ASU Team Creates 3D Bone Atlas to End Elder Abuse

“Only our bodies know the truth. Bones don’t lie,” writes Tayari Jones in “An American Marriage.”

No one understands the power of this statement better than Katelyn Bolhofner. An assistant professor of forensic anthropology at Arizona State University’s School of Interdisciplinary Forensic Science, she is an expert in skeletal biology who has lent her prowess to the FBI extracting actionable information from degraded and burned bones. She has also conducted research funded by grants from the National Science Foundation and the Wenner-Gren Foundation.

Now, Bolhofner has teamed up with Kevin Gary, associate professor of software engineering in the School of Computer Science and Augmented Intelligence, part of ASU’s Ira A. Fulton Schools of Engineering, to create a 3D atlas of the skeletal bones.

The research duo wants to tackle a difficult and growing problem: elder abuse.

One of the biggest challenges in handling elder abuse cases is that it can be difficult for criminologists, pathologists, and other professionals to differentiate between accidental injuries and those that result from neglect or intentional harm. So, with a grant from the National Institute of Justice, Gary and Bolhofner combined their expertise to create digital tools to diagnose bone fractures. Their software solution will enable law enforcement to better investigate elder abuse cases and help caregivers and medical responders understand when intervention is needed.

According to the U.S. Department of Justice, approximately one in ten Americans over the age of 65 experience some form of abuse each year. Physical and psychological abuse can contribute to serious and troubling declines in the health of older adults.

Bolhofner explains that forensic science has already created similar tools to help authorities deal with domestic violence and child abuse.

“I realized that we don’t have the same standards for interpreting the context of fractures in older people,” she says. “The reason we can’t apply the same standard to all patients is that bone density changes over the course of our lives. As most of us age, our bone density naturally decreases.”

With support from the Maricopa County Medical Examiner’s Office, Bolhofner began collecting data that could help authorities differentiate between a broken hip from a fall and a fracture from a push, or identify an untreated, poorly healed arm fracture. For the project, she combined the medical examiner’s records with the results of her own laser bone scans.

As she worked, she began to wonder if technology could help her.

Agile engineering for adaptable solutions

Bolhofner reached out to Gary, an associate professor and software engineer with experience building healthcare computing applications. He also teaches courses in the School of Computer Science and Augmented Intelligence, such as SER 516 Software Agility and SER 421 Web-Based Applications. He saw Bolhofner’s project as an ideal learning opportunity for his students.

Gary worked with a small group of master’s students to create a software system to implement Bolhofner’s ideas. Their web application allows users to view and compare 3D bone scans, assemble an online notebook, use digital tools to take measurements and collect data, and, most importantly, share what they’ve learned with other professionals.

Gary says engaging experts is a critical part of the project.

“In many cases, we’re replacing resources that are quite outdated. Some of this work is still done with pen and paper,” he says. “Our plan is to make the skeletal bone atlas available to the forensic science community.”

He also believes the project was a useful way for his students to see agile software engineering concepts in action, applied in real-world situations. Agile software engineering is a style of development in which engineers work in small teams focused on delivering individual pieces of software.

The team demonstrated the system at the spring 2024 Innovation Showcase held on ASU’s Polytechnic campus, which is also home to the school’s software engineering program.

Gary believes the experience was very beneficial and prepared the students for their future work.

“When student teams write software in my lab, I guide them in the same way I would for industrial projects,” Gary says. “The students get to see a lot of the things they learned in class, like how to manage design requirements and find a technical solution, and put them into practice.”

Artificial intelligence can help human experts

In their work, Gary and Bolhofner speculated that artificial intelligence, or AI, could provide better options for experts. They wondered whether AI could be used to help adult protective services identify cases of abuse that might otherwise go unnoticed. They considered how AI could reduce bias among forensic experts when they are called to testify in criminal proceedings.

Gary is leading the development of a machine learning system, a type of AI in which his software will take bone scans and other data from the app. This data will be combined with probability information, allowing the atlas to identify patterns. The information can then be reported back to the expert user. The system can warn a user that a certain type of fracture is likely not accidental and prompt the expert to take action, such as removing an elderly person from a dangerous environment.

The researchers will then gather feedback from potential professional users. In February, Gary and Bolhofner will lead a workshop on usability at a conference hosted by the American Academy of Forensic Sciences. Gaining user acceptance in this specialized field requires user-centered design, and the team hopes to gain valuable insights from anthropologists, law enforcement specialists and members of the academy.

Although elder abuse is a serious and difficult topic, Bolhofner is motivated by a desire to protect one of our most vulnerable populations.

“There are criminal applications for this project, because it can ensure the fairest outcome for a person who is a victim of abuse,” Bolhofner says. “But there is also a sense of hope that the project will allow older people to get help before it is too late.”

She adds: “We want to be the voice of those who perhaps cannot speak for themselves.”