Pathologists at Dartmouth-Hitchcock are looking to curb the use of unnecessary blood transfusions for non-bleeding patients by adding a “best-practice alert” in the patient’s EMR, with the hope of reducing risk of complications and costs.
“We figured out how to harness the power of the electronic medical record to embed evidence-based transfusion criteria into the computerized physician order entry process through the best practices alert functionality,” Dr. Nancy Dunbar, who led the implementation, said in a statement.
Dartmouth-Hitchcock’s Norris Cotton Cancer Center issued new guidelines on transfusion practices, having found that not all providers were following evidence-based protocols.
Transforming Patient Care: The Role of AI-Powered Assistants
The progress in artificial intelligence (AI) is reshaping patient care, across various dimensions, from facilitating faster discharge to curating treatment plans and suggesting lifestyle changes.
By using the EMR, Dunbar said pathologists are provided with “real-time” education and reminders at a moment’s notice of each order. The New Hampshire academic medical center studied its new transfusion guidelines and found that the proportion of two-unit transfusions decreased after the implementation of the electronic best practices alert — from 47 percent to 15 percent.
Curbing unnecessary two-unit transfusions could lead to big savings; there is growing evidence that such transfusions can increase the risk of a hospital-acquired infection like sepsis and pneumonia.
In addition, blood is often a scarce and expensive resource — especially globally — so more methodically determining which patients most need a transfusion could go a long way in improving outcomes.
There are exceptions, including cases of trauma and hemorrhaging, or both, according to a study from Johns Hopkins.
Reducing Clinical and Staff Burnout with AI Automation
As technology advances, AI-powered tools will increasingly reduce the administrative burdens on healthcare providers.
“This project in transfusion practice highlights the potential for information technology to potentially improve the quality of medical care in many other sites at our institution,” Dunbar said.
Several startups have begun to tackle the issue, including Silicon Valley’s Gauss Surgical. It has developed an iPad app that can scan surgical surfaces covered in blood, chiefly pieces of gauze that soak up blood during surgery. Currently, many surgeons monitor blood loss by psychically weighing gauze or by simply through visual estimation.