Multiomics, virtual reality and artificial intelligence in heart failure.

Abstract

Aim: Multiomics delivers more biological insight than targeted investigations. We applied multiomics to patients with heart failure (HF) and\xa0reduced ejection fraction (HFrEF), with machine learning applied to advanced ECG (AECG) and echocardiography artificial intelligence (Echo AI). Patients & methods: In total, 46\xa0patients with HFrEF and 20 controls underwent metabolomic profiling, including liquid/gas chromatography-mass spectrometry\xa0and solid-phase microextraction\xa0volatilomics in plasma and urine. HFrEF was defined using left ventricular (LV)\xa0global longitudinal strain, EF and N-terminal pro hormone BNP. AECG and Echo AI were performed over 5\xa0min, with a subset of patients undergoing a virtual reality mental stress test. Results: A-ECG had similar diagnostic accuracy as N-terminal pro hormone BNP for HFrEF (area under the curve =\xa00.95, 95% CI: 0.85-0.99), and correlated with global longitudinal strain (r\xa0=\xa0-0.77, p\xa0<\xa00.0001), while Echo AI-generated measurements correlated well with manually measured LV\xa0end diastolic volume\xa0r\xa0=\xa00.77, LV\xa0end systolic volume r\xa0=\xa00.8, LVEF r\xa0=\xa00.71, indexed left atrium\xa0volume r\xa0=\xa00.71 and indexed LV mass r\xa0=\xa00.6, p\xa0<\xa00.005. AI-LVEF and other HFrEF biomarkers had a similar discrimination for HFrEF (area under the curve AI-LVEF =\xa00.88;\xa095% CI: -0.03 to\xa00.15;\xa0p\xa0=\xa00.19). Virtual reality mental stress test elicited arrhythmic biomarkers on AECG and indicated blunted autonomic responsiveness (alpha\xa02 of RR interval variability, p\xa0=\xa01\xa0×\xa010-4) in HFrEF. Conclusion: Multiomics-related machine learning shows promise for the assessment of HF.