![\"From](\"https:\/\/news.utoledo.edu\/wp-content\/uploads\/2026\/09\/Champa-Jayasuriya-.jpg\")
From left, Dr. A. Champa Jayasuriya, incoming doctoral candidate Shyama Tripathy and graduate student Syam Sundar Nallamekala developed an AI model that can identify potential osteoporosis risk using existing CT scans, offering an alternative to traditional DEXA scans.<\/p><\/div>\n
“Once they have a fracture, then it is very severe, especially a hip fracture,” Jayasuriya said. “Sometimes they must get a full hip transplant, at which point they cannot go to work and somebody needs to take care of them. The burden is very high for the patient as well as society \u2014 it costs a billion dollars per year in the United States for these hip fractures.”<\/p>\n
Now working alongside graduate students Shyama Tripathy and Syam Sundar Nallamekala, Jayasuriya\u2019s team has developed an AI model that can analyze a patient’s existing CT scan data alongside clinical information to predict osteoporosis risk, potentially years before symptoms arise.<\/p>\n
The tool analyzes CT scans by isolating bone tissue and extracting 18 key bone-density features, discarding soft tissue and background imagery to focus exclusively on what the bone reveals. Combined with clinical data points such as age, body mass index and lab markers, the model produces a high, medium or low risk assessment for potential osteoporosis, within minutes.<\/p>\n
In previous testing, the model demonstrated approximately 88% accuracy in identifying patients at risk of osteoporosis. The next phase of testing, supported by a $50,000 National Science Foundation grant through UToledo’s I-Corps program, will help them focus on improving the model’s accuracy, with a goal of reaching up to 90%.<\/p>\n
A dual-energy X-ray absorptiometry, or DEXA, scan is the current standard method for measuring bone density, but scheduling delays mean many at-risk patients go undetected until a fracture brings them to the emergency department. This new AI tool is designed to work from imaging data that many patients already have on file, eliminating the need to wait weeks for a separate DEXA scan appointment.<\/p>\n
“My motivation is that healthcare is really expensive in the U.S.,” said Tripathy, who recently completed his master’s degree in computer science and engineering at UToledo and will return in January to begin his doctorate. “By offering this as a service to both physicians and the direct patient, they can save money on expensive exploratory tests.”<\/p>\n
The research team has conducted initial testing with UToledo patient records under institutional review board approval, and a manuscript is currently being finalized for journal submission.<\/p>\n
With the technology at the prototype stage, the research team has now filed a patent application through The University of Toledo Technology Transfer Office to protect the AI model and its underlying technology.<\/p>\n
Meanwhile, the $50,000 grant from the National Science Foundation will support the next phase of the project. The I-Corps\u2019 entrepreneurial training will help them focus on commercializing their research, including further testing and customer discovery with clinicians, radiologists and potential end users. The team will work with these groups to determine how the tool can best be deployed and what additional development is needed before broader release.<\/p>\n
“Once they’ve learned the process [of commercialization], it changes how they do research, how they do things,” said Norman Rapino, executive director of Rocket Innovations at UToledo, which administers the I-Corps program locally. “This training is not only to push stuff out, but to train the next generation of scientists and engineers to do things that create value for society.”<\/p>\n
Looking ahead, the research team is working to expand the model beyond its current focus on upper femur CT scans to include the hip, spine and other skeletal areas, while also working to standardize performance across CT scanners from different health systems, a key step toward broader clinical adoption and eventual Food and Drug Administration review.<\/p>\n","protected":false},"excerpt":{"rendered":" A $50,000 National Science Foundation grant will fund the next phase of testing for a web-based tool that could flag osteoporosis risk before a fracture ever occurs.<\/p>\n","protected":false},"author":932,"featured_media":100658,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[50,96,38,1,3,7],"tags":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/posts\/100657"}],"collection":[{"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/users\/932"}],"replies":[{"embeddable":true,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/comments?post=100657"}],"version-history":[{"count":3,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/posts\/100657\/revisions"}],"predecessor-version":[{"id":100660,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/posts\/100657\/revisions\/100660"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/media\/100658"}],"wp:attachment":[{"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/media?parent=100657"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/categories?post=100657"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news.utoledo.edu\/index.php\/wp-json\/wp\/v2\/tags?post=100657"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}![\"From](\"https:\/\/news.utoledo.edu\/wp-content\/uploads\/2026\/09\/Champa-Jayasuriya--150x150.jpg\")
<\/a>