Monday, 17 Nov 2025
  • My Feed
  • My Saves
  • History
  • Blog
Living Well Study
  • Blog
  • Ageing Well
  • Brain Health
  • Healthy Diets
  • Physical Wellness
  • Wellness
  • 🔥
  • Wellness
  • older adults
  • Living Well
  • public health
  • Brain Health
  • dementia
  • Ageing Well
  • mental health
  • physical exercise
  • cardiovascular disease
Font ResizerAa
Living Well StudyLiving Well Study
  • My Saves
  • My Feed
  • History
Search
  • Pages
    • Home
    • Search Page
  • Personalized
    • Blog
    • My Feed
    • My Saves
    • History
  • Categories
    • Ageing Well
    • Brain Health
    • Healthy Diets
    • Mental Wellness
    • Physical Wellness
    • Wellness
Have an existing account? Sign In
Follow US
© 2022 Foxiz News Network. Ruby Design Company. All Rights Reserved.
Living Well Study > Blog > Wellness > Research Unveils Causes of Bias in AI Models for Medical Imaging Analysis
Wellness

Research Unveils Causes of Bias in AI Models for Medical Imaging Analysis

support
Share
Big data technology and data science. Data scientist querying, analysing and visualising complex data set on virtual screen. Artificial intelligence. Image by NicoElNino via iStock.
SHARE

Artificial intelligence models are increasingly integrated into medical diagnostic processes, particularly in analysing imaging data like X-rays. Research has indicated that these AI systems do not consistently perform well across different demographic groups, often underperforming in diagnostic accuracy for women and individuals from diverse ethnic backgrounds.

In an intriguing development, a 2022 study by MIT researchers demonstrated that AI models could reliably predict a patient’s race from their chest X-rays, a task that even experienced radiologists cannot achieve. This capability, however, comes with significant implications. The same team has discovered that the accuracy of these models in predicting demographic details correlates with substantial fairness gaps in medical diagnostics. Essentially, models better at identifying demographic characteristics tend to have more significant disparities in diagnosing diseases across different racial and gender groups. This suggests that the AI might be taking demographic shortcuts in its evaluations, leading to potentially incorrect diagnoses for certain groups, such as women and Black individuals.

Marzyeh Ghassemi, an associate professor at MIT, underscored the connection between AI’s ability to predict demographics and its uneven performance across groups, a link that had not been previously established. The study underscores the urgent need to address these biases, as they could potentially lead to harmful consequences for patient care.

The researchers have explored methods to enhance the fairness of these models. They found that retraining the AI with an emphasis on reducing biases showed promising results, but only when the models were applied to patients similar to those they were trained on. When used on patients from different hospitals, the fairness gaps reemerged, suggesting that the debiasing efforts were only sometimes effective.

Haoran Zhang, an MIT graduate student and lead author of the study, advises that hospitals should rigorously test external AI models with their demographic data to ensure any fairness claims are valid in their specific context. This is crucial because models often perform best on the data they were trained on and may need to generalise better across different settings.

The FDA has approved many AI-enabled medical devices for use in radiology, highlighting the growing reliance on AI in medical diagnostics. However, the discovery that these models can inadvertently learn and utilise demographic information to make predictions—even when not explicitly trained—raises concerns about their application and the ethical implications of their use.

The study employed AI models on publicly available chest X-ray datasets to predict several medical conditions and examine their performance. The findings revealed not only variability in accuracy based on gender and race but also a correlation between the models’ demographic prediction accuracy and their fairness gaps. This indicates that the AI may be using demographic features as proxies in its diagnostic processes, which could undermine the fairness and efficacy of medical diagnostics.

To combat these issues, the researchers employed training models to improve subgroup robustness and group adversarial methods to strip demographic information from the training process. Both approaches succeeded, but their effectiveness could have been enhanced when the data closely resembled the training set.

