This artificial intelligence makes it possible to generate digital twins for clinical trial participants, offering a detailed prediction of their future health status. These predictive models are trained with meaningful patient data from previous studies. The use of digital twins in TwinRCTs makes it possible to improve the power of trials without increasing the number of participants, in line with FDA and EMA guidelines. It also reduces the time required to reach full enrollment in late-stage studies and increases the likelihood that participants will receive the experimental treatment by reducing the size of control groups. By predicting the outcome of each participant in the control group, regardless of their actual assignment in the trial, Unlearn strengthens the ability of researchers to take confident decisions from the early stages of the key tests. Its effectiveness and adaptability make this tool a valuable resource for all professionals involved in clinical research on diseases such as Alzheimer's, amyotrophic lateral sclerosis and many others.
Digital patient models help speed up the process Registration in late-phase studies by requiring fewer patients to achieve the same effectiveness. This optimizes resources and reduces time frames, offering a significant advantage for healthcare professionals involved in clinical research.
The use of digital twins increases the power of early clinical trials without increasing the number of participants. This improves significantly Precision observations of the effects of treatments, allowing more informed and early decisions in the development of new therapies.
By reducing the size of the control groups, TwinRCTs offer a greater probability for participants to receive the experimental treatment. This approach is not only increasing attractiveness of the study for potential participants but also ensures an ethical approach by limiting exposure to non-beneficial treatments.