Researchers have developed an AI-driven risk prediction tool that will help clinicians understand the harms facing cancer patients after they have had a heart attack.
The study describes how the researchers analysed data from more than one million patients to better understand the relationship between cancer and cardiovascular disease. The results, published in The Lancet, have informed the development of their risk prediction tool, which has potential to be adopted in clinical practice and guide treatment decisions for this high-risk patient group.
Cancer patients who suffer a heart attack face a particularly dangerous mix of risks: they are more likely to die, to bleed, or to experience another serious cardiovascular event. As a result of this, patients with cancer have historically been systematically excluded from many clinical trials and available risk scores. Doctors have had no standard tool to guide treatment in this population.
An international team of researchers has now developed the first risk prediction model designed specifically for cancer patients who have had a heart attack. The study analysed more than one million heart attack patients from England, Sweden and Switzerland, including over 47,000 with cancer. Overall, the results show that cancer patients have a strikingly poor prognosis: nearly one in three died within six months, while around one in 14 suffered a major bleed and one in six experienced another heart attack, stroke or cardiovascular death.
Called ONCO-ACS, the tool uses artificial intelligence to combine cancer-related factors with standard clinical data to predict the chances of death, major bleeding and other cardiac events across a six-month window. Although traditionally considered as separate disease entities, the findings highlight the close interplay of cancer and cardiovascular disease. Depending on the tumour characteristics, cancer patients can be at elevated risk of bleeding, of arterial blood clotting, or both - requiring different anti-platelet medication for secondary prevention after the acute event.
By accounting for both cancer and heart disease, ONCO-ACS marks a step towards truly personalised medicine. It can help doctors decide who benefits from invasive procedures and intensive drug therapy, and who may be at greater risk of harm."
Senior author Professor Thomas F. Lüscher, Adjunct Lecturer at King's and the Royal Brompton and Harefield Hospitals
Cancer patients with heart attacks have long been neglected in clinical research, despite being one of the most challenging groups we see in cardiology. This new tool gives doctors reliable information to tailor treatment and balance the benefits and harms."
First author Dr Florian A. Wenzl, from the National Health Service England and the Center for Molecular Cardiology, University of Zurich
The researchers hope the ONCO-ACS score will soon be integrated into clinical practice to support decisions on catheter-based treatment and antiplatelet therapy. ONCO-ACS provides a validated approach to implement clinical practice guidelines. The new tool can also help to design future trials aiming to improve outcomes in cancer patients who suffer a heart attack.
