BEGIN WITH  THE BASICS

An introduction to concepts
of artificial intelligence.

CONCEPTS OF ARTIFICIAL INTELLIGENCE

WHAT IS AN ALGORITHM? 

A computer algorithm is a sequence of instructions provided to solve a class of problems or perform a computation.

WHAT IS ARTIFICIAL INTELLIGENCE (AI) AND HOW DOES IT WORK?

Artificial intelligence is an overarching term for intelligent machines or technologies that can emulate the functions of the human brain, and replicate human capabilities such as decision-making, problem-solving, reasoning, visual perception and speech recognition. AI has the ability to learn through situations that are derived from patterns or features of data. Machine learning (ML), neural networks, and deep learning (DL) are all subsets of AI.

WHAT IS MACHINE LEARNING (ML) AND HOW DOES IT WORK?

Machine learning is one of the most exciting and promising areas in AI. ML is a subset of AI. It employs algorithms that learn from data to make predictions or decisions, and its performance improves with experience. ML gives computers the ability to learn without being explicitly programmed. ML algorithms can be developed to be "locked" so that its function does not change, or "adaptive" so its performance can adapt over time based on new inputs.
Illustration of infographic of artificial intelligence, machine learning, and deep learning.

WHAT IS DEEP LEARNING (DL) AND HOW DOES IT WORK?

Deep learning is a specialized subset of ML, utilizing multi-layered (sometimes 100+ layers) deep neural networks to build algorithms that teach systems to perform tasks on their own, based on large sets of data. DL is one type of ML algorithm and therefore a subset of ML.

WHAT IS TRAINING DATA?

Training data is labeled data used to teach AI or machine learning algorithms to make proper decisions. The data must be robust to provide the most suitable outcomes for AI in clinical practice. The training data should be relevant to real-life scenarios and contain variability that ensures the viability of the AI being addressed and created. 
 
For example, for a visual recognition problem, the training data or training set must properly represent all the variability that may be encountered. This can include the various perspectives on the subject, illumination, deformation, occlusions of object, background clutter, and interclass variation of the object. When the training data is robust, it will increase the likelihood of the AI algorithms meeting a solution.

WHAT IS NATURAL LANGUAGE PROCESSING (NLP) AND WHAT ARE THE APPLICATIONS IN HEALTHCARE? 

Natural language processing is a subfield of AI concerned with the interactions between computers and human language. In particular, how to program computers to process and analyze large amounts of data. NLP is used to comprehend speech or text to extract its meaning. The result is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them. NLP can then accurately extract information and insights contained in the documents as well as categorize and organize the documents themselves.
 
NLP systems can be used to evaluate how to optimize the patient experience, reduce costs and improve care outcomes that are hidden in unstructured data. This capability is valuable across various use cases in healthcare today:
 
  • Speech recognition
  • Improvement in clinical documentation
  • Data mining research
  • Computer-assisted coding
  • Automated reporting
As AI algorithms improve through NLP, there are use cases emerging that will have impact: 
 
  • Clinical trial matching
  • Prior authorization
  • Clinical decision support
  • Risk adjustment
  • Population health management and analytics
Healthcare organizations can use NLP to transform the way they deliver care and manage solutions. Organizations can use ML in healthcare to improve provider workflows and patient outcomes.

WHAT IS THE DIFFERENCE BETWEEN COMPUTER-AIDED DETECTION (CADE) AND COMPUTER-AIDED DIAGNOSIS (CADX)?

The definitions the FDA adheres to are as follows: a radiological CADe device is “intended to identify, mark, highlight or otherwise direct attention to portions of an image […] that may reveal abnormalities during interpretation of images by the clinician.” A CADx device is “intended to provide information beyond identifying […] abnormalities, such as an assessment of disease.” Whenever software is not intended to highlight an abnormality, it is not considered a CADe nor a CADx device. For example, segmentation of brain structures is not considered CADe, while the detection of a tumor candidate is considered CADe. An algorithm that adds information on tumor grade would make it a CADx device. 
Photo of a 3D illustration of a network abstract background.

Discover the suitable applications of artificial intelligence

The application of AI in healthcare has many potential benefits to physicians, patients, and healthcare systems alike.

LEADING THE WAY IN GI HEALTH

See the opportunities available now for using AI in gastroenterology.

SEE THE SOLUTION

PHYSICIAN PODCAST SERIES

Hear from experts using AI to detect and treat cancer sooner.

LISTEN NOW

CHANGING GI HEALTH WITH AI

Learn how artificial intelligence is shaping the future of GI care.

SEE HOW

Disclaimer: All content from healthcare professionals is their individual conclusions, unless otherwise cited. All speaker or author engagement for content is noted to acknowledge funding from Covidien LP, a Medtronic company, for any consulting engagement.

Sign Up

Sign up for new AI education resources.

Sign Up