Outcome prediction of out-of-hospital cardiac arrest with presumed cardiac aetiology using an advanced machine learning technique

Introduction and Objective: Early prognostication for cardiogenic out-of-hospital cardiac arrest (OHCA) patients remain challenging. Recently, advanced machine learning techniques have been employed for clinical diagnosis and prognostication for various conditions. Therefore, in this study, we attempted to establish a prognostication model for cardiogenic OHCA using an advanced machine learning technique. Methods and Results: Data of a prospective multi-center cohort study of OHCA patients transported by an ambulance to 67 medical institutions in Kanto area of Japan between January 2012 and March 2013 was used in this study. Data for cardiogenic OHCA patients aged ≥18 years were retrieved and patients were grouped according to the time of calls for ambulances (training set: between January 1, 2012 and December 12, 2012; test set: between January 1, 2013 and March 31, 2013). From among 421 variables observed during the period between calls for ambulances and initial in-hospital treatments of cardiogenic OHCA, 38 prehospital factors or 56 prehospital factors and initial in-hospital factors were used for prognostication, respectively. Prognostication models for 1-year survival were established with random forest method, an advanced machine learning method that aggregates a series of decision trees for classification and regression. After 10-fold internal cross validation in the training set, prognostication models were validated using test set. Area under the receiver operating characteristics curve (AUC) was used to evaluate the prediction performance of models. Prognostication models trained with 38 variables or 56 variables for 1-year survival showed AUC values of 0.93±0.01 and 0.95±0.01, respectively. Conclusions: Prognostication models trained with advanced machine learning technique showed favorable prediction capability for 1-year survival of cardiogenic OHCA. These results indicate that an advanced machine learning technique can be applicable to establish early prognostication model for cardiogenic OHCA.

Download Full-text

Predictive model of cardiac arrest in smokers using machine learning technique based on Heart Rate Variability parameter

Applied Computing and Informatics ◽

10.1016/j.aci.2019.06.002 ◽

2020 ◽

Vol ahead-of-print (ahead-of-print) ◽

Cited By ~ 5

Author(s):

R. Shashikant ◽

P. Chetankumar

Keyword(s):

Machine Learning ◽

Heart Rate ◽

Heart Rate Variability ◽

Logistic Regression ◽

Cardiac Arrest ◽

Random Forest ◽

Decision Tree ◽

Machine Learning Technique ◽

Forest Model ◽

Learning Technique

Cardiac arrest is a severe heart anomaly that results in billions of annual casualties. Smoking is a specific hazard factor for cardiovascular pathology, including coronary heart disease, but data on smoking and heart death not earlier reviewed. The Heart Rate Variability (HRV) parameters used to predict cardiac arrest in smokers using machine learning technique in this paper. Machine learning is a method of computing experience based on automatic learning and enhances performances to increase prognosis. This study intends to compare the performance of logistical regression, decision tree, and random forest model to predict cardiac arrest in smokers. In this paper, a machine learning technique implemented on the dataset received from the data science research group MITU Skillogies Pune, India. To know the patient has a chance of cardiac arrest or not, developed three predictive models as 19 input feature of HRV indices and two output classes. These model evaluated based on their accuracy, precision, sensitivity, specificity, F1 score, and Area under the curve (AUC). The model of logistic regression has achieved an accuracy of 88.50%, precision of 83.11%, the sensitivity of 91.79%, the specificity of 86.03%, F1 score of 0.87, and AUC of 0.88. The decision tree model has arrived with an accuracy of 92.59%, precision of 97.29%, the sensitivity of 90.11%, the specificity of 97.38%, F1 score of 0.93, and AUC of 0.94. The model of the random forest has achieved an accuracy of 93.61%, precision of 94.59%, the sensitivity of 92.11%, the specificity of 95.03%, F1 score of 0.93 and AUC of 0.95. The random forest model achieved the best accuracy classification, followed by the decision tree, and logistic regression shows the lowest classification accuracy.

