ai in healthcare

AI in Healthcare: How New GPT-3 Tech Can Revolutionize Medical Data Science

Forward by Regina Moore, PharmD

Topics like AI in healthcare are going to get more and more buzz.  Using AI to improve patient care, tackle the ever expanding collection of digital health information, and using data points to assist providers with clinical decision making will become ever more important.

Unique inroads are being made with AI technologies.  Machine learning is making it possible for these systems to understand more natural language.  Speech recognition and improved language processing will help make AI applications feel more and more intuitive.

So please read on for this great write up, specifically about how medical professionals working with clinical data can use machine learning algorithms to improve their ease of working with medical and drug data.

Read on to Dr. Shabbir’s post!


AI in Healthcare: How OpenAI’s GPT-3 Can Revolutionize The Landscape Of Medical Information

Drug manufacturers daily respond to medical information questions posed by healthcare providers, key opinion leaders and patients regarding drugs in their respective pipeline.

Medical Information and AI in Healthcare

Medical information specialists are dedicated to responding to inquiries through written and verbal forms of communication. They strive to be experts and have to be up to date with the latest data available in their respective therapeutic areas and medications in order to deliver the most accurate information possible.

These drug specialists update responses to frequently asked questions and have to develop custom response letters that may require analyzing copious or rare amounts of scientific literature.


Read more about how a student is getting involved in the pharmaceutical industry here


Can AI in Healthcare Make This Work Simpler?

What if there is a faster and simpler way? Could there be a system for developing these responses that would eliminate the need to spend significant time conducting literature searches?

What if medical information specialists did not have to face the continuous obstacles of keeping up with the complexity and abundance of information available?

Similarly, what if providers and patients had access to information they need without going through the drug manufacturer?

Say Hello to GPT-3

This could all soon be possible with OpenAI’s latest language model, GPT-3.

OpenAI is an artificial intelligence lab based in San Francisco. In creating OpenAI this lab has made a system that contains a vast amount of text and information. What is unique is that this system has processing capabilities to generate a link between provided words.

What Can GPT-3 Do?  Ways to integrate AI in Healthcare

Here are some examples of what can be accomplished using the GPT-3 language model:

  • Create layouts based on their description, instead of typing in code to generate the output you desire
  • Explain programming languages such as Python using simple jargon
  • Generate a conversation between Albert Einstein and Sir Isaac Newton
  • Learn about various topics of your choosing from any individual that you desire. For example, you can learn how to execute a perfect fadeaway jumper from Michael Jordan himself!

The functionalities of GPT-3 could be monumental in the medical information function.

The Power of Machine Learning

Searching through medical information is made much easier as the technology uses the true meaning of a string of words as opposed to generating results by matching keywords.

How a medical information specialist might use GPT-3:

Suppose a medical information specialist was asked “Does Drug X cause leukopenia when taken with Drug Y?”

Current search process:

To access literature that could answer this question I would do a search on PubMed. In this search. I would get prompted with results corresponding to keywords from my search (such as leukopenia).

If the leukopenia is a rare incidence, responding to the question would be time consuming and challenging.  The medical information specialist would have to evaluate contributing factors such as the number of results and their relevance.

The GPT-3 technology would change this process completely.

A potential GPT-3 search process:

Using GPT-3 the medical information specialist could access PubMed and type the question into a browser plugin integrated with the GPT-3 technology. The Application Programming Interface (API) could produce results based on the context and meaning of your search. The results may not have the keyword “leukopenia” but the technology would be able to point you to the areas in the article(s) that answer your question based on the context.

Data Science and Semantic Search Technology

The contextual search technique described above is called semantic search technology   It could be integrated into many databases. Resources such as PubMed, Web of Science, various drug compendias (Lexicomp, UptoDate etc), drug manufacturer websites or the FDA labeling website might use them (side note – this could make searching for things like law based questions much easier!).

Additionally, GPT-3 can be plugged into cloud computing companies like Veeva Systems which provides data, software and services to support crucial functions ranging from R&D to commercial. It could also be integrated into internal documents including Clinical Summary Reports, Trials/Listings/Files, and other sources of raw data to generate medical information responses.

We may be able to use GPT-3 the technology to develop our medical information request responses all together!

Using the previous question “Does Drug X cause leukopenia when taken with Drug Y?”, it is possible to have the response generated immediately.  By using this technology to access the vast amount of information, analyze the data and format its own answer. This would reduce the burden on both the medical information specialist and the recipient by cutting down the time needed to conduct scientific research.

GPT-3 is still in its preliminary stage and there are several things that need to be improved and further discovered. However, such an innovation would be extremely beneficial and can affect the landscape of how various functions are performed within the pharmaceutical industry and healthcare systems.

Moving Forward with GPT-3 and Evolving Trends for AI in Healthcare:

I am currently on the waitlist to gain access to the API so I can participate in their private beta testing. It would be interesting to see the comparison of the medical information response letters generated by the AI to the responses prepared by drug manufacturers. 

Stay tuned for more about how OpenAI’s GPT-3 is continuing to make waves and shake things up for AI in healthcare.

burhanuddin shabbir
Dr. Burhanuddin Shabbir

Burhanuddin Shabbir, PharmD is a graduate from Pacific University School of Pharmacy who explores his passion for life sciences by conducting in depth evaluations of upcoming trends and innovations in the biotechnology and pharmaceutical space to examine how it can shape the future of healthcare.
Feel free to connect with him at www.linkedin.com/in/burhanuddinshabbir

Scroll to Top