Artificial intelligence may be used to aid in clinical decision-making following total joint replacement surgeries, according to a study from the New York City-based Hospital for Special Surgery.
Researchers used data from 7,239 hip and 6,480 knee replacement surgeries performed at Hospital for Special Surgery between 2007 and 2012 to calculate whether the patient will report a minimally clinically important difference in symptoms two years following surgery. The researchers then created models to predict which patients would report symptoms based on patient factors such as demographics, medical history and insurance.
"The least valuable health care is that which is not wanted or needed," said Catherine MacLean, MD, PhD, Hospital for Special Surgery chief value medical officer and senior author of the study. "Accurate prediction of whether individual patients will achieve a meaningful improvement after a procedure will greatly assist patients and their physicians in determining the best course of therapy — and in avoiding those that are unlikely to work."
The researchers reported machine learning can improve clinical decision-making by helping physicians prioritize aspects of a patient's care following surgery based on predicted outcomes.
Additionally, the researchers are creating decision-aids for surgeons to use to determine if a patient would receive a minimally clinically important difference in symptoms based on their characteristics.
"Pain and function are subjective, so asking patients themselves how they're doing is necessary. For patients considering surgery, perhaps even more important, is understanding whether surgery is likely to improve their pain and function and get them back to the activities they love most —- which is always our overarching goal at HSS," said Mark Fontana, PhD, Senior Director of Data Science at Hospital for Special Surgery and lead author of the study.