Innovgas | Optimising Anaesthetics

View Original

The machine knows what you are thinking

What is artificial intelligence?

Artificial intelligence or AI has been in the news a great deal recently. ChatGPT was launched by OpenAI in November 2022 and because of a partnership, Microsoft will add ChatGPT to its Bing search engine. This launch created some anxiety at Google, the market leading search engine and so they announced the launch of Bard, which will be built into the Google search engine. Both ChatGPT and Bard are chatbots and signal the next evolutionary step in internet search engines.

A chatbot is a computer program that uses AI and natural language processing (NLP) to understand customer questions and automate responses to them, simulating human conversation. Chatbot technology is everywhere these days, from the smart speakers at home to messaging applications in the workplace. They can use audio input, such as Apple's Siri, Google Assistant and Amazon Alexa, or interact with you via SMS text messaging.

Introducing ChatGPT

‘ChatGPT  is an advanced conversational AI tool that can remember user interactions and offer far more comprehensive responses than other AI tools. When you ask a question or make a request, ChatGPT will analyse your query and generate a response based on what it has learned from its training data. ChatGPT also offers a more extensive database that allows for deeper dialogue and more accurate responses than Alexa or Siri are currently capable of providing. Alexa and Siri will give you answers to a question about Italian restaurants near to you. ChatGPT could write this blog for me if I asked it the right question.

Although this area of AI grabs the headlines, the use of AI in medicine has been making progress and its presence can now be seen in many areas of medicine. Some of the brightest minds on the planet work in AI and it’s not easy to understand. I’ll try to make that easier by looking at the processes that make up the science of AI.

ChatGPT User Interface

The speciality can be sub divided into:

  1. Machine Learning (ML). In this area AI uses data and algorithms to imitate the way that humans learn, gradually improving its accuracy. The system can then perform tasks with or without supervision.

  2. Natural Language Processing (NLP). This technology enables computers to process human language in the form of text or voice data and to understand its full meaning. This is what Alexa and Siri use.

  3. Artificial Neural Networks (ANN). Now it gets complicated. Inspired by the structure of the brain artificial neural networks are comprised of a node layers, containing an input layer, one or more hidden layers, and an output layer. These networks rely on training data to learn and improve their accuracy over time. Once these learning algorithms are fine-tuned for accuracy, they are powerful tools in artificial intelligence, allowing us to classify and cluster data at high speed.

  4. Deep Learning (DL). This is really ANN but is comprised of a number of neural networks. This allows analysis and interpretation of large sets of data.

  5. Computer Vision. This technology is used for visual search to recognize details and patterns in medical images and videos and take actions or make recommendations based on that information.

  6. Convolutional Neural Network (CNN). This is another form of ANN that is particularly useful in many visual applications such as image classification.

A video camera on a stand with robotic arm

If most of that went whistling over your head, you are not alone. Unless you work in AI on a day-to-day basis it can be difficult to understand. I have tried to explain the basics to make the point  that sophisticated and expensive computing is now being deployed in 21st century medicine. AI happens in the background. What is really important is the patient facing end of this. Does all this sophisticated technological wizardry result in improved patient outcomes? Is it safer for the patient? Are patients diagnosed and treated quicker? Despite the initial costs of AI, does the healthcare system save money? It’s important to remember that sometimes you have to make the investment up front to make savings further down the line.

Da Vinci robot during surgery

To illustrate the answers to these questions, let’s look at a few examples where AI is making an enormous impact

Cardiology

In Cardiology, AI in smartphones and internet-based technology enables at risk cardiac patients to be monitored at home. AI enables early detection of cardiac events meaning the patient can be recalled to hospital before the event occurs. This ensures a better outcome for the patient and saves money through saved bed days and avoiding emergency procedures.

Surgical Procedures

In surgical procedures, AI enabled Da Vinci machines carry out operations through several small incisions in the body as opposed to one large incision. This lessens the insult on the body and reduces patient recovery time from four days to one, freeing up beds, enabling more procedures and reducing costs through reduced nurse time and the use of consumables.

Oncology

In oncology, algorithms are trained to spot the difference between normal tissue and a tumour. Doctors still quality control the results but the diagnosis is quicker and fewer doctors are needed. In 2020, it was reported that an AI algorithm developed by the University of Pittsburgh achieved the highest accuracy to date in identifying prostate cancer, with 98% sensitivity and 97% specificity. Again, this can result in better outcomes for the patient reducing the costs incurred through unnecessary hospital appointments.

Gastroenterology

In gastroenterology, endoscopies and colonoscopies enhanced with AI allows rapid detection of abnormal tissue and early disease giving a better outcome for the patient and reducing hospital time.

Summary

There are many more examples I could use. The story is the same.  Upfront investment in AI leads to a better and safer outcome for the patient and the big win-win is the hospital saves money and becomes more productive.

EyePro, NoPress and BiteMe require a small upfront investment compared to what is currently used. However, using them routinely will lead to a better and safer outcome for your patients and in the long run save your hospital money. Request your free sample today and see for yourself.


Author: Niall Shannon, European Business Manager, Innovgas

This article is based on research and opinion available in the public domain.

See this content in the original post

Interested in a Free Sample?

Free samples of NoPress, EyePro & BiteMe available upon request.
Conditions apply.

See this form in the original post