With the recent surge of open source AI tools we can now quickly ask our computers to write essays, exercise plans, and even plan holiday trips. But what does this mean for AI in medicine?
AI will change how we diagnose patients, treat patients, and make new discoveries. Like any new technology in medicine — particularly ones as fundamental as this — it’s worth understanding how the technology works before it ends up in the hands of clinicians and in front of patients. Let’s start with understanding the vocabulary.
- Artificial Intelligence (AI) is a multidisciplinary computer science field that aims to train machines to model human intelligence.
- Machine Learning, a discipline within AI, means training machines to learn on a “model” or chunk of data that has a set of rules or algorithms to guide predictions without human intervention.
- Deep Learning, referring to mathematical depth, is a technique that dives deeper into AI as a subset discipline within Machine Learning. It is based on an Artificial Neural Network (ANN) that uses mathematical algorithms to mimic the neural network within the brain to guide more accurate predictions on more complex data.
- Generative AI uses an advanced deep learning model architecture, called transformers or large language models (LLMs) , to train on massive amounts of text and data to create or “generate” responses to questions with accurate and natural sounding language. This technology now takes form in popular chatbots and tools that create images from descriptions write music in a particular style or tone.
With clinicians spending two hours on administrative work for every hour of patient care, this technology has the potential to make a huge impact. Solutions using generative AI can be used to help summarize patient encounters and automate form filling, saving hours of time every day and helping clinicians focus on patients during the encounter. But AI tools alone can’t create accurate clinical notes. They need large clinical datasets and tuning - and ultimately the oversight of the clinician using the tool to verify the accuracy of the generated text before submitting it to the patient record.
For a deeper understanding read the full article. Visit www.suki.ai to learn more about how Suki’s AI-powered voice assistant uses these techniques to tackle administrative burden.