Machine Learning Model Links Insulin Resistance to 12 Cancer Types

Researchers have demonstrated for the first time that insulin resistance is a risk factor for 12 types of cancer using a machine learning-based prediction model applied to half a million participants from the UK Biobank. The tool, called AI-IR, predicts insulin resistance in individuals based on nine different pieces of medical information obtained through standard health checkups, providing the first population-scale evidence of the connection between insulin resistance and cancer.

The research team successfully used their machine learning tool to prove a link between insulin resistance and several kinds of cancer. 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. With AI-IR, researchers have provided the first population-scale evidence that insulin resistance is a risk factor for cancer.

AI-IR could be easily implemented to identify high-risk individuals and enable focused screening of diabetes, cardiovascular disease and cancer. 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, but AI-IR provides a robust and scalable alternative for evaluating insulin resistance at the population scale.

By combining nine clinical parameters into a single metric, AI-IR can detect insulin resistance that body mass index (BMI) alone cannot explain. Currently, BMI is commonly used to predict an individual's insulin resistance and knock-on susceptibility to related cancers, but this approach has limitations with false positives and false negatives. The researchers demonstrated not only AI-IR's predictive power but also that their model is robust under various conditions.

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.

The research was published in Nature Communications and was supported by multiple funding sources including the University of Tokyo Excellent Young Researcher Program, Japan Agency for Medical Research and Development, Japan Society for the Promotion of Science, and several other foundations. The team is 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.