ARTIFICIAL INTELLIGENCE
“There are strict inclusion and exclusion criteria where patients with certain comorbidities cannot be recruited, and we could, through algorithms included in an ‘in silico’ trial, respond to medical needs.”
technology, are valuable in efficient, real-time and personalised monitoring of patients automatically and continuously during the trial. Analysing data from this wearable technology can generate patient-specific diaries adapted to behavioural changes and disease expression to tailor the clinical trial to patient needs in terms of patient- centric approach, to improve compliance with protocol requirements and reliability of assessment of end points. Machine learning algorithms such as radiomics would play an important role in image-based end-point detection, which is key for oncologic diseases. This type of algorithm could detect disease progression early to complete the chemotherapy while reducing adverse events. With this model, we could reduce the risk of dropouts due to safety issues and increase the interest of the patient to continue in the trial due to the fact the disease is not progressing. The time to experiment with new trial designs has begun. Currently, adaptive designs are one of the most frequent types of clinical trial design. A new type of clinical trial based on AI, ‘in silico' looks set to transform the pharma industry. In silico is an allusion to the Latin phrases 'in vitro' or 'in situ' and stands for computations carried out on a silicon computer chip. If we can develop reliable computer models of the treatment and its deployment, we can perform exploratory clinical trials within a computer: an ‘in silico’ trial. In such a scenario, ‘virtual’ patients could be administered with a ‘virtual’ treatment, allowing us to observe through a computer simulation how the product acts and whether the drug produces the intended effect without leading to events that might be dangerous for the patient. Experimenting with an ‘in silico’ trial first means we can reduce the size and duration of the clinical trial because we will
already have identified characteristics that determine which patients might be at risk of adverse events or those who will not respond to the drug. This is very important during oncologic drug development.
Another advantage of working with a ‘virtual’ trial could be to refine our clinical trial through more detailed information on potential outcomes and greater explanatory power in interpreting any adverse effects that might happen.
A real clinical trial will remain essential in most cases; however, we can find different situations where a ‘virtual’ trial can be a different way to generate scientific evidence. It could be an option in rare diseases where it’s very difficult to have a large enough patient population to complete a classical Phase III trial. Currently, there are strict inclusion and exclusion criteria where patients with certain comorbidities cannot be recruited, and we could, through algorithms included in an ‘in silico’ trial, respond to medical needs. Where will we be in five years´ time? To be honest, I don’t know. Although the options that we have at our disposal are many, the impact of AI is not enough. Pharma companies need to add data-focused roles to their teams, while the rest of the team increases the digital capabilities to amplify efficiency and agility. There are many questions to solve and many patients to help, where AI has a relevant role to lend a hand.
Outsourcing in Clinical Trials Handbook | 47
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100
