(Press-News.org) Machine learning algorithms designed to diagnose a common infection that affects women showed a diagnostic bias among ethnic groups, University of Florida researchers found.
While artificial intelligence tools offer great potential for improving health care delivery, practitioners and scientists warn of their risk for perpetuating racial inequities. Published Friday in the Nature journal Digital Medicine, this is the first paper to evaluate fairness among these tools in connection to a women’s health issue.
“Machine learning can be a great tool in medical diagnostics, but we found it can show bias toward different ethnic groups,” said Ruogu Fang, an associate professor in the J. Crayton Pruitt Family Department of Biomedical Engineering and the study’s author. “This is alarming for women’s health as there already are existing disparities that vary by ethnicity.”
The researchers evaluated the fairness of machine learning in diagnosing bacterial vaginosis, or BV, a common condition affecting women of reproductive age, which has clear diagnostic differences among ethnic groups.
Fang and co-corresponding author Ivana Parker, both faculty members in the Herbert Wertheim College of Engineering, pulled data from 400 women, comprising 100 from each of the ethnic groups represented — white, Black, Asian, and Hispanic.
In investigating the ability of four machine learning models to predict BV in women with no symptoms, researchers say the accuracy varied among ethnicities. Hispanic women had the most false-positive diagnoses, and Asian women received the most false-negative. Algorithm
“The models performed highest for white women and lowest for Asian women,” said the Parker, an assistant professor of bioengineering. “This tells us machine learning methods are not treating ethnic groups equally well.”
Parker said that while they were interested in understanding how AI tools predict disease for specific ethnicities, their study also helps medical scientists understand the factors associated with bacteria in women of varying ethnic backgrounds, which can lead to improved treatments.
BV, one of the most common vaginal infections, can cause discomfort and pain and happens when natural bacteria levels are out of balance. While there are symptoms associate with BV, many people have no symptoms, making it difficult to diagnose.
It doesn’t often cause complications, but in some cases, BV can increase the risk of sexually transmitted infections, miscarriage, and premature births.
The researchers said their findings demonstrate the need for improved methods for building the AI tools to mitigate health care bias.
Study reveals bias in AI tools when diagnosing women’s health issue
ELSE PRESS RELEASES FROM THIS DATE:
Anti-bias police training improved performance and reduced discrimination-based complaints significantly
In recent years, many police departments have mandated or encouraged anti-bias training. This has occurred in response to government-imposed measures such as consent decrees or as a proactive attempt to enhance public perceptions of police following actions that have raised concerns about racially motivated and other discriminatory practices. In a new study, researchers evaluated the effectiveness of an anti-bias training intervention in one Californian jurisdiction. The study found that officers who received the training had improved performance scores (measured by Body Worn Camera footage), decreased disparity in how they treated different groups of people, ...
Analysis of cyberstalking research identifies factors associated with perpetration, victimization
The widespread use of digital technologies and the Internet has spurred a new type of personal intrusion, known as cyberstalking. Incidences of cyberstalking have risen, with the U.S. Department of Justice estimating that more than 1.3 million people experience this type of victimization annually. A new study explored research to identify the factors associated with perpetration and victimization in cyberstalking. The study’s findings can inform the development of efforts to prevent and address cyberstalking. Conducted by a researcher at Sam Houston State ...
Massive 2022 eruption reduced ozone levels
When the Hunga Tonga-Hunga Ha’apai volcano erupted on January 15, 2022 in the South Pacific, it produced a shock wave felt around the world and triggered tsunamis in Tonga, Fiji, New Zealand, Japan, Chile, Peru and the United States. It also changed the chemistry and dynamics of the stratosphere in the year following the eruption, leading to unprecedented losses in the ozone layer of up to 7% over large areas of the Southern Hemisphere, according to a recent study published in the Proceedings of the National ...
Remarkably detailed view of “teenage galaxies” from just 2 to 3 billion years after the Big Bang revealed by JWST
Pasadena, CA—Galaxies that formed just 2 to 3 billion years after the Big Bang are unusually hot and glow with light from surprising elements, like nickel, according to new work led by Carnegie’s Gwen Rudie and Northwestern University’s Allison Strom. Studying “teenage galaxies” from the ancient universe can teach scientists about how these massive systems of stars mature and evolve. Their findings, published in The Astrophysical Journal Letters, are part of the CECILIA (Chemical Evolution Constrained using Ionized Lines in Interstellar Aurorae) ...
Litigating the Pandemic
When the COVID-19 pandemic spread across the United States, healthcare workers faced new demands, childcare and grocery store workers became essential workers, businesses shut down, and churches and school doors closed. The pandemic also arrived amidst protests over police violence. Deep partisan divisions and record natural disasters amplified these challenges. The national government offered new funding for businesses and individuals and public health guidance, and local governments issued guidelines for gathering in public. Litigating the Pandemic (University of Pennsylvania Press, 2023), a new book by Susan Sterett, professor ...
Personalized cancer medicine: humans make better treatment decisions than AI
Treating cancer is becoming increasingly complex, but also offers more and more possibilities. After all, the better a tumor’s biology and genetic features are understood, the more treatment approaches there are. To be able to offer patients personalized therapies tailored to their disease, laborious and time-consuming analysis and interpretation of various data is required. Researchers at Charité – Universitätsmedizin Berlin and Humboldt-Universität zu Berlin have now studied whether generative artificial intelligence ...
Genomic study links cannabis abuse to multiple health problems
New Haven, Conn. — A Yale-led analysis of the genomes of more than 1 million people has shed light on the underlying biology of cannabis use disorder and its links to psychiatric disorders, abuse of other substances such as tobacco, and possibly even an elevated risk of developing lung cancer. For the study, researchers examined a genome-wide set of genetic variants in individuals from multiple ancestry groups enrolled in the U.S. Department of Veterans Affairs’ Million Veteran Program, one of the world’s largest genetic databases, and ...
Younger people are more vulnerable to the effects of cardiovascular risk associated with high blood cholesterol and hypertension
Young people may be more susceptible to the effects of the risk factors for developing atherosclerosis. According to a study carried out at the Centro Nacional de Investigaciones Cardiovasculares (CNIC), younger people are especially vulnerable to the damaging effects of elevated blood cholesterol and hypertension, two of the major modifiable cardiovascular risk factors. These findings, published in the Journal of the American College of Cardiology, underline the need to implement aggressive control of cardiovascular risk factors at younger ages, requiring a change in primary prevention strategies to include “surveillance of subclinical atherosclerosis ...
Creativity in the age of generative AI: a new era of creative partnerships
Recent advancements in generative artificial intelligence (AI) have showcased its potential in a wide range of creative activities such as to produce works of art, compose symphonies, and even draft legal texts, slide presentations or the like. These developments have raised concerns that AI will outperform humans in creativity tasks and make knowledge workers redundant. These comments are most recently underlined by a Fortune article entitled ‘Elon Musk says AI will create a future where ‘no job is needed’: ‘The AI will be able to do everything’. In ...
Ambegaonkar studying physical & mental workload & recovery in collegiate dancers
Ambegaonkar Studying Physical & Mental Workload & Recovery In Collegiate Dancers Jatin Ambegaonkar, Professor, School of Kinesiology, received funding for the project: "Physical and mental workload and recovery in collegiate dancers." He and his collaborators, Kelley Wiese (PhD Student, CEHD – Kinesiology concentration) and Dr. Jena Hansen-Honeycutt (School of Dance, CVPA) aim to comprehensively assess the workload in collegiate dancers over the academic year. Specifically, they are examining objective physical activity demands ...