Cancerworld Magazine
  • About the Magazine
    • Editorial Team
    • Leadership and Management
    • Events
    • Magazine
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
    • Partnership
    • Supported contents
  • Media Corner
    • Journalist Cancer Guide
    • Cancer Journalism Award
    • Cancer Journalist Grant
NEWSLETTER  |  PRINT VERSION
Facebook
Twitter
LinkedIn
Cancerworld Magazine
Cancerworld Magazine
  • About the Magazine
    • Editorial Team
    • Leadership and Management
    • Events
    • Magazine
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
    • Partnership
    • Supported contents
  • Media Corner
    • Journalist Cancer Guide
    • Cancer Journalism Award
    • Cancer Journalist Grant
Cancerworld Magazine > News > Artificial intelligence is prone to overdiagnosis
  • News

Artificial intelligence is prone to overdiagnosis

  • 7 January 2020
  • Elena Riboldi
Artificial intelligence is prone to overdiagnosis
Total
0
Shares
0
0
0
0
0

The use of artificial intelligence might increase the speed and the consistency of cancer diagnosis, but could also exacerbate the problem of overdiagnosis, according to a perspective article recently published in the New England Journal of Medicine by Adewole Adamson and Gilbert Welch, who suggest that this risk may be mitigated by overcoming the dichotomous classification between “cancer” and “not cancer”.

Supervised machine learning consists in the generation of decision-making algorithms starting from sets of images that pathologists have categorized as either “cancer” or “not cancer.” “The computer system learns by judging its diagnosis against the external standard of pathological interpretation” Adewole Adamson, assistant professor of Internal Medicine at Dell Medical School at the University of Texas, explains. “Reliance on this external standard is problematic, however, since machine learning doesn’t solve the central problem associated with cancer diagnosis: the lack of a histopathological gold standard.”

There is no single right answer to the question: “What constitutes cancer?” In fact, some microscopic cellular abnormalities may meet the pathological definition of cancer but may not be destined to cause symptoms or death. Since AI allows to analyse images in a faster and cheaper way, clinicians may be encouraged to request more exams, boosting opportunities for overdiagnosis.

“One approach to mitigating this problem would be to make use of the information manifested by disagreements regarding pathology” Gilbert Welch, senior investigator at Brigham’s Centre for Surgery and Public Health, Brigham Women’s Hospital in Boston, suggests. “In other words, using an external

standard based on judgments from a diverse panel of pathologists, algorithms could be trained to discriminate among three categories: total agreement regarding the presence of cancer, total agreement regarding the absence of cancer, and disagreement regarding whether cancer is present.” Lesions that are of uncertain significance should deserve further attention by the pathologist and, possibly, a conservative approach from the oncologist.

“Ultimately, what matters to patients and clinicians is whether the diagnosis of cancer has relevance to the length or quality of life” the authors conclude. “We believe that the possibility of training machine-learning algorithms to recognize an intermediate category between “cancer” and “not cancer” should be given serious consideration before this technology is widely adopted.”

Total
0
Shares
Share 0
Tweet 0
Share 0
Share 0
Share 0
Related Topics
  • Artificial intelligence
  • cancer
  • diagnosis
  • machine learning
  • overdiagnosis
Elena Riboldi

Previous Article
  • Voices

A Global Licence for Breast Surgery – my call to action!

  • 19 September 2016
  • Shirley Bianca
View Post
Next Article
  • Articles
  • Practice Points

Tackling resistance to anti-EGFR therapies, from challenges to re-challenge

  • 7 January 2020
  • Cristina Ferrario
View Post
You May Also Like
View Post
  • News

US study suggests colorectal cancer screening should start at age 45

  • Janet Fricker
  • 25 May 2022
View Post
  • News

Multicomponent prevention strategy reduces risk of cancer

  • Janet Fricker
  • 20 May 2022
View Post
  • News

Lumpectomy as effective as mastectomy in young breast cancer patients

  • Janet Fricker
  • 13 May 2022
View Post
  • News

Multi organ chip could facilitate personalised cancer therapy 

  • Janet Fricker
  • 12 May 2022
View Post
  • News

100,000 Genomes Project pinpoints new cancer genetic culprits

  • Janet Fricker
  • 29 April 2022
View Post
  • News

IL-6 provides missing link between exercise and colon cancer protection

  • Janet Fricker
  • 28 April 2022
View Post
  • News

CAR T-cell therapy shows efficacy in solid tumours

  • Janet Fricker
  • 20 April 2022
View Post
  • News

No link between brain tumours and ‘usual’ use of mobile phones

  • Janet Fricker
  • 14 April 2022

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

search
or search in Cancerworld archive
Newsletter

Subscribe free to
Cancerworld!

We'll keep you informed of the latest features and news with a fortnightly email

Subscribe now
Latest News
  • US study suggests colorectal cancer screening should start at age 45
    • 25 May 2022
  • Multicomponent prevention strategy reduces risk of cancer
    • 20 May 2022
  • Lumpectomy as effective as mastectomy in young breast cancer patients
    • 13 May 2022
  • Multi organ chip could facilitate personalised cancer therapy 
    • 12 May 2022
  • 100,000 Genomes Project pinpoints new cancer genetic culprits
    • 29 April 2022
Article
  • Cervical cancer: Rebuilding a nation’s broken trust in their screening service
    • 25 May 2022
  • What can we expect from mRNA cancer vaccines?
    • 13 May 2022
  • Sri Lanka cancer care hit by foreign currency crisis
    • 6 May 2022
Latest printed issue
Social

Would you follow us ?

Contents
  • Message from a Ukrainian oncologist: Please prioritise my patients ‒ if you don’t who will?
    • 19 April 2022
  • Pandemics, War, Reconstruction and the Duty of Medicine and Science
    • 4 April 2022
  • Crisis in the Ukraine: we can help by doing what we do best
    • 4 March 2022
MENU
  • About the Magazine
    • Editorial Team
    • Leadership and Management
    • Events
    • Magazine
    • Archive
    • Contacts
  • Articles
    • Policy
    • Practice Points
    • Delivery of Care
    • Biology basic
    • Medicine
    • Featured
  • Contents
    • News
    • Editorials
    • Interviews to the Expert
    • In the Hot Seat
    • Profiles
    • Obituaries
    • Voices
    • Partnership
    • Supported contents
  • Media Corner
    • Journalist Cancer Guide
    • Cancer Journalism Award
    • Cancer Journalist Grant
Cancerworld Magazine
  • About the Magazine
  • Articles
  • Media Corner
  • Privacy Policy
  • Cookie Policy

Cancerworld is funded by SPCC Sharing Progress in Cancer Care | Piazza Indipendenza 2, 6500 Bellinzona - Switzerland | info@spcc.net

Archivio Cancerworld

Input your search keywords and press Enter.