Speakers
Graeme Eisenhofer
Plenary
Chair: Kath Hayden
Clinical decision support system-based integration of plasma steroidomics with artificial intelligence: A blending of technologies for diagnostic stratification of primary aldosteronism
Graeme Eisenhofer,1 Georgiana Constantinescu,1 Manuel Schulze,2 Mirko Peitzsch,1 Hanna Remde,3 Lydia Kürzinger,3 Sven Gruber,4 Jun Yang,5 Andrea R Horvath,6 Tracy A Williams,7 Lisa Müller,7 Martin Reincke,7 Felix Beuschlein,4 Jacques W.M. Lenders,8 Christina Pamporaki.1
1University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany; 2Center for Interdisciplinary Digital Sciences, Technische Universität Dresden, Germany; 3University Hospital, University of Würzburg, Germany; 4University Hospital Zurich, Zurich, Switzerland; 5Hudson Institute of Medical Research, Clayton, Victoria, Australia; 6New South Wales Health Pathology, Prince of Wales Hospital, Sydney, Australia; 7University Hospital, Ludwig Maximilian University Munich, Munich, Germany; 8Radboud University Medical Center, Nijmegen, the Netherlands.
With advances in clinical mass spectrometry (MS) that allow for simultaneous measurements of multiple analytes there is need for systems to facilitate interpretation of multidimensional data and conveyance to physicians in an easily digestible form. This can be achieved by a blending of laboratory and artificial intelligence (AI) technologies within a clinical decision support system (CDSS), which for laboratory medicine must satisfy not only regulatory requirements for in vitro diagnostics but also those for a CDSS as a medical device. For medical device regulation (MDR), the CDSS should not only provide valid support of clinical decisions, but should also be robust, efficient, cost-effective and safe for the designated task. In diagnostics, applications of AI usually involve supervised machine learning (ML) with algorithms for disease classification to generate mathematical models that are then applied to laboratory and other clinical data. MS-based steroidomics for diagnostic stratification of patients with primary aldosteronism is one area of laboratory medicine for which we have blended the various technologies within a CDSS to convey steroidomic data and ML model-derived interpretations to physicians. The CDSS has been applied in a prospective multicenter study (PROSALDO) of over 800 patients with hypertension recruited to validate previously established ML models developed for screening purposes and stratification of patients for therapeutic intervention. To satisfy MDR requirements, robustness of the CDSS has been tested by reproducibility of generated steroid probability scores within and between different laboratories. Effectiveness and efficiency of the CDSS has been established from steroid probability scores that for screening purposes compare favourably with conventional use of the aldosterone:renin ratio, but more importantly enable identification of a subset of patients as candidates for adrenalectomy. Such patients, with imaging evidence of a unilateral mass, may thereby escape need for confirmatory tests as well as expensive and invasive adrenal venous sampling studies. Minimized need for withdrawal of antihypertensive medications further supports MDR requirements for cost-effectiveness, efficiency and safety of the CDSS.
Graeme Eisenhofer received his PhD in 1983 from the University of Otago, New Zealand, with clinical research on autonomic and neuroendocrine systems. He then moved to the NIH where he carried out basic and clinical studies mapping the pathways of catecholamine metabolism. In 1988 he moved to the Baker Heart Research Institute (Melbourne, Australia), where he worked on sympathetic nervous system function in health and disease. He returned to the NIH in 1991 before taking up a Professorship at the University Hospital in Dresden. Together with Dr. Jacques Lenders, Dr. Eisenhofer developed measurements of plasma metanephrines for laboratory diagnosis of phaeochromocytoma. He was also responsible for the first ever synthesis of 18F-fluorodopamine as a PET imaging agent for localising catecholamine-producing tumours. At Dresden, Dr. Eisenhofer leads laboratory and clinical research groups with a focus on adrenal disorders and endocrine hypertension. The work has most recently centred on applications of mass spectrometry-based measurements of steroids and catecholamine metabolites. For this, approaches are being developed that integrate multidimensional diagnostics with artificial intelligence to build clinical decision support systems for efficient and appropriate therapeutic interventions.
Kath Hayden is a Consultant Clinical Biochemist at Manchester University NHS Foundation Trust and Honorary Senior Lecturer at the University of Manchester.
Following training in South Manchester, Kath has held posts in hospitals in Manchester and Liverpool over a 35 year period, overseeing significant advances in analytical technologies, point of care testing (POCT) and harmonisation of laboratories. With specialist interests in endocrinology, POCT, leadership and service improvement, her latest roles have been as Clinical Head of Division for Laboratory Medicine at Manchester University NHS Foundation Trust, Trust Lead Healthcare Scientist, Clinical Director for Laboratory Medicine and Head of Service for Clinical Biochemistry at Central Manchester University Hospitals NHS Foundation Trust.