• Sign In
  • Sign Out
  • My Account
Subscribe
  • BioWorld
  • BioWorld MedTech
  • BioWorld Asia
  • BioWorld Science
  • Data Snapshots
  • Special reports
Clarivate
  • Data Snapshots
  • BioWorld
  • BioWorld MedTech
  • Infographics: Dynamic digital data analysis
  • Index insights
  • Special reports
  • Infographics: Dynamic digital data analysis
  • Trump administration impacts
  • Biopharma M&A scorecard
  • BioWorld 2024 review
  • BioWorld MedTech 2024 review
  • BioWorld Science 2024 review
  • Women's health
  • China's GLP-1 landscape
  • PFA re-energizes afib market
  • China CAR T
  • Alzheimer's disease
  • Coronavirus
  • More reports can be found here

BioWorld. Link to homepage.

Clarivate
  • BioWorld
  • BioWorld MedTech
  • BioWorld Asia
  • BioWorld Science
  • Data Snapshots
    • BioWorld
    • BioWorld MedTech
    • Infographics: Dynamic digital data analysis
    • Index insights
  • Special reports
    • Infographics: Dynamic digital data analysis
    • Trump administration impacts
    • Biopharma M&A scorecard
    • BioWorld 2024 review
    • BioWorld MedTech 2024 review
    • BioWorld Science 2024 review
    • Women's health
    • China's GLP-1 landscape
    • PFA re-energizes afib market
    • China CAR T
    • Alzheimer's disease
    • Coronavirus
    • More reports can be found here

BioWorld. Link to homepage.

  • Sign In
  • Sign Out
  • My Account
Subscribe
Breaking News: Trump administration impacts continue to roil the life sciences sectorSee today's BioWorld Science
Home » Without enough data, machine learning can lead analyses astray
To read the full article sign up for free or sign in.
Drug Design, Drug Delivery & Technologies

Without enough data, machine learning can lead analyses astray

Jan. 12, 2024
By Anette Breindl
Researchers have reported that the predictive abilities of a machine learning algorithm trained using best practices on a large clinical dataset did not generalize beyond the data that was used to train it. The algorithm was able to predict, to a degree, which individual patients would benefit from the medication when the patients were from the dataset the algorithm was trained on. But when it was supposed to predict who would benefit in clinical cohorts that were not part of the training, it performed no better than chance.
BioWorld Science Artificial intelligence Drug design, drug delivery and technologies

Popular Stories

  • Today's news in brief

    BioWorld
    BioWorld briefs for July 25, 2025.
  • Today's news in brief

    BioWorld MedTech
    BioWorld MedTech briefs for July 25, 2025.
  • EU flag, syringe, capsules

    CHMP rejects Sarepta’s Elevidys, changes mind on Lilly’s Kisunla

    BioWorld
    After a tough few weeks for Sarepta Therapeutics Inc., the EMA dealt another blow on July 25, announcing it will not be approving the Duchenne muscular dystrophy...
  • Brain and neural networks

    Proteomics finds surprise commonalities as well as differences in neurodegenerative diseases

    BioWorld
    The switch will be flicked today to make the world’s largest dementia-related proteomics dataset freely available to researchers, at the same time as members of...
  • Illustration of Microglia cells (red) in Alzheimer´s disease

    Two cancer drugs combined modify Alzheimer’s disease in mice

    BioWorld
    Current treatments for Alzheimer’s disease have limited effects. While they can slow cognitive decline or alleviate symptoms, they do not reverse this complex...
  • BioWorld
    • Today's news
    • Analysis and data insight
    • Clinical
    • Data Snapshots
    • Deals and M&A
    • Financings
    • Newco news
    • Opinion
    • Regulatory
    • Science
  • BioWorld MedTech
    • Today's news
    • Clinical
    • Data Snapshots
    • Deals and M&A
    • Financings
    • Newco news
    • Opinion
    • Regulatory
    • Science
  • BioWorld Asia
    • Today's news
    • Analysis and data insight
    • Australia
    • China
    • Clinical
    • Deals and M&A
    • Financings
    • Newco news
    • Regulatory
    • Science
  • BioWorld Science
    • Today's news
    • Biomarkers
    • Cancer
    • Conferences
    • Endocrine/Metabolic
    • Immune
    • Infection
    • Neurology/Psychiatric
    • Patents
  • More
    • About
    • Advertise with BioWorld
    • Archives
    • Article reprints and permissions
    • Contact us
    • Cookie policy
    • Copyright notice
    • Data methodology
    • Infographics: Dynamic digital data analysis
    • Index insights
    • Podcasts
    • Privacy policy
    • Share your news with BioWorld
    • Staff
    • Terms of use
    • Topic alerts
Follow Us

Copyright ©2025. All Rights Reserved. Design, CMS, Hosting & Web Development :: ePublishing

BioWorld. Link to homepage.

Clarivate
  • BioWorld
  • BioWorld MedTech
  • BioWorld Asia
  • BioWorld Science
  • Data Snapshots
    • BioWorld
    • BioWorld MedTech
    • Infographics: Dynamic digital data analysis
    • Index insights
  • Special reports
    • Infographics: Dynamic digital data analysis
    • Trump administration impacts
    • Biopharma M&A scorecard
    • BioWorld 2024 review
    • BioWorld MedTech 2024 review
    • BioWorld Science 2024 review
    • Women's health
    • China's GLP-1 landscape
    • PFA re-energizes afib market
    • China CAR T
    • Alzheimer's disease
    • Coronavirus
    • More reports can be found here

BioWorld. Link to homepage.

  • Sign In
  • Sign Out
  • My Account
Subscribe