PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

New AI tool addresses accuracy and fairness in data to improve health algorithms

Detects biases in the datasets used to train machine-learning algorithms

2025-09-04
(Press-News.org)

New York, NY [September 4, 2025]—A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms—addressing a critical issue that can affect diagnostic accuracy and treatment decisions. The findings were published in the September 4 online issue of the Journal of Medical Internet Research [DOI: 10.2196/71757].

To tackle the problem, the investigators developed AEquity, a tool that helps detect and correct bias in health care datasets before they are used to train artificial intelligence (AI) and machine-learning models. The investigators tested AEquity on different types of health data, including medical images, patient records, and a major public health survey, the National Health and Nutrition Examination Survey, using a variety of machine-learning models. The tool was able to spot both well-known and previously overlooked biases across these datasets.

AI tools are increasingly used in health care to support decisions, ranging from diagnosis to cost prediction. But these tools are only as accurate as the data used to train them. Some demographic groups may not be proportionately represented in a dataset. In addition, many conditions may present differently or be overdiagnosed across groups, the investigators say. Machine-learning systems trained on such data can perpetuate and amplify inaccuracies, creating a feedback loop of suboptimal care, such as missed diagnoses and unintended outcomes.

 “Our goal was to create a practical tool that could help developers and health systems identify whether bias exists in their data—and then take steps to mitigate it,” says first author Faris Gulamali, MD. “We want to help ensure these tools work well for everyone, not just the groups most represented in the data.”

The research team reported that AEquity is adaptable to a wide range of machine-learning models, from simpler approaches to advanced systems like those powering large language models. It can be applied to both small and complex datasets and can assess not only the input data, such as lab results or medical images, but also the outputs, including predicted diagnoses and risk scores.

The study’s results further suggest that AEquity could be valuable for developers, researchers, and regulators alike. It may be used during algorithm development, in audits before deployment, or as part of broader efforts to improve fairness in health care AI.

“Tools like AEquity are an important step toward building more equitable AI systems, but they’re only part of the solution,” says senior corresponding author Girish N. Nadkarni, MD, MPH, Chair of the Windreich Department of Artificial Intelligence and Human Health, Director of the Hasso Plattner Institute for Digital Health, and the Irene and Dr. Arthur M. Fishberg Professor of Medicine at the Icahn School of Medicine at Mount Sinai, and the Chief AI Officer of the Mount Sinai Health System. “If we want these technologies to truly serve all patients, we need to pair technical advances with broader changes in how data is collected, interpreted, and applied in health care. The foundation matters, and it starts with the data.”

“This research reflects a vital evolution in how we think about AI in health care—not just as a decision-making tool, but as an engine that improves health across the many communities we serve,” says David L. Reich MD, Chief Clinical Officer of the Mount Sinai Health System and President of The Mount Sinai Hospital. “By identifying and correcting inherent bias at the dataset level, we’re addressing the root of the problem before it impacts patient care. This is how we build broader community trust in AI and ensure that resulting innovations improve outcomes for all patients, not just those best represented in the data. It’s a critical step in becoming a learning health system that continuously refines and adapts to improve health for all.”

The paper is titled “Detecting, Characterizing, and Mitigating Implicit and Explicit Racial Biases in Health Care Datasets With Subgroup Learnability: Algorithm Development and Validation Study.”

The study’s authors, as listed in the journal, are Faris Gulamali, Ashwin Shreekant Sawant, Lora Liharska, Carol Horowitz, Lili Chan, Patricia Kovatch, Ira Hofer, Karandeep Singh, Lynne Richardson, Emmanuel Mensah, Alexander Charney, David Reich, Jianying Hu, and Girish Nadkarni.

The study was funded by the National Center for Advancing Translational Sciences and the National Institutes of Health.

For more Mount Sinai artificial intelligence news, visit: https://icahn.mssm.edu/about/artificial-intelligence. 

