Insulin resistance — when the body doesn't properly respond to insulin, a hormone that helps control blood glucose levels — is one of the fundamental causes of diabetes. In addition to diabetes, it is widely known that insulin resistance can lead to cardiovascular, kidney and liver diseases. While insulin resistance is tightly associated with obesity, it has been difficult to evaluate insulin resistance itself in the clinic. For the first time, researchers including those from the University of Tokyo applied a machine learning-based prediction model of insulin resistance to half a million participants from the UK Biobank and demonstrated that insulin resistance is a risk factor for 12 types of cancer.
Diabetes is a common cause for concern around the world. Its connection to insulin resistance is a familiar concept to many, but what is less well known is that resistance to insulin is also suggested to be a risk factor for several cancers. However, the human body is a complex thing, and ascertaining causal connections between diseases and issues within the body is far from easy. Medical researchers explore different ways to search for these connections, and an increasingly common tool in their arsenal is artificial intelligence, in particular machine learning. Yuta Hiraike, a researcher from the University of Tokyo Hospital, and his team have successfully used a machine learning tool they created to prove a link between insulin resistance and several kinds of cancer.
“We recently made a tool, AI-IR, for predicting insulin resistance in individuals based on nine different pieces of medical information. It proved successful and made us think we could apply this tool to related concerns,” said Hiraike. “While a possible link between insulin resistance and cancer has been suggested, large-scale evidence has been limited due to the difficulty of evaluating insulin resistance in the clinic. But with AI-IR, we have provided the first population-scale evidence that insulin resistance is a risk factor for cancer. And since the nine input parameters for AI-IR are obtained through standard health checkups, AI-IR could be easily implemented to identify high-risk individuals and enable focused screening of diabetes, cardiovascular disease and cancer.”
It's common at present for body mass index (BMI), a measure for body fat, to predict an individual’s insulin resistance and knock-on susceptibility to related cancers. But with that there are false positives, where some obese people are considered metabolically healthy and don’t suffer the ill effects of obesity to the same degree as others, and false negatives, where people with ideal BMI end up suffering from insulin resistance or related concerns usually connected with obesity. Part of the challenge Hiraike and team faced was convincing reviewers of the paper that AI-IR could overcome these shortcomings and in a reliable, repeatable way. Thankfully, they demonstrated not only its predictive power but also that their model is robust under various conditions.
“When compared with directly measured insulin resistance in validation datasets, AI-IR achieved strong predictive performance. Directly measuring insulin resistance is impractical except for where patients are treated in specialized diabetes clinics. AI-IR provides a robust and scalable alternative for evaluating insulin resistance at the population scale,” said Hiraike. “By combining nine clinical parameters into a single metric, AI-IR can detect insulin resistance that BMI alone cannot explain. We are now working to understand how genetic differences between individuals influence this risk, and ultimately to link large-scale human data with molecular biology studies to develop better strategies to overcome insulin resistance.”
###
Journal: Chia-Lin Lee, Tomohide Yamada, Wei-Ju Liu, Kazuo Hara, Toshimasa Yamauchi, Shintaro Yanagimoto & Yuta Hiraike, “Machine learning-predicted insulin resistance is a risk factor for 12 types of cancer”, Nature Communications, https://doi.org/10.1038/s41467-026-68355-x
Funding: This work was supported by University of Tokyo Excellent Young Researcher Program, Japan Agency for Medical Research and Development (AMED) (Grant 24ek0210204h0001), Japan Society for the Promotion of Science (JSPS) KAKENHI – Early-Career Scientists (Grants 19K17976, 23K15387, 19K19432), JSPS KAKENHI – Challenging Research (Exploratory) (Grant 25K22704), JSPS KAKENHI – Fund for the Promotion of Joint International Research (A) (Grant 21KK0293), Japan Science and Technology Agency (JST) FOREST Program (Grant JPMJFR245I), Japan Foundation for Applied Enzymology – Front Runner of Future Diabetes Research (Grant 17F005), MSD Life Science Foundation, Takeda Science Foundation (Life Science Research Grant; Life Science Research Continuous Grant), Public Health Research Foundation, Mishima Kaiun Memorial Foundation, Japan Health Foundation, Kao Research Council for the Study of Healthcare Science, TANITA Healthy Weight Community Trust, Senri Life Science Foundation, Inamori Foundation, Mitsubishi Foundation, Japanese Biochemical Society, Lotte Foundation, The Vehicle Racing Commemorative Foundation, Taichung Veterans General Hospital (Grants TCVGH-1137313C, TCVGH-1137306D, TCVGH-1144302C, TCVGH-1144302D, TCVGH-VTA114V211, TCVGH-PNTHU1145001), National Science and Technology Council of Taiwan (Grants 113-2314-B-075A-003, 114-2314-B-075A-011-MY3).
Research Contact:
Yuta Hiraike
The University of Tokyo Hospital, The University of Tokyo,
7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, JAPAN
yhiraike@g.ecc.u-tokyo.ac.jp
The University of Tokyo Hospital - https://www.h.u-tokyo.ac.jp/english/
Press contact:
Mr. Rohan Mehra
Strategic Communications Group, The University of Tokyo,
7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8656, Japan
press-releases.adm@gs.mail.u-tokyo.ac.jp
About The University of Tokyo:
The University of Tokyo is Japan's leading university and one of the world's top research universities. The vast research output of some 6,000 researchers is published in the world's top journals across the arts and sciences. Our vibrant student body of around 15,000 undergraduate and 15,000 graduate students includes over 5,000 international students. Find out more at www.u-tokyo.ac.jp/en/ or follow us on X (formerly Twitter) at @UTokyo_News_en.
Nature Communications
Meta-analysis
People
Machine learning-predicted insulin resistance is a risk factor for 12 types of cancer
16-Feb-2026