CHAMPAIGN, Ill. — The most effective way to harness the power of artificial intelligence when screening for breast cancer may be through collaboration with human radiologists — not by wholesale replacing them, says new research co-written by a University of Illinois Urbana-Champaign expert in the intersection of health care and technology.

The study finds that a “delegation” strategy — where AI helps triage low-risk mammograms and flags higher-risk cases for closer inspection by human radiologists — could reduce screening costs by as much as 30% without compromising patient safety.

The findings could help shape how hospitals and clinics integrate AI into their diagnostic workflows amid a growing demand for early breast cancer detection and a shortage of radiologists, said Mehmet Eren Ahsen, a professor of business administration and Deloitte Scholar at Illinois.

“We often hear the question: Can AI replace this or that profession?” Ahsen said. “In this case, our research shows that the answer is ‘Not exactly, but it can certainly help.’ We found that the real value of AI comes not from replacing humans, but from helping them via strategic task-sharing.”

The study, which was published by the journal Nature Communications, was co-written by Mehmet U. S. Ayvaci and Radha Mookerjee of the University of Texas at Dallas; and Gustavo Stolovitzky of the NYU Grossman School of Medicine and NYU Langone Health.

The researchers developed a decision model to compare three decision-making strategies in breast cancer screening: an expert-alone strategy — the current clinical norm in which radiologists read every mammogram; an automation strategy, in which AI assessed all mammograms without human oversight; and a delegation strategy, in which AI performed an initial screening and referred ambiguous or high-risk cases to radiologists.

The model accounted for a wide range of costs, including implementation, radiologist time, follow-up procedures and potential litigation. It evaluated outcomes using real-world data from a global AI crowdsourcing challenge for mammography, which was sponsored as part of the White House Office of Science and Technology Policy’s Cancer Moonshot initiative of 2016-17.

The researchers found that the delegation model outperformed both the full automation and the expert-alone approaches, yielding up to 30.1% in cost savings, according to the paper.

While the idea of fully automating radiological tasks may seem appealing from an efficiency standpoint, the study cautions that current AI systems still fall short of replacing human judgment in complex or borderline cases.

“AI is excellent at identifying low-risk mammograms that are relatively straightforward and easy to interpret,” said Ahsen, also the Health Innovation Professor at the Carle Illinois College of Medicine. “But for high-risk or ambiguous cases, radiologists still outperform AI. The delegation strategy leverages this strength: AI streamlines the workload, and humans focus on the toughest cases.”

With nearly 40 million mammograms performed annually in the U.S. alone, breast cancer screening is a critical public health tool. Yet the process is time-intensive and costly, in both labor and follow-up procedures triggered by false positives. And when cancers are missed, the resulting false negatives can lead to significant harm for patients and health care providers, Ahsen said.

“One of the issues in mammography is, because of the sheer number of screenings performed, that it generates so many false positives and false negatives,” Ahsen said. “If you have a 10% false positive rate out of 40 million mammograms per year, that’s four million women who are being recalled to the hospital for more appointments, screenings and tests, and potentially biopsies.”

That whole process only increases stress and anxiety for the patient, Ahsen said.

“It’s a nightmare scenario,” he said. “Follow-up appointments often take weeks, leaving patients with a black cloud hanging over their heads. It’s a very stressful time for them.”

With AI and the delegation model, it’s possible that health care providers could streamline the process.

“You get screened, AI sees something it doesn’t like and immediately flags you for follow-up, all while you’re still at the hospital,” Ahsen said. “It has the potential to be that much more efficient of a workflow.”

The research also raises broader questions about how AI should be implemented and regulated in medicine.

“The delegation strategy works best when breast cancer prevalence is either low or moderate,” Ahsen said. “In high-prevalence populations, a greater reliance on human experts may still be warranted. But an AI-heavy strategy also might work well in situations where there aren’t a lot of radiologists — in developing countries, for example.”

Another potential landmine involves legal liability. If AI systems are held to stricter liability standards than human clinicians, then “health care organizations may shy away from automation strategies involving AI, even when they are cost-effective,” Ahsen said.

The findings are potentially applicable to other areas of medicine such as pathology and dermatology, where diagnostic accuracy is critical, but AI is potentially able to improve workflow efficiency.

With the infinite work capacity of AI, “we can use it 24/7, and it doesn’t need to take a coffee break,” Ahsen said. “AI is only going to continue to make inroads into health care, and our framework can guide hospitals, insurers, policymakers and health care practitioners in making evidence-based decisions about AI integration.

“We’re not just interrogating what AI can do — we’re asking if it should do it, and when, how and under what conditions it should be deployed as a tool to help humans.”

Journal

Nature Communications

DOI

10.1038/s41467-025-57409-1

Artificial intelligence has made remarkable strides in diagnostic radiology, with algorithms now capable of detecting subtle abnormalities in mammographic images with impressive accuracy. Despite these technological advancements, real-world adoption and acceptance of AI-assisted diagnostic tools remain limited, largely due to concerns about data privacy, inherent biases within AI models, and a general lack of understanding about how these systems function. Researchers have often overlooked the critical viewpoint of patients — the ultimate recipients of these diagnostic technologies — until now.

