(Press-News.org) COLUMBUS, Ohio – Scientists have designed a new artificial intelligence model that emulates randomized clinical trials at determining the treatment options most effective at preventing stroke in people with heart disease.
The model was front-loaded with de-identified data on millions of patients gleaned from health care claims information submitted by employers, health plans and hospitals – a foundation model strategy similar to that of generative AI tools like ChatGPT.
By pre-training the model on a huge cache of general data, researchers could then fine-tune the model with information concerning specific health conditions and treatments – in this case, focusing on stroke risk – to estimate the causal effect of each therapy and determine which therapy would work best based on individual patient characteristics.
The team from The Ohio State University reported today (May 1, 2024) in the journal Patterns that their model outperformed seven existing models and came up with the same treatment recommendations as four randomized clinical trials.
“No existing algorithm can do this work,” said senior author Ping Zhang, associate professor of computer science and engineering and biomedical informatics at Ohio State. “Quantitatively, our method increased performance by 7% to 8% over other methods. And the comparison showed other methods could infer similar results, but they can’t produce a result exactly like a randomized clinical trial. Our method can.”
Replacing gold standard clinical research is not the point – but researchers hope machine learning could help save time and money by putting clinical trials on a faster track and support the personalization of patient care.
“Our model could be an acceleratory module that could help first identify a small group of candidate drugs that are effective to treat a disease, allowing clinicians to conduct randomized clinical trials on a limited scale with just a few drugs,” said first author Ruoqi Liu, a computer science and engineering PhD student in Zhang’s lab.
The team dubbed the proposed framework CURE: CaUsal tReatment Effect estimation.
The beauty of a treatment effect estimation model pre-trained with massive amounts of unlabeled real-world data is its applicability to a multitude of diseases and drugs, Liu said.
“We can pre-train the model on large-scale datasets without limiting it to any treatments. Then we fine-tune the pre-trained model on task-specific small-scale datasets so that the model can adapt quickly to different downstream tasks,” she said.
Unlabeled data used to pre-train the model came from MarketScan Commercial Claims and Encounters from 2012-2017, providing 3 million patient cases, 9,435 medical codes (including 282 diagnosis codes) and 9,153 medication codes.
Two of Liu’s model-constructing techniques added to CURE’s power: filling in gaps in patient records by pairing patient information with biomedical knowledge graphs that represent biomedical concepts and relationships, and pre-training a deep synergized patient data-knowledge foundation model using medical claims and knowledge graphs at scale.
“We also proposed KG-TREAT, a knowledge-enhanced foundation model, to synergize the patient data with the knowledge graphs to have the model better understand the patient data,” said Liu, who was the first author of a March Proceedings of the AAAI Conference on Artificial Intelligence paper describing the knowledge graph work.
To come up with treatment effect estimates, the model considers pre-trained data overlapped with more specific information on medical conditions and therapies, and after further fine-tuning, predicts which patient outcomes would correspond to different treatments.
As part of comparing the model to other machine learning tools and validating it against clinical trial results, the study showed that the broad pre-training is the backbone of CURE’s effectiveness – and incorporation of knowledge graphs improved its performance further.
Zhang envisions a day – pending Food and Drug Administration approval of AI as a decision-support tool – when clinicians could use this type of algorithm, loaded with electronic health record data from tens of millions of people, to access an actual patient’s “digital twin” and let the model function as a treatment guide.
“This model is better than a crystal ball: Based on big data and foundation model AI, we can have reasonable confidence to be able to say what treatment strategy is better,” said Zhang, who leads the Artificial Intelligence in Medicine Lab and is a core faculty member in the Translational Data Analytics Institute at Ohio State. “We want to put physicians in the driver’s seat to see whether this is something that can be helpful for them when they’re making critical decisions.”
This research was funded by the National Institutes of Health. Pin-Yu Chen of IBM Research was a study co-author of CURE in Patterns. Lingfei Wu of Anytime AI was a study co-author of KG-TREAT in AAAI.
#
Contact: Ping Zhang, Zhang.10631@osu.edu
Written by Emily Caldwell, Caldwell.151@osu.edu; 614-292-8152
END
PHILADELPHIA— Protein imbalances that increase brain cell excitability may explain why individuals with Alzheimer’s disease (AD) who also experience seizures demonstrate more rapid cognitive decline than those who do not experience seizures. These imbalances may be present in the brains of individuals before the onset of AD symptoms.The new findings, from a research team at the University of Pennsylvania’s Perelman School of Medicine, are published this week in Brain.
