(Press-News.org) Can artificial intelligence, or AI, potentially transform health care for the better?
Now, rising to the challenge, an Arizona State University team of researchers has built a powerful new AI tool, called Ark+, to help doctors read chest X‑rays better and improve health care outcomes.
“Ark+ is designed to be an open, reliable and ultimately useful tool in real-world health care systems,” said Jianming “Jimmy” Liang, an ASU professor from the College of Health Solutions, and lead author of the study recently published in the prestigious journal Nature.
In a proof-of-concept study, the new AI tool demonstrated exceptional capability in diagnosis, from common lung diseases to rare and even emerging ones like COVID-19 or avian flu. It also was more accurate and outperformed proprietary software currently released by industry titans like Google and Microsoft.
“Our goal was to build a tool that not only performed well in our study but also can help democratize the technology to get it into the hands of potentially everyone,” said Liang. “Ultimately, we want AI to help doctors save lives.”
More bang for the health care buck
People certainly are demanding more bang for their health care buck.
Yet, with health care now the leading driver of the US economy, the US continues to rank lower than many countries in many indicators, including 49th in life expectancy, according to the World Bank. That’s lower than countries like Cuba and Qatar.
Patients want to live healthier lives and have better outcomes. And doctors want to make sure to get the diagnosis right the first time for better patient care.
That’s when AI enters the waiting room.
A new AI healthcare tool
Liang’s research team wanted to use AI to help interpret the most common type of X-ray used in medicine, the chest X-ray.
Chest X-rays are a big help for doctors to quickly diagnose various conditions affecting the chest, including lung problems (like pneumonia, tuberculosis or Valley fever), heart issues, broken ribs and even certain gut conditions.
But sometime, they can be hard to interpret, even for experienced physicians, or they may miss diagnosing rare conditions or emerging diseases, as was seen in the first year of the COVID-19 pandemic.
The Ark+ tool makes chest X-rays easier by reducing mistakes, speeding up diagnosis and making the technology more equitable by providing top‑quality AI health tools free and open access worldwide.
“We believe in open science, said Liang. “So, we used a public data and a global data set as we think this will more quickly develop the AI model.”
Ark+ outperforms previous AI chest x-ray tools
AI works by training computer software on large data sets, or in the case of the Ark+ model, a total of more than 700,000 worldwide images from several publicly available X-ray datasets.
The key difference-maker for Ark+ was adding value and expertise from the human art of medicine. Liang’s team critically included all the detailed doctors’ notes compiled for every image. “You learn more knowledge from experts,” said Liang.
These expert physician notes were critical in the Ark+ learning and getting more and more accuracy as it was trained on each data set.
“Ark+ is accruing and reusing knowledge,” said Liang, explaining the acronym. “That's how we train it. And pretty much, we were thinking of a new way to train AI models with numerous datasets via fully supervised learning.”
“Because before this, if you wanted to train a large model using multiple data sets, people usually used self-supervised learning, or you train it on the disease model, the abnormal, versus a normal x-ray.”
Large companies like Google and Microsoft have been developing AI healthcare models this way.
“That means you are not using the expert labels,” said Liang. “And so, that means you throw out the most valuable information from the data sets, these expert labels. We wanted AI to learn from expert knowledge, not only from the raw data.”
So, in a case of David versus Goliath, Liang’s small yet plucky research team, including graduate students DongAo Ma and Jiaxuan Pang, worked on the project with funding from the National Institutes of Health, National Science Foundation and seed funding from a long-standing collaboration with Mayo Clinic Arizona radiologist Michael Gotway.
ASU’s new tool may be the slingshot needed to give medicine a boost, as it was shown to outperform private and property software developed by giants.
Other key highlights from the pilot project include:
• Foundation model for X‑rays: Ark+ is trained on many different chest X‑ray datasets from hospitals and institutions around the world. This makes it better at detecting a wide range of lung issues.
• Open and sharable: The team has released the code and pretrained models. This means other researchers can improve it or adjust it for local clinics.
• Quick learning: Ark+ can identify rare diseases even when only a few examples are available.
• Adapts to new tasks: Ark+ can be also fine‑tuned to spot new or unseen lung problems without needing full retraining.
