Artificial intelligence in diabetes care

Artificial intelligence in diabetes care IntroductionMedical artificial intelligence (AI) is moving forward at considerable pace. Promising research ideas are surfacing in clinical waters; AI is automating the national 111 triage service and has exhibited dermatologist‐level performance at identifying suspicious skin lesions, a task where experts frequently disagree . The present article explores how machine learning, a prominent branch of AI, may be set to transform diabetes care.What is machine learning?Machine learning finds relationships within data; for example, a linear regression proposes a ‘line of best fit’ relationship. Such simple representations may struggle, however, to describe more complex data, as shown in Fig. . When clinical guidelines are based on simple models, they might fail to make allowances for the enormous variability found in a person's genome, medical history and their behaviours. By contrast, AI research has developed machine learning techniques that can model very large datasets with multiple, non‐linear relationships. For example, a ‘neural network’ represents data as vast numbers of interconnected neurons, analogous to the human brain; therefore, such models can approach clinical problems in a similar fashion to a clinician by integrating numerous sources of disparate information and providing a personalized solution.(a) and (b) Machine learning reveals important relationships in complex data: an http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Diabetic Medicine Wiley

Artificial intelligence in diabetes care

Loading next page...
 
/lp/wiley/artificial-intelligence-in-diabetes-care-xdPCmilSPV
Publisher
Wiley Subscription Services, Inc., A Wiley Company
Copyright
Diabetic Medicine © 2018 Diabetes UK
ISSN
0742-3071
eISSN
1464-5491
D.O.I.
10.1111/dme.13587
Publisher site
See Article on Publisher Site

Abstract

IntroductionMedical artificial intelligence (AI) is moving forward at considerable pace. Promising research ideas are surfacing in clinical waters; AI is automating the national 111 triage service and has exhibited dermatologist‐level performance at identifying suspicious skin lesions, a task where experts frequently disagree . The present article explores how machine learning, a prominent branch of AI, may be set to transform diabetes care.What is machine learning?Machine learning finds relationships within data; for example, a linear regression proposes a ‘line of best fit’ relationship. Such simple representations may struggle, however, to describe more complex data, as shown in Fig. . When clinical guidelines are based on simple models, they might fail to make allowances for the enormous variability found in a person's genome, medical history and their behaviours. By contrast, AI research has developed machine learning techniques that can model very large datasets with multiple, non‐linear relationships. For example, a ‘neural network’ represents data as vast numbers of interconnected neurons, analogous to the human brain; therefore, such models can approach clinical problems in a similar fashion to a clinician by integrating numerous sources of disparate information and providing a personalized solution.(a) and (b) Machine learning reveals important relationships in complex data: an

Journal

Diabetic MedicineWiley

Published: Jan 1, 2018

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off