AI assistance could cut screening-related costs by up to 30%
Integrating artificial intelligence-based tools into breast cancer screening settings could result in significant cost savings for organizations.
In fact, new data indicate that AI—when deployed as a delegation assistant—could save organizations as much as 30% in screening costs without compromising patient safety. Experts recently shared how this can be achieved in Nature Communications.
“The rising global incidence of breast cancer and the persistent shortage of specialized radiologists have heightened the demand for innovative solutions in mammography screening,” corresponding author Mehmet Eren Ahsen, PhD, with the Department of Business Administration at University of Illinois at Urbana-Champaign, and colleagues noted. “Artificial intelligence has emerged as a promising tool to bridge this demand-supply gap, with potential applications ranging from full automation to integrated AI-human decision-making.”
For their work, the team developed a decision model to compare the benefits of AI two different roles—one involving its use as an automation tool that works independently and one that deploys it as a delegation tool that allocates reads to AI or radiologists. Its performance in each role was compared to that of radiologists reading without assistance to determine how AI might impact costs associated with false positives and false negatives. Using real world data, multiple cost factors were considered, including read times, expenses related to follow-ups, litigation costs for missed diagnoses, the need for supplemental imaging, and more.
Through this, the group found that deploying an AI delegation strategy—where AI triages mammograms and identifies them as either low- or high-risk—would provide the most cost savings, ranging from 17.5% to 31.1% compared to the expense of radiologist-only reads.
“The numerical experiments highlight both the practicality and benefits of the proposed approach. Based on the current capabilities of AI in mammography and existing clinical practices, our findings indicate that a human-machine combined workflow (the delegation strategy) emerges as the most effective option,” the authors noted. “By leveraging AI to assign specific tasks to human experts while automating others, healthcare organizations can unlock substantial efficiencies and cost savings.”
The group suggested their findings offer organizations valuable insight into how to best deploy AI in clinical settings, though their work was specific to breast cancer screening workflows and expenses.
Learn more about their findings here.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.