Machine learning models to predict myocardial infarctions from past climatic and environmental conditions
Lennart Marien,Mahyar Valizadeh,Wolfgang zu Castell,Christine Nam,Diana Rechid,Alexandra Schneider,Christine Meisinger,Jakob Linseisen,Kathrin Wolf,and Laurens M. Bouwer
Lennart Marien
Climate Service Center Germany (GERICS), Helmholtz-Zentrum Hereon, Fischertwiete 1, 20095 Hamburg, Germany
Mahyar Valizadeh
Strategy and Digitalization, Helmholtz Zentrum München, German Research Center for Environmental Health, Ingolstädter Landstraße 1, 85764 Neuherberg, Germany
Climate Service Center Germany (GERICS), Helmholtz-Zentrum Hereon, Fischertwiete 1, 20095 Hamburg, Germany
Diana Rechid
Climate Service Center Germany (GERICS), Helmholtz-Zentrum Hereon, Fischertwiete 1, 20095 Hamburg, Germany
Alexandra Schneider
Institute of Epidemiology, Helmholtz Zentrum München, German Research Center for Environmental Health, Ingolstädter Landstraße 1, 85764 Neuherberg, Germany
Christine Meisinger
Chair of Epidemiology, University of Augsburg, University Hospital Augsburg, Stenglinstraße 2, 86156 Augsburg, Germany
Clinical Epidemiology, Helmholtz Zentrum München, German Research Center for Environmental Health, Ingolstädter Landstraße 1, 85754 Neuherberg, Germany
Jakob Linseisen
Chair of Epidemiology, University of Augsburg, University Hospital Augsburg, Stenglinstraße 2, 86156 Augsburg, Germany
Clinical Epidemiology, Helmholtz Zentrum München, German Research Center for Environmental Health, Ingolstädter Landstraße 1, 85754 Neuherberg, Germany
Kathrin Wolf
Institute of Epidemiology, Helmholtz Zentrum München, German Research Center for Environmental Health, Ingolstädter Landstraße 1, 85764 Neuherberg, Germany
Myocardial infarctions (MIs; heart attacks) are influenced by temperature extremes, air pollution, lack of green spaces and ageing population. Here, we apply machine learning (ML) models in order to estimate the influence of various environmental and demographic risk factors. The resulting ML models can accurately reproduce observed annual variability in MI and inter-annual trends. The models allow quantification of the importance of individual factors and can be used to project future risk.
Myocardial infarctions (MIs; heart attacks) are influenced by temperature extremes, air...
