Niklas Nielsen1, Attila Frigyesi2,3, Peder Andersson4,5, Jesper Johnsson1, Ola Björnsson6,3, Tobias Cronberg7, Christian Hassager8, Henrik Zetterberg9,10,11,12, Pascal Stammet13, Johan Undén14, Jesper Kjaergaard8, Hans Friberg15, Kaj Blennow9,10, Gisela Lilja7, Matt P Wise16, Josef Dankiewicz17. 1. Department of Clinical Sciences Lund, Anesthesia and Intensive Care, Lund University, Helsingborg Hospital, Lund, Sweden. 2. Department of Clinical Sciences Lund, Anaesthesia and Intensive Care, Lund University, Skåne University Hospital, Lund, Sweden. 3. Centre for Mathematical Sciences, Mathematical Statistics, Lund University, Lund, Sweden. 4. Department of Clinical Sciences Lund, Anaesthesia and Intensive Care, Lund University, Skåne University Hospital, Lund, Sweden. peder.andersson@med.lu.se. 5. Department of Intensive and Perioperative Care, Skåne University Hospital, Getingevägen 4, 222 41, LundLund, Sweden. peder.andersson@med.lu.se. 6. Department of Energy Sciences, Faculty of Engineering, Lund University, Lund, Sweden. 7. Department of Clinical Sciences Lund, Neurology, Lund University, Skåne University Hospital, Lund, Sweden. 8. Department of Cardiology, Rigshospitalet and Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark. 9. Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, The Sahlgrenska Academy At the University of Gothenburg, Mölndal, Sweden. 10. Clinical Neurochemistry Laboratory, Sahlgrenska University Hospital, Mölndal, Sweden. 11. Department of Neurodegenerative Disease, UCL Institute of Neurology, Queen Square, London, UK. 12. UK Dementia Research Institute At UCL, London, UK. 13. Medical and Health Directorate, National Fire and Rescue Corps, 1, rue Robert Stumper, 2557, Luxembourg, Luxembourg. 14. Department of Clinical Sciences Malmö, Anaesthesia and Intensive Care, Lund University, Hallands Hospital Halmstad, Halland, Sweden. 15. Department of Clinical Sciences Lund, Anaesthesia and Intensive Care, Lund University, Skåne University Hospital, Malmö, Sweden. 16. Adult Critical Care, University Hospital of Wales, Cardiff, UK. 17. Department of Clinical Sciences Lund, Cardiology, Lund University, Skåne University Hospital, Lund, Sweden.
Abstract
BACKGROUND: Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers. METHODS: We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients' background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1-2 whilst a poor outcome was defined as CPC 3-5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets. RESULTS: AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p < 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions. CONCLUSIONS: In this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatose patients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.
BACKGROUND: Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers. METHODS: We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatosepatients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients' background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1-2 whilst a poor outcome was defined as CPC 3-5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets. RESULTS: AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p < 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions. CONCLUSIONS: In this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatosepatients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.
Authors: Timothy N Jones; Matthew Kelham; Krishnaraj S Rathod; Charles J Knight; Alastair Proudfoot; Ajay K Jain; Andrew Wragg; Muhiddin Ozkor; Paul Rees; Oliver Guttmann; Andreas Baumbach; Anthony Mathur; Daniel A Jones Journal: Am J Cardiovasc Dis Date: 2021-12-15
Authors: Gaetano Manzo; Davide Calvaresi; Oscar Jimenez-Del-Toro; Jean-Paul Calbimonte; Michael Schumacher Journal: J Med Syst Date: 2021-11-11 Impact factor: 4.460