It’s long been understood that negative events or conditions encountered during childhood and adolescence, known medically as Adverse Childhood Experiences (ACEs), can have an array of health consequences in adulthood. According to a study recently published in the Journal of Medical Internet Research - Medical Informatics, new AI may be able to help providers treating adult patients who are grappling with the array of negative health conditions ACEs can cause.
For the study, Arash Shaban-Nejad, PhD, MPH, an assistant professor, and Nariman Ammar, PhD, a postdoctoral fellow, both at the Center for Biomedical Informatics in the Department of Pediatrics at the University of Tennessee Health Science Center, implemented an AI platform called Semantic Platform for Adverse Childhood Experiences Surveillance (SPACES) to help medical practitioners and health care workers with diagnosing ACEs in the early stages by using real-time data captured through conversations during in-person consultations.
"Current treatment options are long, complex, costly, and most of the time a non-transparent process," Dr. Shaban-Nejad explained in a statement. "We aim not only to assist health care practitioners in extracting, processing, and analyzing the information, but also to inform and empower patients to actively participate in their own health care decision-making process in close cooperation with medical and health care professionals.”
As the team explained in their report, “Explainable artificial intelligence is an emerging approach for promoting credibility, accountability, and trust in mission-critical areas such as medicine by combining machine-learning approaches with explanatory techniques that explicitly show what the decision criteria are and why (or how) they have been established. Hence, thinking about how machine learning could benefit from knowledge graphs that combine ‘common sense’ knowledge as well as semantic reasoning and causality models is a potential solution to this problem.”
Currently, they noted, many AI platforms don't provide enough explanation to interpret and justify decisions, prolonging the diagnosis and treatment processes. In response, the SPACES platform has functions that can mitigate many of these difficulties by detecting patient health disparity variants (geographic location, sexual identity, socioeconomic status, etc.), recommending intervention plans to health professionals, and allocating resources as needed.
To make real-time recommendations, the system instantly captures new resource interests, ACEs, and social determinants of health-related risk factors detected in the user’s current conversation and uses them to incrementally refine a personalized knowledge paragraph.
“The significance of the proposed approach lies in its ability to provide recommendations to the question-answering agent with the least effort from both the user and the healthcare practitioner,” researchers said.
The team’s prototype is intended for an array of users, including caregivers and healthcare professionals.