Artificial intelligence methods for improved detection of undiagnosed heart failure with preserved ejection fraction.

AIM: Heart failure with preserved ejection fraction (HFpEF) remains under-diagnosed in clinical practice despite accounting for nearly half of all heart failure (HF) cases. Accurate and timely diagnosis of HFpEF is crucial for proper patient management and treatment. In this study, we explored the potential of natural language processing (NLP) to improve the detection and diagnosis of HFpEF according to the European Society of Cardiology (ESC) diagnostic criteria. METHODS AND RESULTS: In a retrospective cohort study, we used an NLP pipeline applied to the electronic health record (EHR) to identify patients with a clinical diagnosis of HF between 2010 and 2022. We collected demographic, clinical, echocardiographic and outcome data from the EHR. Patients were categorized according to the left ventricular ejection fraction (LVEF). Those with LVEF ≥50% were further categorized based on whether they had a clinician-assigned diagnosis of HFpEF and if not, whether they met the ESC diagnostic criteria. Results were validated in a second, independent centre. We identified 8606 patients with HF. Of 3727 consecutive patients with HF and LVEF ≥50% on echocardiogram, only 8.3% had a clinician-assigned diagnosis of HFpEF, while 75.4% met ESC criteria but did not have a formal diagnosis of HFpEF. Patients with confirmed HFpEF were hospitalized more frequently; however the ESC criteria group had a higher 5-year mortality, despite being less comorbid and experiencing fewer acute cardiovascular events. CONCLUSIONS: This study demonstrates that patients with undiagnosed HFpEF are an at-risk group with high mortality. It is possible to use NLP methods to identify likely HFpEF patients from EHR data who would likely then benefit from expert clinical review and complement the use of diagnostic algorithms.

QT prolongation and torsades de pointes in a patient with heart block and a pacemaker.

Prolongation of the QT interval and development of torsades de pointes are known in patients with complete heart block and profound bradycardia. We report the case of a patient with complete heart block and torsades, with long QT seen during a period of junctional tachycardia at a rate faster than the minimum pacemaker rate.

Developmental Expression and Glucocorticoid Control of the Leptin Receptor in Fetal Ovine Lung.

The effects of endogenous and synthetic glucocorticoids on fetal lung maturation are well-established, although the role of leptin in lung development before birth is unclear. This study examined mRNA and protein levels of the signalling long-form leptin receptor (Ob-Rb) in fetal ovine lungs towards term, and after experimental manipulation of glucocorticoid levels in utero by fetal cortisol infusion or maternal dexamethasone treatment. In fetal ovine lungs, Ob-Rb protein was localised to bronchiolar epithelium, bronchial cartilage, vascular endothelium, alveolar macrophages and type II pneumocytes. Pulmonary Ob-Rb mRNA abundance increased between 100 (0.69 fractional gestational age) and 144 days (0.99) of gestation, and by 2-4-fold in response to fetal cortisol infusion and maternal dexamethasone treatment. In contrast, pulmonary Ob-Rb protein levels decreased near term and were halved by glucocorticoid treatment, without any significant change in phosphorylated signal transducer and activator of transcription-3 (pSTAT3) at Ser727, total STAT3 or the pulmonary pSTAT3:STAT3 ratio. Leptin mRNA was undetectable in fetal ovine lungs at the gestational ages studied. These findings demonstrate differential control of pulmonary Ob-Rb transcript abundance and protein translation, and/or post-translational processing, by glucocorticoids in utero. Localisation of Ob-Rb in the fetal ovine lungs, including alveolar type II pneumocytes, suggests a role for leptin signalling in the control of lung growth and maturation before birth.