Machine Learning Methods for Predicting Long-term Mortality in Patients after Cardiac Surgery

2021 ◽  
Author(s):  
Yue Yu ◽  
Chi Peng ◽  
Zhiyuan Zhang ◽  
Kejia Shen ◽  
Yufeng Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiac Surgery ◽  
Early Warning Systems ◽  
Gradient Boosting ◽  
Distribution Width ◽  
Extreme Gradient Boosting ◽  
Mimic Iii ◽  
Long Term Mortality

Abstract Background Establishing a mortality prediction model of patients undergoing cardiac surgery might be useful for clinicians for alerting, judgment, and intervention, while few predictive tools for long-term mortality have been developed targeting patients post-cardiac surgery. Objective We aimed to construct and validate several machine learning (ML) algorithms to predict long-term mortality and identify risk factors in unselected patients after cardiac surgery during a 4-year follow-up. Methods The Medical Information Mart for Intensive Care (MIMIC-III) database was used to perform a retrospective administrative database study. Candidate predictors consisted of the demographics, comorbidity, vital signs, laboratory test results, prognostic scoring systems, and treatment information on the first day of ICU admission. 4-year mortality was set as the study outcome. We used the ML methods of logistic regression (LR), artificial neural network (NNET), naïve bayes (NB), gradient boosting machine (GBM), adapting boosting (Ada), random forest (RF), bagged trees (BT), and eXtreme Gradient Boosting (XGB). The prognostic capacity and clinical utility of these ML models were compared using the area under the receiver operating characteristic curves (AUC), calibration curves, and decision curve analysis (DCA). Results Of 7,368 patients in MIMIC-III included in the final cohort, a total of 1,337 (18.15%) patients died during a 4-year follow-up. Among 65 variables extracted from the database, a total of 25 predictors were selected using recursive feature elimination (RFE) and included in the subsequent analysis. The Ada model performed best among eight models in both discriminatory ability with the highest AUC of 0.801 and goodness of fit (visualized by calibration curve). Moreover, the DCA shows that the net benefit of the RF, Ada, and BT models surpassed that of other ML models for almost all threshold probability values. Additionally, through the Ada technique, we determined that red blood cell distribution width (RDW), blood urea nitrogen (BUN), SAPS II, anion gap (AG), age, urine output, chloride, creatinine, congestive heart failure, and SOFA were the Top 10 predictors in the feature importance rankings. Conclusions The Ada model performs best in predicting long-term mortality after cardiac surgery among the eight ML models. The ML-based algorithms might have significant application in the development of early warning systems for patients following operations.

scholarly journals A Medium and Long-Term Runoff Forecast Method Based on Massive Meteorological Data and Machine Learning Algorithms

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1308
Author(s):  
Yujie Li ◽  
Dong Wang ◽  
Jing Wei ◽  
Bo Li ◽  
Bin Xu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lead Time ◽  
Machine Learning Algorithms ◽  
Classification And Regression Tree ◽  
Gradient Boosting ◽  
Forecast Performance ◽  
Forecast Lead Time ◽  
Extreme Gradient Boosting ◽  
Runoff Forecast

Accurate and reliable predictors selection and model construction are the key to medium and long-term runoff forecast. In this study, 130 climate indexes are utilized as the primary forecast factors. Partial Mutual Information (PMI), Recursive Feature Elimination (RFE) and Classification and Regression Tree (CART) are respectively employed as the typical algorithms of Filter, Wrapper and Embedded based on Feature Selection (FS) to obtain three final forecast schemes. Random Forest (RF) and Extreme Gradient Boosting (XGB) are respectively constructed as the representative models of Bagging and Boosting based on Ensemble Learning (EL) to realize the forecast of the three types of forecast lead time which contains monthly, seasonal and annual runoff sequences of the Three Gorges Reservoir in the Yangtze River Basin. This study aims to summarize and compare the applicability and accuracy of different FS methods and EL models in medium and long-term runoff forecast. The results show the following: (1) RFE method shows the best forecast performance in all different models and different forecast lead time. (2) RF and XGB models are suitable for medium and long-term runoff forecast but XGB presents the better forecast skills both in calibration and validation. (3) With the increase of the runoff magnitudes, the accuracy and reliability of forecast are improved. However, it is still difficult to establish accurate and reliable forecasts only large-scale climate indexes used. We conclude that the theoretical framework based on Machine Learning could be useful to water managers who focus on medium and long-term runoff forecast.

scholarly journals Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

2021 ◽  
Vol 10 (6) ◽  
pp. 1286
Author(s):  
Vida Abedi ◽  
Venkatesh Avula ◽  
Durgesh Chaudhary ◽  
Shima Shahjouei ◽  
Ayesha Khan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Performance Metrics ◽  
Gradient Boosting ◽  
Stroke Recurrence ◽  
Support Vector ◽  
Sampling Strategies ◽  
Specificity And Sensitivity ◽  
Extreme Gradient Boosting

