Skip to content
  • About
  • Contact
  • Contribute
  • Book
  • Careers
  • Podcast
  • Recommended
  • Speaking
  • All
  • Physician
  • Practice
  • Policy
  • Finance
  • Conditions
  • .edu
  • Patient
  • Meds
  • Tech
  • Social
  • Video
    • All
    • Physician
    • Practice
    • Policy
    • Finance
    • Conditions
    • .edu
    • Patient
    • Meds
    • Tech
    • Social
    • Video
    • About
    • Contact
    • Contribute
    • Book
    • Careers
    • Podcast
    • Recommended
    • Speaking

The clinical AI revolution: 3 things to know

Tim O’Connell, MD
Tech
October 18, 2023
Share
Tweet
Share

The use of natural language processing (NLP) in the clinical domain dates as far back as the 1960s, with important early work performed in the 1970s and 1980s. While great technical advances were made during this period, clinical NLP failed to live up to initial expectations as accuracy rates were too low to use for much other than research or bulk analytics.

An AHIMA article explained why clinical text poses a challenge to NLP this way: This text is often ungrammatical, consists of “bullet point” telegraphic phrases with limited context, and lacks complete sentences. Clinical notes make heavy use of acronyms and abbreviations, making them highly ambiguous.

Further, traditional NLP has struggled to disambiguate words and phrases that may have multiple meanings in a medical context. For example, the two-letter acronym “PT” is commonly used to mean “patient,” “physiotherapy,” “posterior tibial” (as in the pulse site), “prothrombin time,” a common blood test – and depending on where the patient’s records are coming from, may even refer to the country of Portugal.

Given these shortcomings, it’s no surprise that clinicians have been hesitant to embrace a technology incapable of accurately interpreting information contained within unstructured data – which comprises 80 percent of all data in EHRs, based on industry estimates.

But recent advances in artificial intelligence (AI), large language models (LLMs), and large-scale data extraction tools have spawned a new generation of medical NLP technologies that meet the stringent needs of both clinicians at the point of care and researchers who require high-quality patient data.

Unlike traditional NLP software, modern medical AI platforms are truly clinical grade, possessing the ability to understand medical text shorthand and abbreviations. Often based on “transformers,” a new type of machine learning model, deep learning algorithms are starting to unlock the clinical value buried within unstructured medical text.

Overcoming doubt and confusion

While these are exciting developments, clinicians may be reluctant to put their faith in new technologies which sound similar to the traditional NLP that to date has underperformed. Another factor that may be causing confusion in the health care sector is the rise of generative AI algorithms such as ChatGPT, which come with their own set of considerable problems.

The vast majority of clinicians and other health care professionals are not technologists or well-versed in LLMs, so you can’t blame them for not immediately understanding 1) what medical-grade AI can do for them and their patients, and 2) how it differs from traditional NLP and generative AI.

Below are three things health care professionals should know about medical-grade AI.

Medical-grade AI can understand and extract unstructured data at scale. Medical-grade AI isn’t just an incremental improvement over traditional NLP; it’s a quantum leap, based on its ability to extract, normalize, and contextualize unstructured medical text. That’s because medical AI is powered by machine learning and LLMs that have been developed only in recent years.

While a generative AI interface may appear useful for question-answering tasks about a single document, clinicians need AI systems that can ingest and understand an entire chart for a patient, or an entire organization’s EHR system. Medical-grade AI is enterprise software that has been designed to process and understand millions of documents, not just a short snippet of text.

Unlike generative AI, medical-grade AI doesn’t “hallucinate.” ChatGPT and other generative AI programs currently are notorious for inventing facts, such as citing research papers and authors that don’t actually exist. This presents a clear danger to patients’ lives if relied upon in many clinical scenarios.

ADVERTISEMENT

Instead, medical AI strikes a balance between recall and precision, giving clinicians the right amount of accurate and relevant data at the point of care, and linking information back to the original data in the patient’s chart, allowing clinicians to check their sources of information for veracity and accuracy.

Medical-grade AI algorithms rely on input from clinicians. Computer scientists and machine learning professionals who typically build traditional NLP software for use in health care frequently lack the medical expertise to understand what type of information would be useful to a clinician or what questions clinicians need answered.

The most effective medical AI platforms are built with a right-brain/left-brain approach using the expertise of working side-by-side with computer scientists to ensure that the AI models understand the important meanings of medical words and the subtleties that often exist in clinical language.

Embrace AI that’s ready for clinicians.

Medical-grade AI is ready, today, built upon the latest technologies, and has hundreds of use cases in clinical medicine, research, administration, and health insurance. Users should be wary of general-purpose generative AI models masquerading as medical-grade AI, and should work with enterprise software vendors who have built products from the ground up specifically to help them transform healthcare and medical research.

Tim O’Connell is a physician executive.

Prev

Bringing words to a knife fight: Why we're losing the health care war

October 18, 2023 Kevin 1
…
Next

The Israeli-Palestinian conflict, and why medical professionals should care

October 18, 2023 Kevin 3
…

Tagged as: Health IT

Post navigation

< Previous Post
Bringing words to a knife fight: Why we're losing the health care war
Next Post >
The Israeli-Palestinian conflict, and why medical professionals should care

ADVERTISEMENT

ADVERTISEMENT

ADVERTISEMENT

Related Posts

  • Are negative news cycles and social media injurious to our health?

