Ximing Nie1,2, Yuan Cai1,2,3, Jingyi Liu1,2, Xiran Liu1,2, Jiahui Zhao1,2, Zhonghua Yang1,2, Miao Wen1,2, Liping Liu1,2. 1. Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China. 2. China National Clinical Research Center for Neurological Diseases, Beijing, China. 3. Department of Medicine and Therapeutics, Prince of Wales Hospital, Chinese University of Hong Kong, Hong Kong, China.
Abstract
Objectives: This study aims to investigate whether the machine learning algorithms could provide an optimal early mortality prediction method compared with other scoring systems for patients with cerebral hemorrhage in intensive care units in clinical practice. Methods: Between 2008 and 2012, from Intensive Care III (MIMIC-III) database, all cerebral hemorrhage patients monitored with the MetaVision system and admitted to intensive care units were enrolled in this study. The calibration, discrimination, and risk classification of predicted hospital mortality based on machine learning algorithms were assessed. The primary outcome was hospital mortality. Model performance was assessed with accuracy and receiver operating characteristic curve analysis. Results: Of 760 cerebral hemorrhage patients enrolled from MIMIC database [mean age, 68.2 years (SD, ±15.5)], 383 (50.4%) patients died in hospital, and 377 (49.6%) patients survived. The area under the receiver operating characteristic curve (AUC) of six machine learning algorithms was 0.600 (nearest neighbors), 0.617 (decision tree), 0.655 (neural net), 0.671(AdaBoost), 0.819 (random forest), and 0.725 (gcForest). The AUC was 0.423 for Acute Physiology and Chronic Health Evaluation II score. The random forest had the highest specificity and accuracy, as well as the greatest AUC, showing the best ability to predict in-hospital mortality. Conclusions: Compared with conventional scoring system and the other five machine learning algorithms in this study, random forest algorithm had better performance in predicting in-hospital mortality for cerebral hemorrhage patients in intensive care units, and thus further research should be conducted on random forest algorithm.
Objectives: This study aims to investigate whether the machine learning algorithms could provide an optimal early mortality prediction method compared with other scoring systems for patients with cerebral hemorrhage in intensive care units in clinical practice. Methods: Between 2008 and 2012, from Intensive Care III (MIMIC-III) database, all cerebral hemorrhagepatients monitored with the MetaVision system and admitted to intensive care units were enrolled in this study. The calibration, discrimination, and risk classification of predicted hospital mortality based on machine learning algorithms were assessed. The primary outcome was hospital mortality. Model performance was assessed with accuracy and receiver operating characteristic curve analysis. Results: Of 760 cerebral hemorrhagepatients enrolled from MIMIC database [mean age, 68.2 years (SD, ±15.5)], 383 (50.4%) patientsdied in hospital, and 377 (49.6%) patients survived. The area under the receiver operating characteristic curve (AUC) of six machine learning algorithms was 0.600 (nearest neighbors), 0.617 (decision tree), 0.655 (neural net), 0.671(AdaBoost), 0.819 (random forest), and 0.725 (gcForest). The AUC was 0.423 for Acute Physiology and Chronic Health Evaluation II score. The random forest had the highest specificity and accuracy, as well as the greatest AUC, showing the best ability to predict in-hospital mortality. Conclusions: Compared with conventional scoring system and the other five machine learning algorithms in this study, random forest algorithm had better performance in predicting in-hospital mortality for cerebral hemorrhagepatients in intensive care units, and thus further research should be conducted on random forest algorithm.
Authors: A Carolei; C Marini; M Di Napoli; G Di Gianfilippo; P Santalucia; M Baldassarre; G De Matteis; F di Orio Journal: Stroke Date: 1997-12 Impact factor: 7.914
Authors: Torrey Boland; Galen V Henderson; Fiona K Gibbons; H Bart Brouwers; Steven M Greenberg; Miriam Raffeld; Christina E Kourkoulis; Jonathan Rosand; Kenneth B Christopher Journal: Neurocrit Care Date: 2016-08 Impact factor: 3.210