‘Medical-grade’ AI is poised to help health systems manage their data

There’s been a lot of hype over the past year around generative artificial intelligence tools like ChatGPT. But for all emerging healthcare applications involving large language models, it’s worth remembering that a key value of LLMs is their ability to improve natural language processing capabilities that have been around for decades.

Healthcare organizations need AI systems that can process and understand an entire patient record, or an entire organization’s EHR system – and genAI tools are well positioned to help.

We interviewed Kim Perry, Chief Growth Officer at emtelligent, a medical NLP company, who talks about the power of generative AI and large language models and their relationship to NLP, AI systems that can understand an entire record or EHR system, and how “medical grade AI” can improve patient outcomes and prevent physician burnout.

Q. There’s a bit of a misunderstanding about the power of generative AI and large language models – that they actually power natural language processing, another form of AI. Please talk about this relationship.

A. It’s amazing how ChatGPT and generative AI were essentially unknown to the general public just a year ago. And now ChatGPT has more than 100 million users around the world, including consumers and entire industries. Unfortunately, many people form their opinions about emerging technologies based on first impressions and casual reading. But genAI and large language models are new topics for many consumers and businesses, so some confusion is inevitable.

Natural language processing predates generative AI and recent developments in LLMs. However, we are now seeing genAI and LLMs being used to create what we call “medical AI” or medical grade NLP. LLMs are trained specifically on clinical data and, unlike traditional NLP, medical-grade AI is capable of unlocking the 80% of medical data currently hidden in unstructured text.

The ability of medical-grade AI to process and understand millions of documents will transform the way physicians do their work at the point of care. But its value will extend across the healthcare continuum and benefit not only providers, but also payers, pharmaceutical companies, life sciences and academic researchers.

Q. AI like ChatGPT is great for answering a single question, but you suggest that service providers need systems that can understand an entire diagram or EHR system. Please provide some more information.

A. GenAI is great for answering a single question, but we assume the answer is actually correct. Too often, applications like ChatGPT make up facts, or ‘hallucinate’ them. That is simply unacceptable in a situation where physicians must make evidence-based decisions at the point of care.

If providers cannot trust an information source, they will stop using it. Furthermore, genAI can inundate users with a flood of keyword-driven data, making it difficult for doctors to find the information they need.

Providers need tools that can access, understand and contextualize patient information from a single diagram or through an EHR system. This is where traditional NLP falls short; it can’t make sense of all that unstructured data.

Medical-grade AI leverages advances in healthcare machine learning and LLMs I mentioned earlier to enable provider organizations to unlock the value of unstructured data such as free-text notes. For example, medical-grade AI can understand medical terminology, including acronyms and slang, that is indecipherable to traditional NLP.

And because medical-grade AI is built for enterprises, it can process and understand millions of documents. This ability to scale is critical as the amount of health data continues to grow.

Q. How can what you call “medical-grade AI” improve patient outcomes?

A. Medical-grade AI can improve patient outcomes by giving doctors the information they need, when they need it, and in an easy-to-use format, helping them provide more effective care.

When doctors do not have access to patient information in unstructured data – for example about a previous procedure, a chronic condition or a severe allergy to a drug – they miss a holistic view of the patient. This can lead to errors in diagnosing and treating patients, leading to negative outcomes.

Conversely, when medical-grade AI generates automated summaries of patient history, physicians at the point of care have immediate access to information that provides insights into patient health and well-being. This is especially valuable when a doctor sees a patient for the first time.

As I said before, doctors won’t use tools they don’t trust because they can’t verify the information they’re given. Medical-grade AI addresses this concern by linking information in a patient summary back to the original data in the patient record, allowing physicians to assess context and verify sources for accuracy.

Q. How can medical-grade AI prevent physician burnout?

A. Doctors spend far too much time searching for and sorting through patient data. This creates a lot of stress for healthcare providers because they want to communicate with patients and not stare at a computer screen or search for specific information hidden in a long patient file.

Medical-grade AI offers powerful capabilities such as context-sensitive search and automated summaries that significantly improve workflows. By striking the right balance between recall and precision, medical AI allows doctors to be more efficient and effective when treating patients.

Better workflows help minimize burnout because physicians don’t feel like they are constantly struggling to keep up with their patients’ workload. It only makes sense that when physicians have smarter digital tools at their desks and at the exam table, they will be less frustrated and better able to practice at the top of their license. And that’s what all doctors want to do.

Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.