ObjectiveCurrent Endocrine Society Clinical Practice Guidelines use a specific aldosterone/renin ratio (ARR) threshold to screen for primary aldosteronism (a treatable disease causing up to 15% of hypertension in primary care) in all patients. We sought to characterize demographic variations in the ARR, hypothesizing a need for age‐ and sex‐specific reference ranges to improve the accuracy of the test.DesignRetrospective cross‐sectional analysis of ARR measurements at a single tertiary hospital from December 2016 to June 2018.PatientsA total of 442 patients with clinically indicated ARR were included, after excluding those who were on spironolactone or the oral contraceptive pill, were pregnant or had an existing adrenal condition.MeasurementsAldosterone, renin and the ARR.ResultsAmong those aged 20‐39 years (n = 74), females had significantly higher median aldosterone (369 vs 244 pmol/L, P = .028), lower median renin (17.0 vs 27.6 mIU/L, P = .034) and higher median ARR (20.7 vs 10.3 (pmol/L)/(mIU/L), P = .001) than males, despite having lower systolic (135 vs 145 mmHg, P = .021) and diastolic (89 vs 96.5 mmHg, P = .007) blood pressure. The ≥ 60‐year age group (n = 157) also had significant sex differences in the ARR. With increasing age (20‐39 vs ≥ 60 years), there was a significant fall in plasma aldosterone in females (369 pmol/L vs 264 pmol/L, P = .005), with no change observed in males.ConclusionsFor those 20‐39 years old, aldosterone and the ARR are significantly higher in females despite a lower systolic and diastolic BP, highlighting the potential for false‐positive results. Our findings indicate the need for prospective studies with a control population to define age‐ and sex‐specific ARR reference ranges.

Artificial intelligence (AI) offers much promise for improving healthcare. However, it runs the looming risk of causing individual and societal harms; for instance, exacerbating inequalities amongst minority groups, or enabling compromises in the confidentiality of patients’ sensitive data. As such, there is an expanding, unmet need for ensuring AI for healthcare is developed in concordance with human values and ethics. Augmenting “principle-based” guidance that highlight adherence to ethical ideals (without necessarily offering translation into actionable practices), we offer a solution-based framework for operationalising ethics in AI for healthcare. Our framework is built from a scoping review of existing solutions of ethical AI guidelines, frameworks and technical solutions to address human values such as self-direction in healthcare. Our view spans the entire length of the AI lifecycle: data management, model development, deployment and monitoring. Our focus in this paper is to collate actionable solutions (whether technical or non-technical in nature), which can be steps that enable and empower developers in their daily practice to ensuring ethical practices in the broader picture. Our framework is intended to be adopted by AI developers, with recommendations that are accessible and driven by the existing literature. We endorse the recognised need for ‘ethical AI checklists’ co-designed with health AI practitioners, which could further operationalise the technical solutions we have collated. Since the risks to health and wellbeing are so large, we believe a proactive approach is necessary for ensuring human values and ethics are appropriately respected in AI for healthcare.

No abstract