Download Full-text

Abstract 27: Machine Learning Models for Outcome Prediction of Out-Of-Hospital Cardiac Arrest of Presumed Cardiac Cause Using the All-Japan Utstein Registry

Circulation ◽

10.1161/circ.140.suppl_2.27 ◽

2019 ◽

Vol 140 (Suppl_2) ◽

Author(s):

Tomohisa Seki ◽

Tomoyoshi Tamura ◽

Kazuhiko Ohe ◽

Masaru Suzuki

Keyword(s):

Neural Network ◽

Machine Learning ◽

Logistic Regression ◽

Cardiac Arrest ◽

Deep Neural Network ◽

Outcome Prediction ◽

Machine Learning Techniques ◽

Test Set ◽

Learning Techniques ◽

Hospital Cardiac Arrest

Background: Outcome prediction for patients with out-of-hospital cardiac arrest (OHCA) using prehospital information has been one of the major challenges in resuscitation medicine. Recently, machine learning techniques have been shown to be highly effective in predicting outcomes using clinical registries. In this study, we aimed to establish a prediction model for outcomes of OHCA of presumed cardiac cause using machine learning techniques. Methods: We analyzed data from the All-Japan Utstein Registry of the Fire and Disaster Management Agency between 2005 and 2016. Of 1,423,338 cases, data of OHCA patients aged ≥18 years with presumed cardiac etiology were retrieved and divided into two groups: training set, n = 584,748 (between 2005 and 2013) and test set, n = 223,314 (between 2014 and 2016). The endpoints were neurologic outcome at 1-month and survival at 1-month. Of 47 variables evaluated during the prehospital course, 19 variables (e.g.,sex, age, ECG waveform, and practice of bystander CPR) were used for outcome prediction. Performances of logistic regression, random forests, and deep neural network were examined in this study. Results: For prediction of neurologic outcomes (cerebral performance category 1 or 2) using the test set, the generated models showed area under the receiver operating characteristic curve (AUROC) values of 0.942 (95% confidence interval [CI] 0.941-0.943), 0.947 (95% CI 0.946-0.948), and 0.948 (95% CI 0.948-0.950) in logistic regression, random forest, and deep neural network, respectively. For survival prediction, the generated models showed AUROC values of 0.901 (95% CI 0.900-0.902), 0.913 (95% CI 0.912-0.914), and 0.912 (95% CI 0.911-0.913) in logistic regression, random forest, and deep neural network, respectively. Conclusions: Machine learning techniques using prehospital variables showed favorable prediction capability for 1-month neurologic outcome and survival in OHCA of presumed cardiac cause.

Download Full-text

Early outcome prediction for out-of-hospital cardiac arrest with initial shockable rhythm using machine learning models

Resuscitation ◽

10.1016/j.resuscitation.2020.11.020 ◽

2021 ◽

Vol 158 ◽

pp. 49-56

Author(s):

Yohei Hirano ◽

Yutaka Kondo ◽

Koichiro Sueyoshi ◽

Ken Okamoto ◽

Hiroshi Tanaka

Keyword(s):

Machine Learning ◽

Cardiac Arrest ◽

Outcome Prediction ◽

Learning Models ◽

Early Outcome ◽

Shockable Rhythm ◽

Hospital Cardiac Arrest ◽

Machine Learning Models

Download Full-text

Machine Learning Models for Survival and Neurological Outcome Prediction of Out-of-Hospital Cardiac Arrest Patients

BioMed Research International ◽

10.1155/2021/9590131 ◽

2021 ◽

Vol 2021 ◽

pp. 1-8

Author(s):

Chi-Yung Cheng ◽

I-Min Chiu ◽

Wun-Huei Zeng ◽

Chih-Min Tsai ◽

Chun-Hung Richard Lin

Keyword(s):

