For the first time, researchers have used machine learning to identify the most important drivers of cancer survival across nearly all countries worldwide — and one of the leading researchers behind the initiative was Milit Patel, an undergraduate student at The University of Texas at Austin. The paper was recently published in one of the world’s most-cited cancer journals, Annals of Oncology.
The research identifies which improvements or policy changes can be made in almost any nation worldwide to have the greatest impact on cancer survival. Patel developed the machine learning model used in the study, which is based on data from global health systems. It’s also behind a new online tool that shows which factors — such as national wealth and access to radiotherapy and health coverage — are most strongly associated with cancer outcomes in a given country.
“We chose to use machine learning models because they allow us to generate estimates and predictions specific to each country,” said Patel, the paper’s first and corresponding author and a biochemistry senior. “We are, of course, aware of the limitations of population-level data, but we hope these findings can guide cancer-system planning globally.”
Patel, who is minoring in statistics and data science, health care reform and innovation business, said his starting point was earlier lessons from his UT statistics and data science courses. He also credits on-campus mentorship and other opportunities — such as participating in the College of Natural Sciences’ Freshman Research Initiative and working on an ongoing thesis project at UT’s Dell Medical School that uses artificial intelligence to prioritize cancer drug candidates.
Each opportunity led to collaborations with researchers at Memorial Sloan Kettering Cancer Center, MD Anderson Cancer Center, Massachusetts Institute of Technology, Massachusetts General Hospital/Harvard Medical School, and, via a Google Summer of Code project, the National Institutes of Health.
Through these collaborations, Patel has contributed to research on how statins affect cell signaling in ovarian cancer, on ways to improve real-time decision-making for clinical principal investigators, and on the ethical and policy implications of deploying AI in health care. He has also worked to build an AI system that enables researchers and clinicians to analyze complex cancer genomic datasets using natural language queries.
“The skills I developed at UT absolutely allowed me to gain access to top cancer institutes to conduct specialized research,” Patel said.
For the new paper, the researchers used machine learning, a form of artificial intelligence, to analyze data on cancer incidence and mortality from the Global Cancer Observatory for 185 countries. They also gathered information on health systems from the World Health Organization, the World Bank, United Nations agencies, and the Directory of Radiotherapy Centres to better understand how various factors relate to cancer outcomes across countries.
“Global cancer outcomes vary widely, largely due to differences in national health systems,” said Edward Christopher Dee, M.D., resident physician in radiation oncology at Memorial Sloan Kettering Cancer Center, who co-led the study with Patel. “We wanted to create an actionable, data-driven framework that helps countries identify their most impactful policy levers to reduce cancer mortality. We found that access to radiotherapy, universal health coverage, and economic strength were often important levers associated with better national cancer outcomes.”
This study was funded by the National Cancer Institute; the National Heart, Lung, and Blood Institute; the Prostate Cancer Foundation; and the Swiss National Science Foundation.
Patel’s model generates mortality-to-incidence ratios, which reflect the proportion of cancer cases that result in death, serving as a proxy for the effectiveness of cancer care. In each country’s graph in the online tool, green bars represent factors that are currently most strongly and positively associated with improved cancer outcomes there, signaling that continued or increased investment in that area is likely to have a meaningful impact.
“Beyond merely describing disparities, our approach offers actionable, data-driven road maps for policymakers, showing precisely which health system investments yield the greatest impact in each country,” Patel said. “As the global cancer burden grows, these insights can help nations prioritize resources and close survival gaps.”
Entering the start of the last semester before he graduates, Patel reflected on starting in academic research as a first-year student in UT’s Freshman Research Initiative “Virtual Cures” lab, where he worked under research educator Josh Beckham. FRI enables hundreds of students to conduct real-world research with peers and faculty members early in their undergraduate careers.
“I learned core wet-lab and computational approaches to protein modeling,” Patel said. “That early exposure made it clear I wanted to work at the intersection of biology, computation and health systems.”