• Resilient and fair: Ark+ works well even with uneven data and fights against biases. It can also be used in private, secure ways.
Among the most important aspects of outcompeting proprietary companies was making the Ark+ software open access, and free to all.
“If we compete directly, it’s unlikely that we're going to win,” said Liang. “But with open-source software, we invite collaborations with many other labs. And with everyone involved, I think we are more powerful than one company.”
Putting the AI into the hands of doctors
Liang also notes that the software can be adapted for any kind of medical imaging diagnosis, including CT, MRI and other imaging tools, thereby expanding its impact in the future.
Liang and his research team hopes Ark+ will become a foundation for future AI tools in medicine, allowing better care no matter where patients live.
The Ark+ team hopes to further commercialize the software for hospitals so that researchers everywhere will use and build on their work. By sharing everything openly, they want to help doctors in all countries, even rural places without big data resources.
Their goal is to make medical AI safer, smarter and more helpful for everyone.
“By making this model fully open, we’re inviting others to join us in making medical AI more fair, accurate and accessible,” Liang added. “We believe this will help save lives.”
That’s a better pill for US healthcare that every American would like to swallow.
###
About this Study:
Published in Nature, the paper is titled “A fully open AI foundation model applied to chest radiography.” Authors: DongAo Ma1, Jiaxuan Pang1, Michael B. Gotway3, Jianming Liang2*
1School of Computing and Augmented Intelligence, Arizona State University, 1151 S Forest Ave, Tempe, 85281, AZ, USA. 2Biomedical Informatics and Data Science, Arizona State University, 6161 E Mayo Blvd, Phoenix, 85054, AZ, USA. 3Department of Radiology, Mayo Clinic, 5881 E. Mayo Blvd., Phoenix, 85054, AZ, USA.
*Corresponding author(s). E-mail(s): Jianming.Liang@asu.edu; Contributing authors: dongaoma@asu.edu; jpang12@asu.edu; Gotway.Michael@mayo.edu
Why this research matters
Research is the invisible hand that powers America’s progress. It unlocks discoveries and creates opportunity. It develops new technologies and new ways of doing things.
Learn more about ASU discoveries that are contributing to changing the world and making America the world’s leading economic power at researchmatters.asu.edu.
###
END
New AI tool gives a helping hand to x ray diagnosis
2025-07-10
ELSE PRESS RELEASES FROM THIS DATE:
New Leicester study reveals hidden heart risks in women with Type 2 Diabetes
2025-07-10
Women with type 2 diabetes are nearly twice as likely as men to have hidden heart damage, according to a major new study by Leicester researchers funded through a National Institute for Health and Care Research (NIHR) Professorship.
The research, published in the Journal of Cardiovascular Magnetic Resonance, is one of the most detailed investigations into coronary microvascular dysfunction (CMD) to uncover sex-specific risk patterns in people with no signs of heart disease.
CMD is a form of early, silent heart damage caused by impaired blood flow in the ...
Over 400 different types of nerve cell have been grown – far more than ever before
2025-07-10
Nerve cells are not just nerve cells. Depending on how finely we distinguish, there are several hundred to several thousand different types of nerve cell in the human brain according to the latest calculations. These cell types vary in their function, in the number and length of their cellular appendages, and in their interconnections. They emit different neurotransmitters into our synapses and, depending on the region of the brain – for example, the cerebral cortex or the midbrain – different cell ...
Newly discovered molecule may explain reduced muscle mass in type 2 diabetes
2025-07-10
Researchers at Karolinska Institutet have discovered a previously unknown molecule that may explain why people with type 2 diabetes often suffer from muscle weakness and muscle loss – a condition that has a major impact on quality of life and overall health.
In the new study, published in Sciences Advances, researchers have identified a previously unknown molecule, TMEM9B-AS1, which may explain why people with type 2 diabetes often suffer from muscle weakness and loss of muscle mass. The molecule is a long non-coding RNA that plays ...
