AI-Guided Outreach Increased Cancer Screenings and Reduced Mortality, New Study Finds

New research suggests the most powerful use of AI in healthcare may be helping patients receive care before it's too late

BALTIMORE, July 6, 2026 — A machine learning program that identified patients overdue for colorectal cancer screening helped increase screening rates and was associated with significantly lower mortality, according to new research published in the INFORMS journal Manufacturing & Service Operations Management.

The study examined a real-world outreach initiative at Geisinger health system that used predictive analytics to identify patients at elevated risk for colorectal cancer and encourage them to schedule potentially life-saving screenings.

Researchers found that patients targeted through the program were 6% more likely to complete a colonoscopy within three months and 6.9% more likely within six months compared with similar patients who did not receive the outreach. Most notably, the program was associated with a 6.2% reduction in two-year mortality, representing a 43% decrease relative to the study's control group.

The study, “Cancer Screening Outreach Guided by Machine Learning: The Benefits of Proactive Care,” highlights how artificial intelligence can help healthcare providers move beyond predicting risk and toward proactively connecting patients with care. The authors of the study are Minje Park of the University of Hong Kong; Carri Chan of Columbia Business School; Keith Boell, Elliot Mitchell, and David Vawdrey of Geisinger; and Abdul Tariq of Children’s Hospital of Philadelphia.

“Our results showed that a proactive cancer screening outreach program guided by machine learning can significantly improve patient outcomes in addition to achieving higher disease detection rates,” said Park. “The program not only boosts screening participation but also meaningfully reduces mortality.”

Colorectal cancer is the second leading cause of cancer deaths in the United States, despite the fact that early detection can dramatically improve survival. Yet many eligible patients remain overdue for recommended screenings.

The Geisinger program sought to address that challenge by combining machine learning with personalized human outreach. The health system's algorithm analyzed information including complete blood count results, age and sex to identify patients at elevated risk among those who had not completed recommended screenings.

Patients flagged by the system received outreach from nurse coordinators who educated them about the benefits of colonoscopy and helped schedule appointments. The research suggests that one of the most effective uses of artificial intelligence in healthcare may be identifying patients who are likely to benefit from intervention and helping providers reach them before disease progresses.

“This work demonstrates an analytical framework for rigorously evaluating machine learning-aided outreach programs for other cancers and diseases,” said Chan. “Establishing unbiased estimates of the impact is critical for capacity planning of screening resources such as colonoscopies.”

“Colorectal cancer is one of the most preventable causes of cancer death if we can reach patients in time. This study shows that thoughtfully applied AI can do exactly that—identify individuals who might otherwise fall through the cracks and connect them to life‑saving screening,” added Vawdrey.

Researchers analyzed outcomes from the program, which has been operating since 2019. Their findings suggest that healthcare systems can use predictive analytics not only to identify risk but also to improve care delivery and patient engagement.

The study also provides a roadmap for hospitals and health systems seeking to scale similar programs. The authors note that factors such as screening capacity, communication strategies and disease severity should be considered when expanding proactive outreach efforts.

As healthcare organizations continue to invest heavily in artificial intelligence, the findings point to an important lesson: some of the biggest benefits may come not from replacing clinicians, but from helping patients receive care they might otherwise miss.

Read the full study here.

About INFORMS and Manufacturing & Service Operations Management

INFORMS is the world’s largest association for professionals and students in operations research, AI, analytics, data science and related disciplines, serving as a global authority in advancing cutting-edge practices and fostering an interdisciplinary community of innovation. INFORMS empowers its community to improve organizational performance and drive data-driven decision-making through its journals, conferences and resources. Learn more at www.informs.org or @informs.

Manufacturing & Service Operations Management, a leading journal published by INFORMS, publishes research on operations management in manufacturing and service industries that informs managerial and policy decisions.

###

Contact

Rebecca Seel

Public Affairs Specialist

[email protected]

(443) 757-3578