The persistence of fairness gaps in other datasets underscores a significant challenge: models debiased in one context may not maintain their fairness in another. This variability highlights the complexity of AI in medicine and the crucial need for continuous vigilance and adaptation to ensure these technologies serve all patients equitably.

Ghassemi’s team plans to continue exploring new methods to refine AI’s ability to make fair and accurate predictions across diverse patient populations. The research underscores the critical necessity for hospitals to thoroughly evaluate AI models with their specific demographic data before implementation. This responsible deployment and development of AI technologies in healthcare is a vital step in ensuring unbiased medical outcomes.

More information: Yuzhe Yang et al, The limits of fair medical imaging AI in real-world generalization, Nature Medicine. DOI: 10.1038/s41591-024-03113-4

Journal information: Nature Medicine Provided by Massachusetts Institute of Technology

TAGGED:artificial intelligencecomputer modelingfairnessmachine learningmedical diagnosisradiology
Share This Article
Email Copy Link Print
Previous Article Pregnant and Postpartum Women with Depression at Increased Risk of Cardiovascular Disease
Next Article Impact of a Youthful Outlook on Dementia Caregivers and Their Relatives
Leave a Comment

Leave a Reply Cancel reply

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

Recent Posts

  • Innovative support programme shown to ease burnout among dementia caregivers
  • Total daily step count plays a greater role in supporting healthy ageing in older women than stepping frequency
  • Rigid arterial pathways could intensify the initial stages of cognitive decline in later life
  • Playing or listening to music in later life tied to sharply lower dementia risk, research shows
  • Enhancing Longevity Through Improved Hand Dexterity

Tags

adolescents adverse effects ageing populations aging populations air pollution alzheimer disease amyloids anxiety atopic dermatitis behavioral psychology biomarkers blood pressure body mass index brain caffeine cancer cancer research cardiology cardiovascular disease cardiovascular disorders caregivers children climate change effects clinical research cognitive development cognitive disorders cognitive function cognitive neuroscience cohort studies COVID-19 dementia depression diabetes diets discovery research disease control disease intervention disease prevention environmental health epidemiology foods food science gender studies geriatrics gerontology gut microbiota health and medicine health care health care costs health care delivery heart disease heart failure home care human brain human health hypertension inflammation insomnia life expectancy life sciences longitudinal studies memory disorders menopause mental health metabolic disorders metabolism mortality rates neurodegenerative diseases neurological disorders neurology neuroscience nursing homes nutrients nutrition obesity older adults parkinsons disease physical exercise pollution control population studies preventive medicine psychiatric disorders psychological science psychological stress public health research impact risk assessment risk factors risk reduction skin sleep sleep disorders social research social sciences social studies of science socioeconomics stress management type 2 diabetes weight loss working memory
November 2025
S M T W T F S
 1
2345678
9101112131415
16171819202122
23242526272829
30  
« Oct    

This website is for information purpose only and is in no way intended to replace the advice, professional medical care, diagnosis or treatment of a doctor, therapist, dietician or nutritionist.

About | Contact | Cookie Policy | Digital Millennium Copyright Act Notice | Disclaimer | Privacy Policy | Terms of Service

You Might Also Like

Wellness

The functional capacity of individuals in their advanced years can be likened to an ecosystem that is prone to collapse upon facing disturbances

By support
Wellness

Discrimination: A Catalyst for Accelerated Ageing

By support
Wellness

Why Sleep Counts: How Duration, Timing, and Quality May Influence Heart Disease Risk

By support
Wellness

Rising Use of Ozempic and Wegovy Among Privately Insured Patients Could Exacerbate Health Disparities

By support
Living Well Study
Categories
  • Ageing Well
  • Brain Health
  • Healthy Diets
  • Mental Wellness
  • Physical Wellness
  • Wellness
LivingWellStudy
  • About
  • Contact
  • Cookie Policy
  • Digital Millennium Copyright Act Notice
  • Disclaimer
  • Privacy Policy
  • Terms of Service
Welcome Back!

Sign in to your account

Username or Email Address
Password

Lost your password?