-####-

About Mount Sinai's Windreich Department of AI and Human Health  

Led by Girish N. Nadkarni, MD, MPH—an international authority on the safe, effective, and ethical use of AI in health care—Mount Sinai’s Windreich Department of AI and Human Health is the first of its kind at a U.S. medical school, pioneering transformative advancements at the intersection of artificial intelligence and human health. 

The Department is committed to leveraging AI in a responsible, effective, ethical, and safe manner to transform research, clinical care, education, and operations. By bringing together world-class AI expertise, cutting-edge infrastructure, and unparalleled computational power, the department is advancing breakthroughs in multi-scale, multimodal data integration while streamlining pathways for rapid testing and translation into practice. 

The Department benefits from dynamic collaborations across Mount Sinai, including with the Hasso Plattner Institute for Digital Health at Mount Sinai—a partnership between the Hasso Plattner Institute for Digital Engineering in Potsdam, Germany, and the Mount Sinai Health System—which complements its mission by advancing data-driven approaches to improve patient care and health outcomes. 

At the heart of this innovation is the renowned Icahn School of Medicine at Mount Sinai, which serves as a central hub for learning and collaboration. This unique integration enables dynamic partnerships across institutes, academic departments, hospitals, and outpatient centers, driving progress in disease prevention, improving treatments for complex illnesses, and elevating quality of life on a global scale. 

In 2024, the Department's innovative NutriScan AI application, developed by the Mount Sinai Health System Clinical Data Science team in partnership with Department faculty, earned Mount Sinai Health System the prestigious Hearst Health Prize. NutriScan is designed to facilitate faster identification and treatment of malnutrition in hospitalized patients. This machine learning tool improves malnutrition diagnosis rates and resource utilization, demonstrating the impactful application of AI in health care. 

For more information on Mount Sinai's Windreich Department of AI and Human Health, visit: ai.mssm.edu.

 

About the Hasso Plattner Institute at Mount Sinai 

At the Hasso Plattner Institute for Digital Health at Mount Sinai, the tools of data science, biomedical and digital engineering, and medical expertise are used to improve and extend lives. The Institute represents a collaboration between the Hasso Plattner Institute for Digital Engineering in Potsdam, Germany, and the Mount Sinai Health System.  

Under the leadership of Girish Nadkarni, MD, MPH, who directs the Institute, and Professor Lothar Wieler, a globally recognized expert in public health and digital transformation, they jointly oversee the partnership, driving innovations that positively impact patient lives while transforming how people think about personal health and health systems. 

The Hasso Plattner Institute for Digital Health at Mount Sinai receives generous support from the Hasso Plattner Foundation. Current research programs and machine learning efforts focus on improving the ability to diagnose and treat patients. 

 About the Icahn School of Medicine at Mount Sinai 

The Icahn School of Medicine at Mount Sinai is internationally renowned for its outstanding research, educational, and clinical care programs. It is the sole academic partner for the seven member hospitals* of the Mount Sinai Health System, one of the largest academic health systems in the United States, providing care to New York City’s large and diverse patient population.  

The Icahn School of Medicine at Mount Sinai offers highly competitive MD, PhD, MD-PhD, and master’s degree programs, with enrollment of more than 1,200 students. It has the largest graduate medical education program in the country, with more than 2,600 clinical residents and fellows training throughout the Health System. Its Graduate School of Biomedical Sciences offers 13 degree-granting programs, conducts innovative basic and translational research, and trains more than 560 postdoctoral research fellows. 

Ranked 11th nationwide in National Institutes of Health (NIH) funding, the Icahn School of Medicine at Mount Sinai is among the 99th percentile in research dollars per investigator according to the Association of American Medical Colleges.  More than 4,500 scientists, educators, and clinicians work within and across dozens of academic departments and multidisciplinary institutes with an emphasis on translational research and therapeutics. Through Mount Sinai Innovation Partners (MSIP), the Health System facilitates the real-world application and commercialization of medical breakthroughs made at Mount Sinai.

