|
Abstract:
|
Artificial intelligence (AI) or machine learning (ML) has been used in drug discovery in biopharmaceutical companies for nearly 20 years. The clinical endpoints currently collected in the clinical practice and clinical trials are unable to give a holistic assessment of the patient prognosis and quality of life as it is usually collected at discrete timepoints and protocol pre-specified in-patient visits. In addition, patients who are unable to come to the clinic physically miss their visits and have incomplete assessments. This was also apparent during the COVID-19 pandemic when patients were unable to get to the clinic. Digital endpoints collected through digital sensors have the potential to circumvent these situations and holistic measure the patient outcomes 24/7 and is the future of drug development. In this session, we will discuss some case studies where we have implemented digital sensors, its impact on some of the therapeutics areas, regulatory interactions, implementation challenges and opportunities to measure more robust clinical endpoints. We will also discuss role of quantitative scientists especially statisticians to lead in this new paradigm.
|