The team found ...
NEW ORLEANS, La. – Dedicated to excellence in patient safety, several Ochsner Health hospitals and partners throughout Louisiana and Mississippi have earned an “A” Hospital Safety Grade from The Leapfrog Group, a national nonprofit watchdog. Leapfrog assigns an “A,” “B,” “C,” “D” or “F” grade to general hospitals across the country based on over 30 measures of errors, accidents, injuries and infections as well as the systems hospitals ...
A new mobile game launching today allows anyone with a smartphone or tablet to take part in ocean exploration and discovery. Welcome to FathomVerse. Now available for download on the App Store and Google Play, FathomVerse allows players to interact with real underwater images to improve the artificial intelligence that helps researchers study ocean life. The game combines immersive imagery, compelling gameplay, and cutting-edge science to inspire a new wave of ocean explorers.
Scientists are collecting massive amounts of images and video to study marine life and assess ocean ...
A group of researchers at the University of Waterloo and the University of British Columbia have discovered a potential “cosmic glitch” in the universe’s gravity, explaining its strange behaviour on a cosmic scale.
For the last 100 years, physicists have relied upon Albert Einstein’s theory of “general relativity” to explain how gravity works throughout the universe. General relativity, proven accurate by countless tests and observations, suggests that gravity impacts ...
About The Study: For postmenopausal women, the Women’s Health Initiative (WHI) randomized clinical trials do not support menopausal hormone therapy to prevent cardiovascular disease or other chronic diseases. Menopausal hormone therapy is appropriate to treat bothersome vasomotor symptoms among women in early menopause, without contraindications, who are interested in taking hormone therapy. The WHI evidence does not support routine supplementation with calcium plus vitamin D for menopausal women to prevent fractures or a low-fat diet with increased fruits, vegetables, and grains to prevent ...
About The Study: The proportions of American Indian or Alaska Native, Black, and white females of reproductive age in states with effective abortion bans were higher than in states without such policies, while proportions for other racial and ethnic groups were lower. Although these restrictive laws were not based on race, they were concentrated in states with higher proportions of American Indian or Alaska Native and Black individuals, resulting in a differential effect of restrictive abortion laws in these groups. American Indian or Alaska Native and Black populations are disproportionately affected by disparities in pregnancy-related ...
The gut microbiota is the microbial community that occupies the gastrointestinal tract. It is responsible for producing enzymes, metabolites, and other molecules crucial for host metabolism and in response to the environment.
Consequently, a balanced gut microbiota is important for mammalian health in many ways, such as helping to regulate the immune and endocrine systems. This in turn, impacts the physiology of tissues throughout the body. However, little was known about the impact of the gut microbiota on host reproduction, ...
The health benefits of exercise are well known but new research shows that the body’s response to exercise is more complex and far-reaching than previously thought. In a study on rats, a team of scientists from across the United States has found that physical activity causes many cellular and molecular changes in all 19 of the organs they studied in the animals.
Exercise lowers the risk of many diseases, but scientists still don’t fully understand how exercise changes the body on a molecular level. Most studies have focused on a single organ, sex, or time point, and only include one or two data types.
To take a more comprehensive ...
Philadelphia, May 1, 2024 – Researchers from Children’s Hospital of Philadelphia (CHOP) have identified a causal genetic variant strongly associated with childhood obesity. The study provides new insight into the importance of the hypothalamus of the brain and its role in common childhood obesity and the target gene may serve as a druggable target for future therapeutic interventions. The findings were published today in the journal Cell Genomics.
Both environmental and genetic factors play critical roles in the increasing incidence of childhood ...
BURLNGTON, Vt.—For the past eight years, researchers have been conducting a groundbreaking study supported by the National Institutes of Health (NIH) Common Fund: The Molecular Transducers of Physical Activity Consortium (MoTrPAC). With nearly 2,600 volunteers, the study aims to examine the molecular effects of exercise on healthy adults and children, considering factors like age, race, and gender. The goal is to create comprehensive molecular maps of these changes and uncover why physical activity has significant health benefits.
“This ...