    Rabia Jalal, MD
  • How social media can help or hurt your health care career

    Health eCareers
  • Sharing mental health issues on social media

    Tarena Lofton
  • 3 ways to advance the credibility of online health information

    Robert Pearl, MD
  • Digital health equity is an emerging gap in health

    Joshua W. Elder, MD, MPH and Tamara Scott
  • Improve mental health by improving how we finance health care

    Steven Siegel, MD, PhD

More in Tech

  • Health care’s data problem: the real obstacle to AI success

    Jay Anders, MD
  • What ChatGPT’s tone reveals about our cultural values

    Jenny Shields, PhD
  • Bridging the digital divide: Addressing health inequities through home-based AI solutions

    Dr. Sreeram Mullankandy
  • Staying stone free with AI: How smart tech is revolutionizing kidney stone prevention

    Robert Chan, MD
  • Medical school admissions are racing toward an AI-driven disaster

    Newlyn Joseph, MD
  • AI in health care: the black box of prior authorization

    P. Dileep Kumar, MD, MBA
  • Most Popular

  • Past Week

    • What’s driving medical students away from primary care?

      ​​Vineeth Amba, MPH, Archita Goyal, and Wayne Altman, MD | Education
    • A faster path to becoming a doctor is possible—here’s how

      Ankit Jain | Education
    • Make cognitive testing as routine as a blood pressure check

      Joshua Baker and James Jackson, PsyD | Conditions
    • The dreaded question: Do you have boys or girls?

      Pamela Adelstein, MD | Physician
    • A world without antidepressants: What could possibly go wrong?

      Tomi Mitchell, MD | Meds
    • Rethinking patient payments: Why billing is the new frontline of patient care [PODCAST]

      The Podcast by KevinMD | Podcast
  • Past 6 Months

    • What’s driving medical students away from primary care?

      ​​Vineeth Amba, MPH, Archita Goyal, and Wayne Altman, MD | Education
    • The silent crisis hurting pain patients and their doctors

      Kayvan Haddadan, MD | Physician
    • Internal Medicine 2025: inspiration at the annual meeting

      American College of Physicians | Physician
    • What happened to real care in health care?

      Christopher H. Foster, PhD, MPA | Policy
    • Are quotas a solution to physician shortages?

      Jacob Murphy | Education
    • The hidden bias in how we treat chronic pain

      Richard A. Lawhern, PhD | Meds
  • Recent Posts

    • Why great patient outcomes don’t protect female doctors from burnout [PODCAST]

      The Podcast by KevinMD | Podcast
    • Why ADHD in women is finally getting the attention it deserves

      Arti Lal, MD | Conditions
    • How a $75 million jet brought down America’s boldest doctor

      Arthur Lazarus, MD, MBA | Physician
    • Why ruling out sepsis in emergency departments can be lifesaving

      Claude M. D'Antonio, Jr., MD | Conditions
    • The hidden cost of delaying back surgery

      Gbolahan Okubadejo, MD | Conditions
    • Precision and personalization: Charting the future of cancer care [PODCAST]

      The Podcast by KevinMD | Podcast

Subscribe to KevinMD and never miss a story!

Get free updates delivered free to your inbox.


Find jobs at
Careers by KevinMD.com

Search thousands of physician, PA, NP, and CRNA jobs now.

Learn more

View 1 Comments >

Founded in 2004 by Kevin Pho, MD, KevinMD.com is the web’s leading platform where physicians, advanced practitioners, nurses, medical students, and patients share their insight and tell their stories.

Social

  • Like on Facebook
  • Follow on Twitter
  • Connect on Linkedin
  • Subscribe on Youtube
  • Instagram

ADVERTISEMENT

ADVERTISEMENT

ADVERTISEMENT

ADVERTISEMENT

  • Most Popular

  • Past Week

    • What’s driving medical students away from primary care?

      ​​Vineeth Amba, MPH, Archita Goyal, and Wayne Altman, MD | Education
    • A faster path to becoming a doctor is possible—here’s how

      Ankit Jain | Education
    • Make cognitive testing as routine as a blood pressure check

      Joshua Baker and James Jackson, PsyD | Conditions
    • The dreaded question: Do you have boys or girls?

      Pamela Adelstein, MD | Physician
    • A world without antidepressants: What could possibly go wrong?

      Tomi Mitchell, MD | Meds
    • Rethinking patient payments: Why billing is the new frontline of patient care [PODCAST]

      The Podcast by KevinMD | Podcast
  • Past 6 Months

    • What’s driving medical students away from primary care?

      ​​Vineeth Amba, MPH, Archita Goyal, and Wayne Altman, MD | Education
    • The silent crisis hurting pain patients and their doctors

      Kayvan Haddadan, MD | Physician
    • Internal Medicine 2025: inspiration at the annual meeting

      American College of Physicians | Physician
    • What happened to real care in health care?

      Christopher H. Foster, PhD, MPA | Policy
    • Are quotas a solution to physician shortages?

      Jacob Murphy | Education
    • The hidden bias in how we treat chronic pain

      Richard A. Lawhern, PhD | Meds
  • Recent Posts

    • Why great patient outcomes don’t protect female doctors from burnout [PODCAST]

      The Podcast by KevinMD | Podcast
    • Why ADHD in women is finally getting the attention it deserves

      Arti Lal, MD | Conditions
    • How a $75 million jet brought down America’s boldest doctor

      Arthur Lazarus, MD, MBA | Physician
    • Why ruling out sepsis in emergency departments can be lifesaving

      Claude M. D'Antonio, Jr., MD | Conditions
    • The hidden cost of delaying back surgery

      Gbolahan Okubadejo, MD | Conditions
    • Precision and personalization: Charting the future of cancer care [PODCAST]

      The Podcast by KevinMD | Podcast

MedPage Today Professional

An Everyday Health Property Medpage Today
  • Terms of Use | Disclaimer
  • Privacy Policy
  • DMCA Policy
All Content © KevinMD, LLC
Site by Outthink Group

The clinical AI revolution: 3 things to know
1 comments

Comments are moderated before they are published. Please read the comment policy.

Loading Comments...