- \n
- AI tools have the potential to streamline, optimise, or speed up various stages of the clinical trial process.<\/li>\n
- This could accelerate drug development and potentially reduce the number of participants needed in clinical trials.<\/li>\n<\/ul>\n
\n![\"\"](\"https:\/\/i0.wp.com\/thepublicationplan.com\/wp-content\/uploads\/2024\/06\/AdobeStock_762014099.jpeg?resize=1024%2C574&ssl=1\")
<\/p>\nWhile advances in the field of artificial intelligence (AI) have been making headlines recently, drug development has been slowing down. Taking more than a billion dollars and a decade to complete increasingly complex clinical trials, the majority of investigational drugs never reach the market. Could AI help reverse this trend?<\/p>\n
How can AI aid clinical research?<\/strong><\/p>\n
In a recent article for Nature<\/em><\/a>, Matthew Hutson discusses how researchers have already begun to investigate the potential for AI<\/a> to optimise clinical trial processes:<\/p>\n
- \n
- Clinidigest<\/a> claims to simultaneously access dozens of clinical trial records to create summaries, allowing researchers to gain a quick overview of existing trial data<\/strong>.<\/li>\n
- HINT<\/a> aims to predict a drug\u2019s success during the trial design <\/strong>stage to ensure resources are not wasted.<\/li>\n
- Trialpathfinder<\/a> seeks to optimise eligibility criteria<\/strong> by testing whether broadening criteria would have any effect on risk to patients; its developers believe this would also allow for more inclusive trials.<\/li>\n
- DQueST<\/a> seeks to match patients looking to participate in research with suitable clinical trials.<\/li>\n
- SDQ <\/a>is used to extract, analyse, and clean datasets<\/strong>.<\/li>\n
- Some AI tools aim to predict missing data<\/strong> points and identify relevant clinical subgroups.<\/li>\n
- Others aim to monitor adherence to medication<\/strong>, so that investigators will not have to.<\/li>\n<\/ul>\n
\n
Pharmaceutical companies are now experimenting with software that completes tasks within a couple of days, which previously took 2 months.<\/p>\n<\/blockquote>\n
Can AI help patients too?<\/strong><\/p>\n
As well as facilitating recruitment and including more populations in trials, AI tools could decrease the number of patients required for successful research. Hutson highlights examples such as Unlearn.AI<\/a>, which aims to achieve this through creating \u2018digital twins\u2019<\/a>, predicting a patient\u2019s results had they been given a placebo. The makers claim this reduces the sample size required and allows a greater proportion of patients to take investigational drug rather than placebo.<\/p>\n
Technologies such as ChatDoctor<\/a> answer patients’ questions, which could help retain participants in clinical trials, as well as being useful in clinical practice<\/a>.<\/p>\n
Should we be worried?<\/strong><\/p>\n
As Hutson points out, there are concerns about AI and research integrity. Xiaoyan Wang, co-developer of AutoCriteria<\/a>, highlights the risk of biased data<\/a> and confidentiality issues when providing tools with a huge training data set. The WHO has published guidelines on making sure\u00a0 AI is used ethically<\/a>. As is currently widely acknowledged, AI outputs may always need to be checked by a human<\/a> expert.<\/p>\n
While AI has the potential to optimise clinical trials, researchers and clinicians need to be mindful of its limitations.<\/p>\n
\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2013<\/p>\n
- HINT<\/a> aims to predict a drug\u2019s success during the trial design <\/strong>stage to ensure resources are not wasted.<\/li>\n
- Clinidigest<\/a> claims to simultaneously access dozens of clinical trial records to create summaries, allowing researchers to gain a quick overview of existing trial data<\/strong>.<\/li>\n
![\"\"](\"https:\/\/i0.wp.com\/thepublicationplan.com\/wp-content\/uploads\/2024\/06\/Aspirations_Elena-Dennis_1.png?resize=1024%2C125&ssl=1\")
<\/a><\/p>\n