Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

ARTIFICIAL INTELLIGENCE IN HEALTHCARE

IP.com Disclosure Number: IPCOM000250348D
Publication Date: 2017-Jul-04
Document File: 6 page(s) / 944K

Publishing Venue

The IP.com Prior Art Database

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 55% of the total text.

ARTIFICIAL INTELLIGENCE IN HEALTHCARE

BACKGROUND

 

The present disclosure relates generally to artificial intelligence (AI) and more particularly to artificial intelligence in healthcare.

Artificial intelligence is the ability of a machine to mimic or exceed human intelligence. AI is the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision making and translation between languages.

Over the years, artificial intelligence has refined into machine learning and machine learning has further refined into deep learning, as depicted in Figure 1.

Image Source: https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/

Figure 1

Figure 2 depicts the artificial intelligence trajectory. The first generation of artificial intelligence was started from year 1956, whereas 2011 onwards the second generation of AI has evolved as deep learning.

Figure 2

As depicted in figure 3, deep learning works by refining the image into thousand dimension description vectors and further classifying the image into each object ID (identification)

Figure 3

Figure 4 depicts the difference between first generation AI and second generation AI. The first generation of AI includes conventional machine learning, whereas second generation of AI includes deep learning.

Figure 4

Figure 5 depicts the success rates on image net visual recognition challenge between first generation AI and second generation AI. The human recognition level occurs at ninety five percentages.

Figure 5

It would be desirable to have an artificial intelligence support in healthcare.

BRIEF DESCRIPTION OF DRAWINGS

Figure 1 depicts the artificial intelligence timeline with examples taken from a blog on NVIDIA’s website (https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intell...