Machine Learning ◽

Cardiac Arrest ◽

Neurological Outcome ◽

Outcome Prediction ◽

Neurologic Outcome ◽

Receiver Operating Curve ◽

Secondary Outcome ◽

Support Vector ◽

Extreme Gradient Boosting ◽

Hospital Cardiac Arrest

Background. Out-of-hospital cardiac arrest (OHCA) is a major health problem worldwide, and neurologic injury remains the leading cause of morbidity and mortality among survivors of OHCA. The purpose of this study was to investigate whether a machine learning algorithm could detect complex dependencies between clinical variables in emergency departments in OHCA survivors and perform reliable predictions of favorable neurologic outcomes. Methods. This study included adults (≥18 years of age) with a sustained return of spontaneous circulation after successful resuscitation from OHCA between 1 January 2004 and 31 December 2014. We applied three machine learning algorithms, including logistic regression (LR), support vector machine (SVM), and extreme gradient boosting (XGB). The primary outcome was a favorable neurological outcome at hospital discharge, defined as a Glasgow-Pittsburgh cerebral performance category of 1 to 2. The secondary outcome was a 30-day survival rate and survival-to-discharge rate. Results. The final analysis included 1071 participants from the study period. For neurologic outcome prediction, the area under the receiver operating curve (AUC) was 0.819, 0.771, and 0.956 in LR, SVM, and XGB, respectively. The sensitivity and specificity were 0.875 and 0.751 in LR, 0.687 and 0.793 in SVM, and 0.875 and 0.904 in XGB. The AUC was 0.766 and 0.732 in LR, 0.749 and 0.725 in SVM, and 0.866 and 0.831 in XGB, for survival-to-discharge and 30-day survival, respectively. Conclusions. Prognostic models trained with ML technique showed appropriate calibration and high discrimination for survival and neurologic outcome of OHCA without using prehospital data, with XGB exhibiting the best performance.

Download Full-text

Outcome prediction in out-of-hospital cardiac arrest patients using near-infrared spectroscopy

10.26226/morressier.57108e31d462b80290b4abba ◽

2016 ◽

Author(s):

Eleni Van Dessel

Keyword(s):

Cardiac Arrest ◽

Infrared Spectroscopy ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Outcome Prediction ◽

Hospital Cardiac Arrest

Download Full-text

What Should Investors Care About? Mutual Fund Ratings by Analysts vs. Machine Learning Technique

SSRN Electronic Journal ◽

10.2139/ssrn.3702749 ◽

2020 ◽

Author(s):

Si Cheng ◽

Ruichang Lu ◽

Xiaojun Zhang

Keyword(s):

Machine Learning ◽

Mutual Fund ◽

Machine Learning Technique ◽

Learning Technique

Download Full-text

The Development of a Quantitative Precipitation Forecast Correction Technique Based on Machine Learning for Hydrological Applications

Atmosphere ◽

10.3390/atmos11010111 ◽

2020 ◽

Vol 11 (1) ◽

pp. 111 ◽

Cited By ~ 2

Author(s):

Chul-Min Ko ◽

Yeong Yun Jeong ◽

Young-Mi Lee ◽

Byung-Sik Kim

Keyword(s):

Machine Learning ◽

Heavy Rainfall ◽

Extreme Rainfall ◽

Machine Learning Techniques ◽

Precipitation Forecast ◽

Machine Learning Technique ◽

Rainfall Forecast ◽

Quantitative Precipitation Forecast ◽

Correction Technique ◽

Learning Technique

This study aimed to enhance the accuracy of extreme rainfall forecast, using a machine learning technique for forecasting hydrological impact. In this study, machine learning with XGBoost technique was applied for correcting the quantitative precipitation forecast (QPF) provided by the Korea Meteorological Administration (KMA) to develop a hydrological quantitative precipitation forecast (HQPF) for flood inundation modeling. The performance of machine learning techniques for HQPF production was evaluated with a focus on two cases: one for heavy rainfall events in Seoul and the other for heavy rainfall accompanied by Typhoon Kong-rey (1825). This study calculated the well-known statistical metrics to compare the error derived from QPF-based rainfall and HQPF-based rainfall against the observational data from the four sites. For the heavy rainfall case in Seoul, the mean absolute errors (MAE) of the four sites, i.e., Nowon, Jungnang, Dobong, and Gangnam, were 18.6 mm/3 h, 19.4 mm/3 h, 48.7 mm/3 h, and 19.1 mm/3 h for QPF and 13.6 mm/3 h, 14.2 mm/3 h, 33.3 mm/3 h, and 12.0 mm/3 h for HQPF, respectively. These results clearly indicate that the machine learning technique is able to improve the forecasting performance for localized rainfall. In addition, the HQPF-based rainfall shows better performance in capturing the peak rainfall amount and spatial pattern. Therefore, it is considered that the HQPF can be helpful to improve the accuracy of intense rainfall forecast, which is subsequently beneficial for forecasting floods and their hydrological impacts.

Download Full-text