(Press-News.org) Artificial intelligence (AI) tools significantly improve the readability of online patient education materials (PEMs), making them more accessible, a new study shows.
Led by researchers at NYU Langone Health, the study focused on the readability of PEMs available on the websites of the American Heart Association (AHA), American Cancer Society (ACS), and American Stroke Association (ASA). According to the researchers, these materials help patients make decisions about their health care but often exceed the recommended reading level of grade 6, making them difficult for many patients to understand.
For the study, researchers evaluated the capabilities of three large language models (LLMs) — ChatGPT, Gemini, and Claude — to optimize the readability of PEMs without compromising accuracy. These generative AI tools are designed to simplify complex texts by predicting the next word in a sentence based on extensive Internet data. This next-word prediction gives such models the ability to rewrite any article in simpler language as directed.
Published online April 10 in the Journal of Medical Internet Research, the study involved 60 randomly selected PEMs from the AHA, ACS, and ASA websites. Researchers prompted the LLMs to simplify the reading level of the materials. Results showed that the original readability scores were significantly above the recommended level of grade 6, with mean grade-level scores of 10.7, 10, and 9.6, respectively.
After optimization by the LLMs, readability scores improved significantly across all three websites. ChatGPT improved readability to a mean grade level of 7.6, Gemini to 6.6, and Claude to 5.6. Word counts were also significantly reduced, making the materials more concise.
"Our study shows that widely used large language models have the potential to transform patient education materials into more readable content, which is essential for patient empowerment and better health outcomes," said study senior author Jonah Feldman, MD, medical director of transformation and informatics at NYU Langone.
“Our findings demonstrate that even expert-composed education materials, which are already patient-directed, can benefit from AI-driven improvements,” said Feldman, who also serves as an assistant professor at NYU Grossman Long Island School of Medicine.
This study, the researchers say, provides an example of how healthcare organizations can apply AI to make clinical communication more patient friendly. Prior studies demonstrated the capabilities of AI models to create patient-focused explanations of heart test results, to draft responses to electronic advice queries, and to generate human-friendly summaries of complex medical reports.
“The breadth of possible AI offerings shows how technology can be leveraged to transform the patient experience across health care systems, and not just in the United States,” said study co-author Paul Testa, MD, JD, MPH, chief health informatics officer at NYU Langone.
“These studies are not just theoretical — after demonstrating their effectiveness, we are actively putting these AI tools into practice,” said Testa, who is also a clinical professor at NYU Grossman School of Medicine.
According to Testa, the NYU Langone team is already using the same AI tools in a randomized controlled trial that incorporates AI-generated, patient-friendly summaries for hospital discharge instructions, with the goal to evaluate their effectiveness in improving patient comprehension and satisfaction. The researchers hope to show that providing clear and accessible discharge instructions will help ensure better postdischarge care and smoother transitions.
“Generating real-world evidence through randomized trials is crucial for validating the effectiveness of AI tools in clinical settings,” said study co-author Jonah Zaretsky, MD, associate chief of medicine at NYU Langone Hospital — Brooklyn. “This approach ensures that the AI-generated documentation is not only accurate but also genuinely beneficial for patients and their families,” added Zaretsky, a clinical assistant professor at NYU Grossman School of Medicine.
The study was self-funded by NYU Langone. Besides Feldman, Testa, and Zaretsky, NYU Langone researchers involved in the study were lead author John Will, and co-authors Mahin Gupta and Aliesha Dowlath.
Media Inquiries
David March
212-404-3528
David.March@NYULangone.org
END
Artificial intelligence tools make education materials more patient friendly
2025-04-30
ELSE PRESS RELEASES FROM THIS DATE:
Increasing physical activity in middle age may protect against Alzheimer's disease
2025-04-30
An increase in physical activity between the ages of 45 and 65 could help prevent Alzheimer's disease, while inactivity may be detrimental to brain health. This is the main conclusion of a scientific paper published in Alzheimer's & Dementia, which highlights the need to promote physical activity among middle-aged adults. The study is the result of a collaboration between the Barcelona Institute for Global Health (ISGlobal), a center promoted by the “la Caixa” Foundation, and the ...
Prevention instead of reaction: Intelligent, networked systems for structural monitoring
2025-04-30
The safety and durability of transport and building infrastructure are in the interests of both operators and users. To maintain the best possible building condition at the lowest possible cost, effective monitoring is required to improve condition assessment. Although there are suitable monitoring systems, they are usually not properly networked, not directly integrated into the building management system and their data is often not usable in the long term due to incomplete documentation and non-standardised evaluation procedures. In the PreMainSHM project, a team at Graz ...
