Matthieu Scherpf1, Felix Gräßer2, Hagen Malberg2, Sebastian Zaunseder3. 1. Institute of Biomedical Engineering, TU Dresden, Germany. Electronic address: Matthieu.Scherpf@tu-dresden.de. 2. Institute of Biomedical Engineering, TU Dresden, Germany. 3. Faculty of Information Technology, FH Dortmund, Germany.
Abstract
OBJECTIVE: Predicting sepsis onset with a recurrent neural network and performance comparison with InSight - a previously proposed algorithm for the prediction of sepsis onset. METHODOLOGY: A retrospective analysis of adult patients admitted to the intensive care unit (from the MIMIC III database) who did not fall under the definition of sepsis at the time of admission. The area under the receiver operating characteristic (AUROC) measures the performance of the prediction task. We examine the sequence length given to the machine learning algorithms for different points in time before sepsis onset concerning the prediction performance. Additionally, the impact of sepsis onset's definition is investigated. We evaluate the model with a relatively large and thus more representative patient population compared to related works in the field. RESULTS: For a prediction 3 h prior to sepsis onset, our network achieves an AUROC of 0.81 (95% CI: 0.78-0.84). The InSight algorithm achieves an AUROC of 0.72 (95% CI: 0.69-0.75). For a fixed sensitivity of 90% our network reaches a specificity of 47.0% (95% CI: 43.1%-50.8%) compared to 31.1% (95% CI: 24.8%-37.5%) for InSight. In addition, we compare the performance for 6 and 12 h prediction time for both approaches. CONCLUSION: Our findings demonstrate that a recurrent neural network is superior to InSight considering the prediction performance. Most probably, the improvement results from the network's ability of revealing time dependencies. We show that the length of the look back has a significant impact on the performance of the classifier. We also demonstrate that for the correct detection of sepsis onset for a retrospective analysis, further research is necessary.
OBJECTIVE: Predicting sepsis onset with a recurrent neural network and performance comparison with InSight - a previously proposed algorithm for the prediction of sepsis onset. METHODOLOGY: A retrospective analysis of adult patients admitted to the intensive care unit (from the MIMIC III database) who did not fall under the definition of sepsis at the time of admission. The area under the receiver operating characteristic (AUROC) measures the performance of the prediction task. We examine the sequence length given to the machine learning algorithms for different points in time before sepsis onset concerning the prediction performance. Additionally, the impact of sepsis onset's definition is investigated. We evaluate the model with a relatively large and thus more representative patient population compared to related works in the field. RESULTS: For a prediction 3 h prior to sepsis onset, our network achieves an AUROC of 0.81 (95% CI: 0.78-0.84). The InSight algorithm achieves an AUROC of 0.72 (95% CI: 0.69-0.75). For a fixed sensitivity of 90% our network reaches a specificity of 47.0% (95% CI: 43.1%-50.8%) compared to 31.1% (95% CI: 24.8%-37.5%) for InSight. In addition, we compare the performance for 6 and 12 h prediction time for both approaches. CONCLUSION: Our findings demonstrate that a recurrent neural network is superior to InSight considering the prediction performance. Most probably, the improvement results from the network's ability of revealing time dependencies. We show that the length of the look back has a significant impact on the performance of the classifier. We also demonstrate that for the correct detection of sepsis onset for a retrospective analysis, further research is necessary.
Authors: Daniele Roberto Giacobbe; Alessio Signori; Filippo Del Puente; Sara Mora; Luca Carmisciano; Federica Briano; Antonio Vena; Lorenzo Ball; Chiara Robba; Paolo Pelosi; Mauro Giacomini; Matteo Bassetti Journal: Front Med (Lausanne) Date: 2021-02-12
Authors: Christian Gosset; Jacques Foguenne; Mickaël Simul; Olivier Tomsin; Hayet Ammar; Nathalie Layios; Paul B Massion; Pierre Damas; André Gothot Journal: Sci Rep Date: 2021-10-13 Impact factor: 4.379
Authors: Lucas M Fleuren; Thomas L T Klausch; Charlotte L Zwager; Linda J Schoonmade; Tingjie Guo; Luca F Roggeveen; Eleonora L Swart; Armand R J Girbes; Patrick Thoral; Ari Ercole; Mark Hoogendoorn; Paul W G Elbers Journal: Intensive Care Med Date: 2020-01-21 Impact factor: 17.440