------------------------------------------------------- 

* Mount Sinai Health System member hospitals: The Mount Sinai Hospital; Mount Sinai Brooklyn; Mount Sinai Morningside; Mount Sinai Queens; Mount Sinai South Nassau; Mount Sinai West; and New York Eye and Ear Infirmary of Mount Sinai

 

 

 

 

END



ELSE PRESS RELEASES FROM THIS DATE:

Researchers design robot that can find, pick hidden strawberries

2025-09-04
PULLMAN, Wash. -- Strawberries are delicate and hard to harvest—easily bruised and often hidden under a canopy of leaves. This creates headaches for scientists trying to design robotic harvesters. Now a Washington State University-led team has designed one that combines an artificial-intelligence vision system, soft silicone “fingers,” and a fan that gently move leaves out of the way to get at hidden fruit. Experiments in the lab and in outdoor fields showed that the harvester correctly detected strawberries 80% of the time, on average, and could classify whether the berries were hidden 93% of the time. The design, development ...

Effective urban planning from real-world population tracking

2025-09-04
Tracking human behavioral patterns in cities can be used to determine urban delineations and urban land use, which has the potential to improve urban planning. Urban areas are human settlements, typically cities, characterized by high population densities and built infrastructure. Urban areas need to be carefully planned, to ensure they are safe and sanitary. They are not self-sustaining but are dependent on an influx of essential resources. Delineating urban areas is of great importance for planning and governance. Historically, this has been determined by establishing administrative boundaries and ...

EWG study: PFAS water treatment has double benefits, cutting toxic PFAS and carcinogens

2025-09-04
WASHINGTON – Advanced systems for removing the toxic “forever chemicals” known as PFAS from drinking water can deliver far greater health benefits than previously thought. They also slash levels of other harmful contaminants, a new peer-reviewed Environmental Working Group study finds. The research underscores the fact that PFAS water filtration systems can also help reduce levels of cancer-causing disinfection byproducts, or DBPs, agricultural nitrates and heavy metals like arsenic ...

MIT Press expands Direct to Open (D2O) open access model in 2026 with publishing partners

2025-09-04
As we enter the fifth funding cycle for Direct to Open (D2O)—our model for open access monographs—the MIT Press is thrilled to partner with Duke University Press and Goldsmiths Press to bring even more vital research to the communities that need it most. Starting in 2026, D2O will include offerings from all three presses, furthering our shared mission in building a more open and accessible future for academic publishing. Libraries and consortia can commit to support the growing Direct to Open program through November 30, 2025. Launched in 2021, D2O is the MIT Press’s bold, innovative framework for open access monographs that shifts publishing ...

Pork protein improves recovery, mood and inflammation in military cadets following combat fitness test

2025-09-04
A newly published clinical trial in Nutrients highlights pork’s role in military nutrition, showing that meals containing lean pork support better recovery, mood and anabolic status in cadets performing intense tactical fitness exercises compared to plant-based meals.  The randomized controlled trial, conducted by Texas A&M University and funded by the National Pork Board (NPB) and the U.S. Department of Defense, evaluated whether pork-based or plant-based military-style Meals, Ready-to-Eat (MREs) influenced recovery after the Army Combat Fitness Test (ACFT) in cadets.  Pork Meals Reduce Catabolism, ...

Mount Sinai unveils Emergency Department transformation after extensive upgrades and renovations

2025-09-04
The Mount Sinai Hospital has announced the completion of a major six-phase redesign project of its Emergency Department (ED) that provides more clinical space, a completely renovated observation unit, and a more private and comfortable experience for patients. This transformation features innovative, state-of-the-art advancements to enhance access to life-saving, high-quality care and improved experience for the 100,000 patients who visit the ED each year. Construction began in the summer of 2020. “This exciting work represents the culmination of five years of planning and effort,” says Benjamin S. Abella, ...

Uncovering language learning strategies for Japanese university students in STEM

2025-09-04
In an increasingly globalized world, English is no longer just a beneficial skill to have but a crucial tool for professionals in science, technology, engineering, and mathematics (STEM). Researchers, engineers, and scientists alike must be able to communicate internationally, access the latest research findings, and publish their work in English. It is thus, vital to understand the various language learning strategies (LLSs) that people use to learn English as a second language. Despite the widely recognized importance of LLSs, educators have struggled to accurately and objectively analyze them in specific learning environments. The Strategy Inventory for Language Learning ...

