The increasing adoption of AI across life sciences has already helped showcase its ability to accelerate research, identify new drug targets, and facilitate effective clinical trials with improved patient experience.
This article is the first of a series looking at the impact of AI’s game-changing role so far within life sciences, and the vast future potential it holds.
Traditionally, the process of developing drugs is long, complex, costly, and routinely unsuccessful – it’s estimated that just 12% of drugs that reach clinical trials will actually make it to market.
More and more, AI is being leveraged to accelerate drug development, and its use has already improved the chances of clinical trial success and subsequent regulatory approval.
The drug development process typically starts with the identification of a potential target for a drug. The target could be an enzyme or receptor in the body, or an organism that causes disease.
Once the target is identified, researchers work to develop a compound that can interact with it. Then, after a promising compound has been identified, its safety and efficacy is tested in preclinical models. Only then does it progress to the second phase of clinical trials with patients.
Advanced AI algorithms can rapidly analyze vast amounts of biological data, identifying patterns, and pinpointing the compounds that could potentially bind to the selected target. It can also predict the toxicity of a compound and any probable side effects. This saves researchers significant amounts of time, not just on the analysis but also in reducing the number of compounds that they then put forward for testing in the lab.
Clinical trials are the foundation of safe and effective drug development, but traditionally, due to the many inefficiencies, they’ve been the rate-limiting step to bringing a new drug to market.
One of the major challenges is finding the right patients for clinical trials, and then recruiting and retaining them. The need for frequent travel to the trial site and the time commitment required once there can negatively affect patient retention. There can also be an issue of diversity within clinical trials, as trial sites may be inaccessible to underrepresented populations.
AI automates eligibility analysis to identify the patient populations most likely to benefit from a new therapy, and matches potential participants to the trial in question.
AI has also enabled clinical trials to be done virtually from patient’s homes through a web-based platform, plus sensors and other wearable devices to improve patient monitoring.
This removes the need for patients to travel to a clinical site and spend time there, improving patient enrollment and engagement, while reducing costs.
Additionally, AI-triggered smartphone alerts and reminders help with adherence and retention, and AI chatbots, intelligent search, and voice assistance all improve patient access to relevant trial information.
AI is already transforming life sciences, and its potential future impact could be exponential. Earlier this year, the first fully AI-generated drug entered phase 2 clinical trials. The drug, INS018_055, is being tested for the treatment of a rare, progressive chronic lung disease called idiopathic pulmonary fibrosis. AI played a crucial role in discovering the specific protein target the drug binds to, and the timeline of the drug development process to clinical trial was just one year, a striking contrast to the usual average of five years.
As AI becomes increasingly prevalent in the life sciences, we can expect to see more significant advancements in drug discovery. However, more regulatory guidance around privacy and data security issues is needed to ensure AI tools are fully embraced.