AI tool predicts repeat heart attack risk for cancer patients
- 6 March 2026
- Researchers have developed an AI tool that predicts the risk of further heart attacks in people with cancer
- Cancer patients often have weakened cardiovascular system and different cancers present different blood risks
- Researchers analysed outcomes for more than 47,000 people with cancer
An AI tool that predicts the risk of further heart attacks in people with cancer has been developed by an international team of researchers led by the University of Leicester.
Cancer patients who suffer a heart attack are at a higher risk of further attacks because of their weakened cardiovascular system. The type of cancer can also affect the risk of bleeding and arterial blood clotting so different treatments are required.
The AI tool, ONCO-ACS, uses machine learning to estimate a patient’s risk of death, major bleeding, or recurrent cardiovascular events within six months of a heart attack.
Senior author Professor David Adlam, interventional cardiologist from the University of Leicester’s department of cardiovascular sciences, said: “Significant advances in the management of heart disease and cancer alike have created new opportunities for these conditions to coexist.
“As a result, the growing overlap between cancer and heart attacks will confront cardiologists and oncologists with an increasingly complex patient population.
“We are addressing this pressing issue through a real-world data perspective.”
The research, published in The Lancet on 31 January 2026, draws on the Virtual Cardio-Oncology Research Initiative (VICORI), a national research platform for England that links routinely collected electronic health records from multiple sources.
Researchers can explore how cancer and cardiovascular disease interact over time by capturing a patient’s NHS journey.
VICORI is supported by the British Heart Foundation Data Science Centre and the Health Data Research UK (HDR UK) Big Data for Complex Diseases programme, which help researchers securely access and analyse data at population scale.
Using this linked dataset, alongside comparable data from Sweden and Switzerland, researchers analysed outcomes for more than one million heart attack patients, including over 47,000 people with cancer.
The scale and depth of the data allowed the team to train and validate an AI model that outperformed existing risk scores, which were not designed to account for the additional complexity introduced by cancer and its treatments.
Clinicians have historically lacked tools that reflect the difficult balance of risks which cancer patients face after a heart attack and ONCO-ACS aims to address this gap by incorporating cancer-specific information alongside standard cardiovascular factors to support more personalised treatment decisions.
Researchers hope that the tool could help clinicians better identify patients who may benefit from more intensive monitoring or tailored therapies, while avoiding unnecessary risks for others.
The VICORI dataset brings together cancer registry data from the National Cancer Registration and Analysis Service with cardiovascular audit data held by the National Institute for Cardiovascular Outcomes Research, alongside hospital admissions and mortality records.
HDR UK says that its role in supporting data infrastructure such as VICORI highlights the importance of secure, linked health data in enabling advanced data science and AI research.
Meanwhile, in February 2026 the government launched its National Cancer Plan, which commits to ensuring that three in four people diagnosed with cancer from 2035 onwards are cancer-free or living well after five years.