The invisible influence: How cultural cognitive biases influence visuomotor adaptations

2025-09-04
The process of improving the synchronization between visual perception and motor skills is called visuomotor learning. It entails adaptation of movements based on visual information. This kind of training can help with skill development and rehabilitation by enhancing motor skills. However, the explicit strategies involved in visuomotor learning might not be universal. Society and culture often control our cognitive behavior, and this leads to unconscious, cultural, and cognitive biases. This might have an impact on ...

New sugar-based stabilizer keeps sweat sensors working under acidic conditions

2025-09-04
The composition of sweat makes it a valuable diagnostic fluid. While it is mostly water, the small fraction containing electrolytes, metabolic byproducts, and chemical traces can reveal important information about a person’s health. Today, commercial sweat-based sensors can already track dehydration, electrolyte loss, and more. One emerging application is the measurement of lactic acid in sweat. Lactic acid, or more precisely L-lactate, is a byproduct of metabolism produced mainly in muscle cells when glucose is broken down for energy under low-oxygen conditions, such as during intense physical activity. Athletes and trainers use lactate measurements ...

Stress & Stars: Two more ERC Starting Grants for ISTA

2025-09-04
Two Assistant Professors at the Institute of Science and Technology Austria (ISTA) have won European Research Council (ERC) Starting Grants of 1.5 million euros each to pursue their potentially groundbreaking work in astrophysics and neuroscience. These prestigious grants empower scientists at the beginning of their careers to launch projects, form teams and explore their best ideas. Neuroscientist Amelia Douglass looks into how animals react to stress – both behavioral and physiological – to ensure their survival. Astrophysicist Ylva Götberg researches pairs of stars ...

LAST 30 PRESS RELEASES:

Acid-resistant artificial mucus improves gastric wound healing in animals

Spaceflight accelerates human stem cell aging, UC San Diego researchers find

Single treatment with MM120 (lysergide) in generalized anxiety disorder

Telephone vs text message counseling and physical activity among midlife and older adults

Students with overprotective parents are more vulnerable to anxiety during their transition to university, researchers find

Seagrass as a carbon sponge?

Study shows how smoking drives pancreatic cancer

Unveiling the identity of Crohn's disease T cells

Frontiers Forum Deep Dive series: Biological ‘moonshot’ accelerates efforts to genetically map life on Earth

After early-life stress, astrocytes affect behaviour

UMD developing AI-powered warning system to predict disease tied to extreme weather

New study links grain foods to healthier diet patterns, metabolic health and everyday accessibility

Korea University College of Medicine explores 'Health for Humanity' at K-CLUB International Symposium with world-renowned scholars

Regular walking prevents chronic back pain

Broccoli seeds can spread resistance to multiple fungicides

New AI tool addresses accuracy and fairness in data to improve health algorithms

Researchers design robot that can find, pick hidden strawberries

Effective urban planning from real-world population tracking

EWG study: PFAS water treatment has double benefits, cutting toxic PFAS and carcinogens

MIT Press expands Direct to Open (D2O) open access model in 2026 with publishing partners

Pork protein improves recovery, mood and inflammation in military cadets following combat fitness test

Mount Sinai unveils Emergency Department transformation after extensive upgrades and renovations

Uncovering language learning strategies for Japanese university students in STEM

The invisible influence: How cultural cognitive biases influence visuomotor adaptations

New sugar-based stabilizer keeps sweat sensors working under acidic conditions

Stress & Stars: Two more ERC Starting Grants for ISTA

ERC honors Hebrew University scientists for pioneering brain and language studies

Theresa Rienmüller and Robert Winkler receive ERC Starting Grants

ERC grant helps to explore innovative approaches to improve the diagnosis of ADHD in adults

Hidden chemistry of Earth’s core revealed by how it froze

[Press-News.org] New AI tool addresses accuracy and fairness in data to improve health algorithms
Detects biases in the datasets used to train machine-learning algorithms