New research conducted by North Carolina State University and the University of South Florida shows that a recently released forensic software that determines the age of a person based on the remains of their skeleton has multiple flaws, researchers warn.
According to a press release, the researchers report that the new software incorrectly estimates the age of an individual’s bones by over 14 years.
“Estimating someone’s age at death, based on skeletal remains, helps to build a biological profile of the deceased,” says Ann Ross, a professor of biological sciences at NC State and co-author of a paper on the work.
“That’s important information for identifying unidentified remains, and can also be important in law enforcement contexts.”
The computer program, which is called DXAGE, was released in 2018 to streamline age estimation based on a person’s bone mineral density. However, according to Ross and his co-worker, Jonathan Bethard, an assistant professor of anthropology at USF, the DXAGE sample size was limited to the remains of only 100 females.
The researchers used bone mineral density (BMD) data from a large randomised sample to determine DXAGE’s efficiency. The report notes that a total of 470 females were chosen to take part in the National Health and Nutrition Examination Survey.
According to the report, the researchers said that the DXAGE estimates were off by 14.25 years. However, researchers found out the bone mineral density data of those women that took part in the survey varied greatly between each participant.
“We think this inaccuracy is primarily due to the small sample size used in developing DXAGE,” Bethard says. “It may also be due, in part, to DXAGE relying on remains from cemeteries, where they may have been buried for decades. Burial means that some of the minerals in the bones may have leached into the environment.”
According to Ross, the DXAGE’s black box neural networking program makes it increasingly difficult for forensic experts to operate the technology.
“That poses a problem if forensic experts are asked to testify on how they arrived at their age-of-death estimates in a court of law.
“We already have a technique for estimating age-of-death based on bone mineral density, which relies on linear regression; I helped develop it,” Ross says. “That technique proved to be more accurate than DXAGE in estimating the age for the 470 women we evaluated in this study. And it allows forensic experts to explain their estimates when called on to testify.”
The researcher says that the inaccurate results displayed in the survey highlight the importance of having to validate software tools such as the DXAGE.
“A lot of new software tools are becoming available to the forensic community,” Ross says. “We need to ensure the validity of these tools before putting them into practice.”