Using Computer Vision and Machine Learning to Identify Patterns of Fraudulent Participant Activity in CNS Trials
In this poster you will learn:
- Artificial Intelligence (AI) and Machine Learning (ML) are increasingly being applied to medicine to improve clinical decision-making, implement efficiencies, and drive behavioral modifications.
- In clinical research, intention non-adherence - ‘professional subjects’ who enroll in trials and feign adherence - has been receiving increased attention. It is estimated that up to 20% of clinical trial participants never actually take the study drug.
- While non-usage of technologies may be indicative of intentional non-adherence, visual evidence of participant deception has not yet been captured.
- An AI platform (AiCure) was used to visually monitor adherence to study treatment in seven CNS studies. We reviewed visual data of participant deception (identification of doses that trigger alerts) to demonstrate the ability of the platform to identify, predict, and potentially correct this behavior.