Rheumatoid arthritis and muscle wasting: New review points to overlooked complications
2025-07-10
Rheumatoid arthritis (RA) is a chronic autoimmune disease that affects individuals across all ages and genders. While its most visible impact is on the joints, RA also contributes to accelerated musculoskeletal ageing, often leading to progressive muscle degeneration and reduced muscle function. Emerging research has identified a specific form of muscle loss in RA—known as myopenia—which differs significantly from other disease-related muscle-wasting conditions such as cancer cachexia or heart failure. Unlike those conditions, myopenia is characterized by a decline in muscle mass without concurrent fat loss and can manifest across all age groups.
Despite ...
Overcoming intrinsic dispersion locking by misaligned bilayer metagratings
2025-07-10
Wavelength and propagation direction (angle) are two fundamental properties of light. The ability to selectively control both a specific wavelength and a specific angle forms the physical foundation for many advanced optical applications. However, due to the intrinsic dispersion in periodic systems, there exists an intrinsic locking relationship between angle and wavelength in the resonant spectrum. As a result, it has been widely accepted that changing the angle of incidence inevitably shifts the filtering wavelength of optical devices. This relationship between angle and wavelength in resonant spectra makes their independent ...
Vaccines work: Cohort data from Denmark show real-world evidence of stable protection against HPV-related cervical cancer
2025-07-10
Among the more than 100 types of human papillomavirus (HPV), at least 14 are considered as ‘high-risk’ types which can cause (cervical) cancer. After breast cancer, cervical cancer is the most common cancer in Europe among women aged 15–44 years [1].
Before HPV vaccination among teenage girls started in Denmark, high-risk HPV was found in all cervical cancers. HPV types 16/18 accounted for around three quarters (74%) of cervical cancers. These two types are covered in the 4-valent HPV vaccine offered to girls since 2008 as well as the 9-valent vaccine which has been in use in Denmark since November 2017. One third (26%) of cervical cancers prior to the HPV immunisation ...
Underwater shaped charge explosions: a comprehensive experimental study on coupling dynamics
2025-07-10
In a recent study published in Engineering, researchers from Harbin Engineering University have conducted an in-depth experimental investigation into the complex coupling dynamics of metal jets, waves, and bubbles generated during the underwater explosion of shaped charges. This research provides valuable insights into the behavior of shaped charges in underwater environments, which is crucial for understanding their potential applications and impacts.
The study was designed to analyze the characteristics of metal ...
Wristband sensor provides all-in-one monitoring for diabetes and cardiovascular care
2025-07-10
A new wearable wristband could significantly improve diabetes management by continuously tracking not only glucose but also other chemical and cardiovascular signals that influence disease progression and overall health. The technology was published in Nature Biomedical Engineering.
The flexible wristband consists of a microneedle array that painlessly samples interstitial fluid under the skin to measure glucose, lactate and alcohol in real time using three different enzymes embedded within the tiny needles. Designed for easy replacement, the microneedle array can be swapped out to tailor ...
Unveiling the spatiotemporal landscape of Ganoderma lingzhi: insights into ganoderic acid distribution and biosynthesis
2025-07-10
A recent study published in Engineering has provided new insights into the spatiotemporal distribution and biosynthesis of ganoderic acids (GAs) in Ganoderma lingzhi (G. lingzhi), a mushroom renowned for its medicinal properties in traditional Chinese medicine. The research, led by scientists from Northeast Forestry University, China, China Academy of Chinese Medical Sciences, and the University of Macau, utilized a multi-omics approach to map the distribution of GAs and elucidate their biosynthetic pathways.
G. lingzhi, often referred to as the “mushroom of immortality,” has been used in traditional Chinese medicine for over 2000 years. It contains various bioactive substances, ...
Quality and antibiotic resistance risks in livestock probiotics in China
2025-07-10
A recent study published in Engineering has shed light on the quality and potential antibiotic resistance dissemination risks associated with livestock probiotics in China. The research, conducted by a team from the Jiangsu Academy of Agricultural Sciences and Yangzhou University, analyzed 95 non-duplicate commercial probiotic products for livestock from across China, revealing significant issues in labeling accuracy, strain composition, and the presence of antibiotic resistance genes (ARGs).
The study found that the labeling compliance rate for Lactobacillus was alarmingly low at just 11%, with approximately ...