Zoo life boosts object exploration in orangutans
2025-04-30
A new study comparing wild and zoo-housed Sumatran orangutans reveals that life in a zoo significantly alters how orangutans interact with their environment. Researchers analyzed over 12,000 instances of daily exploratory object manipulation (EOM)—the active manipulation and visual inspection of objects associated with learning and problem-solving—across 51 orangutans aged 0.5 to 76 years. The findings show that orangutans living in zoos engage in more frequent, more diverse, and more complex exploration than their wild counterparts.
“Our study shows that orangutans ...
MIT engineers advance toward a fault-tolerant quantum computer
2025-04-30
CAMBRIDGE, MA – In the future, quantum computers could rapidly simulate new materials or help scientists develop faster machine-learning models, opening the door to many new possibilities.
But these applications will only be possible if quantum computers can perform operations extremely quickly, so scientists can make measurements and perform corrections before compounding error rates reduce their accuracy and reliability.
The efficiency of this measurement process, known as readout, relies on the strength of the coupling between photons, which are particles of light that carry quantum information, ...
An enzyme-proof glycan glue for extracellular matrix to ameliorate intervertebral disc degeneration
2025-04-30
As the world’s population ages, intervertebral disc degeneration (IDD) has become a major medical issue, causing chronic lower back pain and mobility issues that diminish the quality of life for millions. The study from the University of Macau offers new hope with a novel “sugar glue” designed to repair damaged spinal discs. Led by Professor Chunming Wang, in collaboration with Professor Dong Lei of Nanjing University and supported by Professor Geng Dechun’s team at the First Affiliated Hospital of Soochow University. The research introduces a glucomannan-based solution that restores disc health by targeting a key protein, published in Nature Communications, ...
Deepfakes now come with a realistic heartbeat, making them harder to unmask
2025-04-30
Imagine a world where deepfakes have become so good that no detection mechanism can unmask them as imposters. This would be a bonanza for criminals and malignant state actors: for example, these might use deepfakes to slander rival political candidates or frame inconvenient defenders of human rights.
This nightmare scenario isn’t real yet, but for years, methods for creating deepfakes have been locked in a ‘technological arms race’ against detection algorithms. And now, scientists ...
So, our city’s shrinking—Now what?
2025-04-30
Policymakers often overlook the challenges faced by shrinking small and medium-sized cities. Yet, keeping these cities sustainable is crucial for many urban stakeholders. Unfortunately, the methods that have succeeded in large cities cannot be unilaterally applied to combat this issue. This suggests that a research gap on effective urban management in small and medium-sized cities exists.
Dr. Haruka Kato, a junior associate professor at Osaka Metropolitan University, examined the types of municipal expenditures ...
Parents with alcohol-related diagnoses are twice as likely to maltreat children
2025-04-30
A new systematic review has found that parents and other child caregivers who have alcohol-related diagnoses are twice as likely to maltreat children in their care than parents and caregivers with no alcohol-related diagnoses. ‘Alcohol-related diagnoses’ included alcohol-related hospitalisation, alcohol-related service use, or a history of clinically determined alcohol dependence. ‘Child maltreatment’ included physical, psychological, emotional and sexual abuse; neglect; and other types of maltreatment such as harsh parenting.
The study pooled the results from twelve studies of child maltreatment. All were cohort studies in high-income countries: three in ...
Giant croclike carnivore fossils found in the Caribbean
2025-04-30
Imagine a crocodile built like a greyhound — that’s a sebecid. Standing tall, with some species reaching 20 feet in length, they dominated South American landscapes after the extinction of dinosaurs until about 11 million years ago. Or at least, that’s what paleontologists thought, until they began finding strange, fossilized teeth in the Caribbean.
“The first question that we had when these teeth were found in the Dominican Republic and on other islands in the Caribbean was: What are ...
Palatable versus poisonous: Eavesdropping bats must learn to identify which prey is safe to eat
2025-04-30
Scientists at the Smithsonian Tropical Research Institute (STRI) found that the fringe-lipped bat, known to eavesdrop on frog and toad mating calls to find its prey, learns to distinguish between palatable and unpalatable frogs and toads through experience. The findings, published April 29 in the Proceedings of the Royal Society B, provide the first evidence that eavesdropping predators fine-tune their hunting cues over the course of their development.
To source their food, some predators eavesdrop on calls emitted by prey. Fringe-lipped bats, which range from Panama to Brazil, are some of the most skilled eavesdroppers in the world: They are attuned to the sexual advertisement ...