biostudies-literaturevon Bachmann PAnders WiklöfEuropean Research CouncilUppsala UniversityWallenberg AI, Autonomous Systems and Software Program (WASP) funded by Knut and Alice Wallenberg FoundationSwedish Research CouncilThe Kjell and Marta Beijer Foundation15273https://www.ebi.ac.uk/biostudies/studies/S-EPMC11222546biostudies-literatureUnknown14(1)Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binarScientific reportsEvaluating regression and probabilistic methods for ECG-based electrolyte prediction.PMC11222546no. 2018-05973.n° 101054643Gedon DSchon TBGustafsson Svon Bachmann PLampa EGustafsson FKSundstrom JRibeiro AHfalseEvaluating regression and probabilistic methods for ECG-based electrolyte prediction.Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binar2024-01-01T00:00:00Z2024 Jul2025-04-04T12:54:11.04Z2025-04-04T12:54:11.04ZS-EPMC112225463896110910.1038/s41598-024-65223-w