The lead author, Dr. Basak E. Dogan, a clinical professor of radiology and breast imaging research director at the University of Texas Southwestern Medical Center, emphasizes that patient trust is a cornerstone of successful AI integration. “Without patient confidence in AI, we are likely to see disruptions in adherence to recommended screening schedules, which can negatively impact early detection and health outcomes,” she remarks. This study represents an essential step in evaluating the patient voice to inform responsible AI adoption.

To explore patient sentiments, Dr. Dogan and her team developed a robust 29-question survey administered to patients undergoing breast cancer screening mammograms at their institution over a seven-month period in 2023. The survey was meticulously designed to capture participants’ demographic details, medical and familial breast cancer history, as well as their knowledge and views on AI, allowing for a granular understanding of how these variables interplay in trust formation.

Results from the 518 completed surveys revealed a cautiously optimistic stance toward AI. A striking 71% of respondents favored using AI as a complementary "second reader" alongside radiologists, suggesting an openness to augmented diagnostic workflows. However, only a small fraction, less than 5%, were comfortable with AI independently interpreting their mammograms. This highlights an enduring preference for human oversight, underscoring the perceived value of personal interaction in clinical care and concerns around transparency, algorithmic bias, and data privacy.

Importantly, the study uncovered clear associations between patient demographics and AI acceptance. Participants possessing education beyond college level or those with greater self-reported familiarity with AI technologies exhibited roughly twice the likelihood of endorsing AI integration in screening. This correlation underscores the role of education and knowledge dissemination in shaping AI receptivity and points toward the necessity of targeted informational campaigns to alleviate fears and misconceptions.

Racial and ethnic background emerged as a significant determinant of trust in AI. Hispanic and non-Hispanic Black respondents reported substantially higher apprehensions regarding AI bias and the security of their personal health data. This disparity most likely contributes to their comparatively lower acceptance rates of AI in mammography interpretation. These findings stress the imperative for culturally sensitive patient engagement and equity-focused AI development to mitigate distrust in traditionally underserved communities.

The influence of personal and familial medical history further nuances patient perspectives. Individuals who have close relatives diagnosed with breast cancer tend to exhibit a heightened vigilance, often requesting additional mammographic reviews regardless of whether an AI system or radiologist detected abnormalities. Intriguingly, these patients generally demonstrate strong trust in both AI and human evaluations when their mammograms yield negative results, illustrating a complex but coherent trust framework influenced by personal risk awareness.

Conversely, patients with a history of abnormal mammograms display increased propensity to seek follow-up diagnostics when discrepancies arise between AI and radiologist opinions, especially if the AI flags a potential abnormality not noticed by the human reader. This behavioral trend underscores the sensitivity of patients with prior screening complications and points to the importance of clear communication strategies to navigate conflicting diagnostic outputs.

The implications of these findings are profound for the future integration of AI in mammographic screening. The variation in trust based on sociodemographic and clinical factors mandates a personalized approach to AI deployment, one that aligns technological innovation with patient-centered care practices. Healthcare providers and AI developers must collaborate proactively to ensure that AI tools are transparent, ethically designed, and culturally competent.

Furthermore, this study advocates for continuous, dynamic patient engagement as AI technology evolves. Tracking shifts in patient perceptions over time will be critical to refining AI interfaces and educational materials, securing broad-based acceptance, and ultimately improving clinical outcomes. Dr. Dogan underscores that “trust in AI is not monolithic but highly individualized, contingent on prior experiences, educational background, and cultural context.”

Incorporating these patient perspectives into AI implementation policies holds promise for elevating the standard of breast cancer screening. Doing so can foster greater adherence to screening recommendations, reduce disparities in care, and enhance confidence in radiologic interpretation enhanced by AI. This research thus bridges a vital gap by foregrounding the patient experience in the rapidly advancing landscape of AI-assisted medical imaging.

As AI continues to revolutionize diagnostic radiology, the interplay between cutting-edge technology and human factors remains paramount. This study from the University of Texas Southwestern Medical Center pioneers a patient-centered framework to guide ethical and effective AI integration in mammography, heralding a future where technology and trust coalesce to combat breast cancer more efficiently. Stakeholders across healthcare must heed these insights to ensure that AI not only innovates but also resonates with the people it aims to serve.

Subject of Research: People
Article Title: Patient Perception of Artificial Intelligence Use in Interpretation of Screening Mammograms: A Survey Study
News Publication Date: 18-Apr-2025
Web References:

• Radiology: Imaging Cancer
• Radiological Society of North America (RSNA)
• RadiologyInfo.org Mammography Information
  References:
  “Patient Perception of Artificial Intelligence Use in Interpretation of Screening Mammograms: A Survey Study.” Collaborators: B. Bersu Ozcan, M.D., Yin Xi, Ph.D., Emily E. Knippa, M.D.
  Keywords: Mammography, Artificial intelligence, Radiology, Cancer screening, Cancer patients, Breast cancer, Social surveys