img
img

Learn how our cutting-edge technologies improve your trial efficiency

The recruitment process is the most time-consuming part of clinical trials.

85% of clinical trials fail to retain enough patients, and approximately 86% of all trials are delayed by over 6 months, in part due to recruitment issues, indicating a significant and urgent need for improvement (1, 2). The manual recruitment and processing of patients is one of the major obstacles to running financially and clinically viable trials, and currently, traditional methods rely on doctors suggesting patients to come forward for trials, which can be prone to clinician bias.

In choosing which participants to take forward for a trial, often this means that people of certain races, ages or genders aren’t chosen, simply due to unconscious clinician bias and exclusion, which contributes to small and poorly diverse clinical trial populations (3) . Other methods include word of mouth and patient’s own research to apply for trials, which consequently leads to a lack of patients in clinical trials. Up to 80% of patients aren’t even aware they’re suitable for trials, so improvements must be made in reaching out to larger populations.

Recent technological developments are cognitive technologies that include machine learning, artificial intelligence (AI) and natural language processing (NLP).

AI is the utilisation of computers to perform tasks that have until recently been deemed only feasible for humans. It enables the gathering and processing of huge amounts of data from very disparate sources with high accuracy and in more organised manner, with none of the cognitive or emotional bias of humans.

Machine learning is the continuous improvement of algorithms based on previously fed machine learning experiences.

Both of these cognitive technologies are increasingly making their way into healthcare, and now into the recruitment of clinical trial patients. Through utilising AI and machine learning, patient forums, public search results and websites could be scanned to provide a rapid search of potential patients, to then reach out to suggest participation in trials.

Recent studies suggest that patient centric recruitment via web-based tools such as patient communities better engages patients and reminds them of their potential role and eligibility in clinical trials, when compared to traditional recruitment methods, presenting a significant advantage. By using these AI based outreach programmes, higher engagement has been seen for younger age groups, supporting these novel and targeted AI strategies as a major way to drive up patient recruitment and diversity (4) . Similarly, through using social media or search engine advertising, specific geographical areas could be targeted, for site-specific patient recruitment.

Through combing through this data to gather insights on patient needs in clinical trials, specific wording, using NLP can then be used to engage patients using targeted messaging to increase awareness of clinical trials. With machine learning able to adapt to patient’s engagement levels, campaigns can be sent out to maintain engagement either before or during trials, in order to ultimately improve patient recruitment and retention rates.

The aforementioned techniques can significantly increase the reach and diversity pool of patients, thus decreasing the lengthy recruitment timeline that currently greatly hinders clinical trials. Overall, this more efficient recruitment using AI would reduce costs and improve clinical outcomes, conferring benefits to the patients, clinical research organisations and pharmaceutical companies that sponsor them (5).

Some of the recruitment areas where AI could be most applicable is in finding patients with orphan diseases, or patients with specific comorbidities, or to filter patients for protocol-specific criteria, while still accounting for relevant patient demographics.

Neucruit’s API identifies all channels related to the inclusion criteria of trials, where patients behind each conversation are identified, and launches targeted campaigns for specific patients. Following this, Neucruit pre-screens patients and excludes those that are unsuitable. Neucruit’s NLP will alter phrasing and clinical language for the patient to provide personalised engagement throughout the recruitment process, allowing for concerns to be identified and addressed appropriately to maintain patient engagement and retention.

With respect to the bigger picture, the support of cognitive technologies such as Neucruit’s in the recruitment stage would guide future clinical trial recruitment due to the significant behavioural insights generated. With this, clinical trials would be better designed for specific populations, and through easier patient recruitment, trials would be sped up, bringing treatments to the market much faster, to better benefit a wider population.

References

  1. Gul RB, Ali PA. Clinical trials: the challenge of recruitment and retention of participants. 2010;19(1‐2):227-33.

  2. Ghosh I. How Artificial Intelligence is Transforming Clinical Trial Recruitment2018. Available from: https://www.visualcapitalist.com/artificial-intelligence-transforming-clinical-trial-recruitment/.

  3. Kelly Imperial College London and Cancer Research UK. A Clinical Research Nurses’ Perspective on Recruitment Issues. 2021.

  4. Gebauer M, Krämer A. 2021. Available from: https://www.clinicalleader.com/doc/data-driven-insights-to-improve-your-recruitment-process-for-clinical-trials-0001.

  5. Santikary P. 2018 2018-10-19. Available from:https://www.ert.com/blog/transforming-clinical-trials-through-the-power-of-ai/.

img
Optimising
clinical trials
with AI

Optimising clinical trials with AI whitepaper

Download our "Optimising Clinical trials with AI" whitepaper to see how our data-driven patient recruitment strategies can optimise the clinical research process

Whitepaper Download