In Frontiers in medicine
BACKGROUND : Manually keeping up-to-date with regulations such as directives, guidance, laws, and ordinances related to cell and gene therapy is a labor-intensive process. We used machine learning (ML) algorithms to create an augmented intelligent system to optimize systematic screening of global regulations to improve efficiency and reduce overall labor and missed regulations.
METHODS : Combining Boolean logic and artificial intelligence (i.e., augmented intelligence) for the search process, ML algorithms were used to identify and suggest relevant cell and gene therapy regulations. Suggested regulations were delivered to a landing page for further subject matter expert (SME) tagging of words/phrases to provide system relevance on functional words. Ongoing learning from the repository regulations continued to increase system reliability and performance. The automated ability to train and retrain the system allows for continued refinement and improvement of system accuracy. Automated daily searches for applicable regulations in global databases provide ongoing opportunities to update the repository.
RESULTS : Compared to manual searching, which required 3-4 SMEs to review ~115 regulations, the current system performance, with continuous system learning, requires 1 full-time equivalent to process approximately 9,000 regulations/day. Currently, system performance has 86% overall accuracy, a recommend recall of 87%, and a reject recall of 84%. A conservative search strategy is intentionally used to permit SMEs to assess low-recommended regulations in order to prevent missing any applicable regulations.
CONCLUSION : Compared to manual searches, our custom automated search system greatly improves the management of cell and gene therapy regulations and is efficient, cost effective, and accurate.
Schaut William, Shrivastav Akash, Ramakrishnan Srikanth, Bowden Robert
CAR-T, augmented intelligence, automated systematic search, machine learning, regulations, regulatory documents