During a typical day, we use a variety of applications that, by virtue of their artificial intelligence, automatically understand our speech and provide near-real-time feedback to support decision-making. But is machine learning, one of a number of AI techniques, ready for clinical applications, specifically to accelerate drug development and/or reduce development costs? Machine learning encompasses a variety of algorithmic techniques that clinical drug developers can use to identify and infer patterns to support enhanced/automated decision-making. One such technique is Natural Language Processing, which can be used to "read" scientific text and infer its semantic context in order to search and find information more easily. The main benefit of machine learning and natural language processing is that they can be used to either augment or replace the error-prone manual analysis work performed by people, and they can scale infinitely as the volume and variety of data grow.

During a typical day, we use a variety of applications that, by virtue of their artificial intelligence, automatically understand our speech and provide near-real-time feedback to support decision-making. But is machine learning, one of a number of AI techniques, ready for clinical applications, specifically to accelerate drug development and/or reduce development costs? Machine learning encompasses a variety of algorithmic techniques that clinical drug developers can use to identify and infer patterns to support enhanced/automated decision-making. One such technique is Natural Language Processing, which can be used to "read" scientific text and infer its semantic context in order to search and find information more easily. The main benefit of machine learning and natural language processing is that they can be used to either augment or replace the error-prone manual analysis work performed by people, and they can scale infinitely as the volume and variety of data grow.