The healthcare industry is on the brink of a revolution, and artificial intelligence (AI) is at the forefront. AI has the potential to revolutionize the healthcare industry by accelerating the drug discovery process, freeing up time for busy doctors, and providing remote diagnosis to underserved areas. AI systems can also help patients with follow-up care and the availability of alternatives to prescription drugs. The application of AI in healthcare is still relatively unexplored, but many companies are researching its potential.
Technology giants such as Google and Apple have joined forces to create a contact tracing platform that will use AI systems through the use of application programming interfaces (APIs) on smartphones. The Center for Artificial Intelligence in Medicine & Imaging (AIMI) held a virtual conference last August to discuss this interdisciplinary approach. AI systems are trained with a portion of the collected data (also known as a training data set) and the remaining data is reserved for testing (also known as a test data set). It is important for the user of an AI system to have a basic understanding of how such models are built.
When presented with the performance metrics of a model, they must ensure that the metrics appropriate to the problem are presented and not just the metrics with the highest scores. AI can make medical recommendations, but at the end of the day, doctors must make the last decision in most cases. The health organizations that will be most successful are those that will be able to fundamentally rethink and reimagine their workflows and processes and use machine learning and AI to create a truly intelligent health system. The future of AI in healthcare is bright and promising, and yet much remains to be done.
