data, the tool applies machine learning algorithms to predict the estimated cost of the trial.

Benefits of the Tool

Early Cost Awareness: By analyzing protocols before the trial begins, the tool provides researchers and sponsors with a more accurate picture of potential costs. This allows for better budgeting and resource allocation.
Informed Decision-Making: Cost estimates can influence decisions about trial design, potentially leading to cost-saving optimizations without compromising scientific rigor.
Improved Efficiency: The tool streamlines the cost estimation process, saving time and resources compared to traditional manual analysis.

Fast Data Science’s Clinical Trial Risk Tool is a valuable innovation in the field of clinical research. By harnessing the power of machine learning, this tool can help to improve the efficiency and affordability of clinical trials, ultimately accelerating medical progress.

References

Martin, L., Hutchens, M., Hawkins, C. et al. How much do clinical trials cost?. Nat Rev Drug Discov 16, 381–382 (2017). https://doi.org/10.1038/nrd.2017.70
May, Clinical trial costs go under the microscope, Nature, 2019, https://doi.org/10.1038/d41591-019-00008-7
Wood TA and McNair D. Clinical Trial Risk Tool: software application using natural language processing to identify the risk of trial uninformativeness. Gates Open Res 2023, 7:56 doi: 10.12688/gatesopenres.14416.1.