AI can now Prescribe Medications
Artificial Intelligence Emerging Technology Medicine

AI Can Now Prescribe Medicine

on
March 17, 2021
Share this post now!
  • 21
  • 29
  • 4
  • 5
  • 2
  •  
  •  

AI and its ever-expanding skillset

Reading Time: 3 minutes

Is There Anything AI Can’t Do?

With artificial intelligence, the possibilities are endless.

These machines, models, and algorithms become more human every day – they basically squeeze the decision and discernment power of an active human brain into codes. The results already go beyond our limited capacity. Thus, that AI as the future of work and productivity is an understatement; it should be regarded as THE future.

Artificial intelligence can now prescribe medicine, and experts believe this will positively impact overall health.

Research shows medication-related errors are responsible for one out of 131 outpatient and one out of 854 inpatient deaths in the United States. The act of prescribing medicine is as complicated as it is vital, so medical experts must practice for years before gaining mastery. AI, however, is on the verge of replicating their skills and making prescribing as easy as clicking a button.

 

This is yet another example of artificial intelligence beating humans at their own game. For instance, autonomous AI models can already identify breast cancer better than teams of certified oncologists. It has also been recently reported that AI can successfully discern COVID-19 from cough sounds.

For now, let’s examine how AI models can prescribe medicine.

GPT-3: So Good It’s Scary, Literally

The internet has gone crazy for GPT-3 (Generative Pre-Training Transformer-3) from OpenAI. It is a third-generation machine learning model that designs websites, answers questions, and yes, prescribes medicine.

OpenAI has set the AI-world on fire with debates about safety before; the introduction of GPT-2 was met similarly.

Although GPT-2 boasted many benefits, critics termed it too dangerous because it could create writings that were indistinguishable from those penned by actual humans. It was TOO good.

At the time it was considered to be so dangerous, GPT-2 was only utilizing 124 million parameters of the possible 1.5 billion in its original design. Well, watch out. GPT-3 will feature a staggering 175 billion parameters.

GPT-3 is a neural-network-powered language model that predicts the likelihood of a sentence existing in the world. It leverages a generative model of languages (two neutral networks perfect each other by competition) and can acquire knowledge and process long-range dependencies by pre-training on diverse sets of written material with long stretches of contiguous text.

As a language processing model with the largest database of training sets ever at its disposal, experts believe it can answer medical-related questions, diagnose asthma, and prescribe medicine.  

Google’s Prescribing Model

As powerful as GPT-3 is, it is not the first AI-based model capable of prescribing medicine. Google’s AI could predict the scripts a physician would write with up to 75% accuracy.

The most significant setback of Google’s AI is that it is rooted in historical data. It can only replicate the physician’s prescription patterns and not their ever-expanding knowledge of medication and side effects.

Based on the researchers’ submission however, the system, if appropriately applied to healthcare, could assist physicians in identifying abnormal or incorrect prescriptions. It would work similarly to the fraud detection programs that banks employ.

Takeaways

 

1. Artificial intelligence is our future – that becomes clearer and clearer every day.

2. AI can reduce the human error associated with prescriptions.

3. OpenAI and Google are well on their way to providing AI solutions that will correctly prescribe medicine.

 

Comment and share! For more content related to technology and medicine, check out AIM Blog.

 

Recent Posts

Did you like this post?

Share this post now!
  • 21
  • 29
  • 4
  • 5
  • 2
  •  
  •  
TAGS
RELATED POSTS
2 Comments
  1. Sohail Merchant
    Reply

    Sohail Merchant

    March 21, 2021

    Q1) “Great read! Interesting to learn how the use of AI is disrupting “white collar” spaces as well. Curious on your thoughts regarding the use of AI when it comes to patient care or surgery?”

    A1) I could speak for weeks on this topic alone. AI impacts or potentially impacts almost every single sector of healthcare/medicine. Some of the most common examples include identifying fraudulent transactions, physicians billing too much for patients (another form of fraud). Radiologists use an AI mechanism called computer vision (so do self-driving cars), which identifies lung lesions such as pulmonary emboli or pneumonia, as an example.

