Bernhard Wernly1, Behrooz Mamandipoor2, Philipp Baldia3, Christian Jung3, Venet Osmani2. 1. Department of Cardiology, Paracelsus Medical University of Salzburg, Austria; Division of Cardiology, Department of Medicine, Karolinska Institutet, Karolinska University Hospital, Stockholm, Sweden. Electronic address: bernhard@wernly.at. 2. Fondazione Bruno Kessler Research Institute, Trento, Italy. 3. University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Medical Faculty, Division of Cardiology, Pulmonology and Vascular Medicine, Germany.
Abstract
PURPOSE: To evaluate the application of machine learning methods, specifically Deep Neural Networks (DNN) models for intensive care (ICU) mortality prediction. The aim was to predict mortality within 96 hours after admission to mirror the clinical situation of patient evaluation after an ICU trial, which consists of 24-48 hours of ICU treatment and then "re-triage". The input variables were deliberately restricted to ABG values to maximise real-world practicability. METHODS: We retrospectively evaluated septic patients in the multi-centre eICU dataset as well as single centre MIMIC-III dataset. Included were all patients alive after 48 hours with available data on ABG (n = 3979 and n = 9655 ICU stays for the multi-centre and single centre respectively). The primary endpoint was 96 -h-mortality. RESULTS: The model was developed using long short-term memory (LSTM), a type of DNN designed to learn temporal dependencies between variables. Input variables were all ABG values within the first 48 hours. The SOFA score (AUC of 0.72) was moderately predictive. Logistic regression showed good performance (AUC of 0.82). The best performance was achieved by the LSTM-based model with AUC of 0.88 in the multi-centre study and AUC of 0.85 in the single centre study. CONCLUSIONS: An LSTM-based model could help physicians with the "re-triage" and the decision to restrict treatment in patients with a poor prognosis.
PURPOSE: To evaluate the application of machine learning methods, specifically Deep Neural Networks (DNN) models for intensive care (ICU) mortality prediction. The aim was to predict mortality within 96 hours after admission to mirror the clinical situation of patient evaluation after an ICU trial, which consists of 24-48 hours of ICU treatment and then "re-triage". The input variables were deliberately restricted to ABG values to maximise real-world practicability. METHODS: We retrospectively evaluated septic patients in the multi-centre eICU dataset as well as single centre MIMIC-III dataset. Included were all patients alive after 48 hours with available data on ABG (n = 3979 and n = 9655 ICU stays for the multi-centre and single centre respectively). The primary endpoint was 96 -h-mortality. RESULTS: The model was developed using long short-term memory (LSTM), a type of DNN designed to learn temporal dependencies between variables. Input variables were all ABG values within the first 48 hours. The SOFA score (AUC of 0.72) was moderately predictive. Logistic regression showed good performance (AUC of 0.82). The best performance was achieved by the LSTM-based model with AUC of 0.88 in the multi-centre study and AUC of 0.85 in the single centre study. CONCLUSIONS: An LSTM-based model could help physicians with the "re-triage" and the decision to restrict treatment in patients with a poor prognosis.
Authors: Daniel Dankl; Richard Rezar; Behrooz Mamandipoor; Zhichao Zhou; Sarah Wernly; Bernhard Wernly; Venet Osmani Journal: Med Princ Pract Date: 2022-01-28 Impact factor: 2.132
Authors: Behrooz Mamandipoor; Fernando Frutos-Vivar; Oscar Peñuelas; Richard Rezar; Konstantinos Raymondos; Alfonso Muriel; Bin Du; Arnaud W Thille; Fernando Ríos; Marco González; Lorenzo Del-Sorbo; Maria Del Carmen Marín; Bruno Valle Pinheiro; Marco Antonio Soares; Nicolas Nin; Salvatore M Maggiore; Andrew Bersten; Malte Kelm; Raphael Romano Bruno; Pravin Amin; Nahit Cakar; Gee Young Suh; Fekri Abroug; Manuel Jibaja; Dimitros Matamis; Amine Ali Zeggwagh; Yuda Sutherasan; Antonio Anzueto; Bernhard Wernly; Andrés Esteban; Christian Jung; Venet Osmani Journal: BMC Med Inform Decis Mak Date: 2021-05-07 Impact factor: 2.796
Authors: Christian Jung; Behrooz Mamandipoor; Jesper Fjølner; Raphael Romano Bruno; Bernhard Wernly; Antonio Artigas; Bernardo Bollen Pinto; Joerg C Schefold; Georg Wolff; Malte Kelm; Michael Beil; Sigal Sviri; Peter V van Heerden; Wojciech Szczeklik; Miroslaw Czuczwar; Muhammed Elhadi; Michael Joannidis; Sandra Oeyen; Tilemachos Zafeiridis; Brian Marsh; Finn H Andersen; Rui Moreno; Maurizio Cecconi; Susannah Leaver; Dylan W De Lange; Bertrand Guidet; Hans Flaatten; Venet Osmani Journal: JMIR Med Inform Date: 2022-03-31
Authors: Raphael Romano Bruno; Bernhard Wernly; Behrooz Mamandipoor; Richard Rezar; Stephan Binnebössel; Philipp Heinrich Baldia; Georg Wolff; Malte Kelm; Bertrand Guidet; Dylan W De Lange; Daniel Dankl; Andreas Koköfer; Thomas Danninger; Wojciech Szczeklik; Sviri Sigal; Peter Vernon van Heerden; Michael Beil; Jesper Fjølner; Susannah Leaver; Hans Flaatten; Venet Osmani; Christian Jung Journal: Front Med (Lausanne) Date: 2021-07-09
Authors: Thomas Danninger; Richard Rezar; Behrooz Mamandipoor; Daniel Dankl; Andreas Koköfer; Christian Jung; Bernhard Wernly; Venet Osmani Journal: Wien Klin Wochenschr Date: 2021-09-16 Impact factor: 1.704