How AI tackles bias in screening and reduces underdiagnosis of heart failure in black patients
New research has revealed that Black patients are less likely to be underdiagnosed with a common type of heart failure when using AI than during routine care. The study, funded by the British Heart Foundation (BHF) and King’s College London, utilised Artificial Intelligence to assess the extent of Heart Failure with Preserved Ejection Fraction (HFpEF) underdiagnosis across ethnicities, demonstrating how AI algorithms could help clinicians reduce bias and improve diagnoses.
The study was co-led by Dr. Kevin O’Gallagher, Clinician Scientist and Honorary Consultant in Interventional Cardiology, and Professor Ajay Shah, BHF Chair of Cardiology and Director of the King’s College London BHF Centre of Excellence.
They employed an AI algorithm called Natural Language Processing (NLP), which can read and interpret medical text to analyse electronic medical records. The AI tool identified nearly 1,973 patients who met the European Society of Cardiology guidelines for HFpEF diagnosis, with 64% being White, 29% Black, and 7% Asian.
The researchers compared the AI-driven diagnoses with those made through routine care and found that Black and Asian patients were more likely to be underdiagnosed in current practice. This difference may be attributed to the H2FPEF score, a diagnostic tool not used in the AI algorithm, which emphasizes conditions like atrial fibrillation—more common in White and Asian populations—over hypertension, which is more prevalent in Black patients.
Highlighting the need for improved diagnostic methods that consider ethnic differences in disease presentation, Dr. Kevin O’Gallagher said “It is vital clinicians are aware of how heart failure presents in patients of all ethnicities if we are to effectively tackle inequalities within the condition.”
“More research still needs to be done to improve diagnostic tools. It is crucial that everyone has the same chance of accessing life-enhancing treatment when they need it the most,” added Dr. O’Gallagher.
Dr Sonya Babu-Narayan, BHF’s associate medical director and a consultant cardiologist, said of the research: “Early diagnosis of HFpEF, is vital in ensuring people get the treatment they need to avoid admission to hospital and live longer lives in good health.”
“Thanks to new research, there are now evidence-based medicines for HFpEF that can save and improve lives. It more vital than ever that everyone who needs treatment gets it in time and that research studies include large, diverse patient cohorts that are representative of those that are affected by the condition.”
Find out more about the study here: https://www.sciencedirect.com/science/article/pii/S2772963X24002588?via%3Dihub