    Pixels work as phenomenal inputs in neural networks. For example, their color and the change in color from one pixel to an adjacent pixel help identify things like the edges of a picture. In reality, I think the concern for many of the physicians I know is that they wonder if AI will take their jobs. Artificial intelligence is more of a tool that needs guidance in the right direction, and a physician would mainly set that direction.

    There are five levels of autonomy in AI preached by Eric Topol, and it’s probably better to check and balance a system by keeping them at level 3. I won’t go into that too much, but it is an easy google search away.

    When it comes to surgery, there are some serious advancements with equally accompanying concerns. Currently, there is a great robot called da Vinci. I believe in its current model, there is no significant AI (I could be wrong because I haven’t checked in a while). There are talks about new updates and models that incorporate AI to make precise movements and identify structures within the bodies’ cavities. AI’s ability to identify structures actively exists with machines like some new ultrasound machines, plus others. That’s easy! It is often challenging to discern between certain body structures during an operation until you find specific landmarks to guide you. These landmarks are pretty much only good if the patient is of normal anatomy, which is usually the case.

    As far as surgery goes, AI’s goal is to have a robot that could pretty much do the surgery without much active assistance while still having a team of physicians on standby for oversight or technical issues.

    A book on AI and healthcare is coming out very soon, where I have written approximately seven chapters in detail on answering these exact questions.

    Q2) “Do you see AI use growing in those spaces as well? ”

    A2) Oh yes, AI is already expanding at what feels like a log scale. Things are happening fast. I think it worries me that a fast expansion at such a great magnitude may create huge gaps between hospitals with money versus hospitals without money- a challenging problem with a similar parallel between rich growing richer and poor becoming poorer.

    Introducing various AI technologies is already done at vertical and horizontal scales. A challenging part is identifying an organization’s technological readiness and then implementing an infrastructure that will gain enough traction to stay.

    We use dictation software (eg., nuance dragon, mModal) regularly. In fact, I am using dictation software to dictate this response right now (hence extra gibberish). Dictation software uses an AI mechanism called natural language processing (nlp) to identify words. This mechanism increases its precision with increased use. By adding more data, we increase precision akin to increasing sample size, thereby increasing an experiment’s statistical power. NLP is helpful for physicians in the field and anyone who dictates anything with things like “SIRI.”

    As I mentioned earlier, I see growth in a multitude of areas of medicine/healthcare. If we can bring AI innovation to areas where they are not as technologically rich we can help close the technological gap between wealthy hospitals and not so wealthy hospitals.

    Q3) “Lastly, how has the emergence of Blockchain technology started to manifest in the health care space? Appreciate the insights again!”

    A3) Medicine/healthcare implements blockchain for applications such as securing casual records on specific platforms accessible to hospitals and administrators. Another use for blockchain is patient identity information protection by companies like Medical Chain. I’ve also seen companies like Simply Vital using blockchain for open-source databases allowing healthcare providers to access patient information, create/build secure contracts, and increase data integrity.

    Comment rating
  2. Reply

    Devon Watts

    March 17, 2021

    Great read! Interesting to learn how the use of AI is disrupting “white collar” spaces as well. Curious on your thoughts regarding the use of AI when it comes to patient care or surgery? Do you see AI use growing in those spaces as well? Lastly how has the emergence of Blockchain technology started to manifest in the health care space? Appreciate the insights again!

    Comment rating

LEAVE A COMMENT

SOHAIL MERCHANT
Youngstown, Ohio

Medical Doctor (M.D.); Research Fellow at Lumen Foundation Artificial Intelligence Division

Signup Form

Sign up for the newsletter and receive our free Ebook!

Search

Sign up now and receive our Health and Fitness Apps Ebook for free!

You have Successfully Subscribed!

Sign up now and receive our Health and Fitness Apps Ebook for free!

You have Successfully Subscribed!