Background: The long-term risk of recurrent ischemic stroke, estimated to be between 17% and 30%, cannot be reliably assessed at an individual level. Our goal was to study whether machine-learning can be trained to predict stroke recurrence and identify key clinical variables and assess whether performance metrics can be optimized. Methods: We used patient-level data from electronic health records, six interpretable algorithms (Logistic Regression, Extreme Gradient Boosting, Gradient Boosting Machine, Random Forest, Support Vector Machine, Decision Tree), four feature selection strategies, five prediction windows, and two sampling strategies to develop 288 models for up to 5-year stroke recurrence prediction. We further identified important clinical features and different optimization strategies. Results: We included 2091 ischemic stroke patients. Model area under the receiver operating characteristic (AUROC) curve was stable for prediction windows of 1, 2, 3, 4, and 5 years, with the highest score for the 1-year (0.79) and the lowest score for the 5-year prediction window (0.69). A total of 21 (7%) models reached an AUROC above 0.73 while 110 (38%) models reached an AUROC greater than 0.7. Among the 53 features analyzed, age, body mass index, and laboratory-based features (such as high-density lipoprotein, hemoglobin A1c, and creatinine) had the highest overall importance scores. The balance between specificity and sensitivity improved through sampling strategies. Conclusion: All of the selected six algorithms could be trained to predict the long-term stroke recurrence and laboratory-based variables were highly associated with stroke recurrence. The latter could be targeted for personalized interventions. Model performance metrics could be optimized, and models can be implemented in the same healthcare system as intelligent decision support for targeted intervention.

scholarly journals Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Woojoo Lee ◽  
Joongyub Lee ◽  
Seoung-Il Woo ◽  
Seong Huan Choi ◽  
Jang-Whan Bae ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Support Vector ◽  
St Segment Elevation ◽  
Segment Elevation Myocardial Infarction ◽  
St Segment ◽  
Extreme Gradient Boosting ◽  
Short And Long Term ◽  
Long Term Mortality

AbstractMachine learning (ML) has been suggested to improve the performance of prediction models. Nevertheless, research on predicting the risk in patients with acute myocardial infarction (AMI) has been limited and showed inconsistency in the performance of ML models versus traditional models (TMs). This study developed ML-based models (logistic regression with regularization, random forest, support vector machine, and extreme gradient boosting) and compared their performance in predicting the short- and long-term mortality of patients with AMI with those of TMs with comparable predictors. The endpoints were the in-hospital mortality of 14,183 participants and the three- and 12-month mortality in patients who survived at discharge. The performance of the ML models in predicting the mortality of patients with an ST-segment elevation myocardial infarction (STEMI) was comparable to the TMs. In contrast, the areas under the curves (AUC) of the ML models for non-STEMI (NSTEMI) in predicting the in-hospital, 3-month, and 12-month mortality were 0.889, 0.849, and 0.860, respectively, which were superior to the TMs, which had corresponding AUCs of 0.873, 0.795, and 0.808. Overall, the performance of the predictive model could be improved, particularly for long-term mortality in NSTEMI, from the ML algorithm rather than using more clinical predictors.

A Comparative Study of Machine Learning Techniques for Predicting Sepsis for MIMIC-III Patients

2021 ◽  
Author(s):  
Xuze Zhao ◽  
Bo Qu
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Intensive Care Units ◽  
Medical Information ◽  
Machine Learning Techniques ◽  
Gradient Boosting ◽  
Support Vector ◽  
Mortality And Morbidity ◽  
Extreme Gradient Boosting ◽  
Mimic Iii

Abstract Background: Sepsis is one of the dominating causes of mortality and morbidity in-hospital especially in intensive care units (ICU) patients. Therefore, a reliable decision-making model for predicting sepsis is of great importance. The purpose of this study was to develop an eXtreme Gradient Boosting (XGBoost) based model and explore whether it performs better in predicting sepsis from the time of admission in intensive care units (ICU) than other machine learning (ML) methods. Methods: The source data used for model establishment in this study were from a retrospective medical information mart for intensive care (MIMIC) III dataset, restricted to intensive care units (ICUs) patients aged between 18 and 89. Model performance of the XGBoost model was compared to logistic regression (LR), recursive neural network (RNN), and support vector machine (SVM). Then, the performances of the models were evaluated and compared by the area under the curve (AUC) of the receiver operating characteristic (ROC) curves.Results: A total of 6430 MIMIC-III cases are included in this article, in which, 3021 cases have encountered sepsis while 3409 cases have not, respectively. As for the AUC (0.808 (95% CI): 0.767-0.848,DT), 0.802 (95%CI: 0.762-0.842，RNN), 0.790 (95%CI: 0.751-0.830,SVM), 0.775 (95%CI: 0.736-0.813,LR) , results of the models, XGBoost performs best in predicting sepsis.Conclusions: By using the DT algorithm, a more accurate prediction model can be established. Amongst other ML methods, the XGBoost model demonstrated the best ability in detecting the sepsis of the patients in ICU.

P2877The incidence, predictors, and long-term outcomes of new-onset ventricular tachycardia after cardiac surgery

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
K.-J Choi ◽  
M S Cho ◽  
U Do ◽  
J Kim ◽  
G B Nam ◽  
...  
Keyword(s):  
Cardiac Surgery ◽  
Ventricular Tachycardia ◽  
Hospital Mortality ◽  
Index Hospitalization ◽  
Long Term Outcomes ◽  
Short And Long Term ◽  
Long Term Mortality ◽  
New Onset

Abstract Background Incidence and outcomes of new-onset ventricular tachycardia (VT) after cardiac surgery are not fully evaluated. Purpose We retrospectively analyzed the occurrence of new-onset VTs after cardiac surgery, and their implications on short and long-term mortality. Methods Data of 11,004 adult patients who underwent cardiac surgery at our center from 2006 to 2016 were analyzed. VT was diagnosed when 3 or more consecutive wide QRS complexes (>100 bpm) were documented on ECG. The major study outcomes were in-hospital and 5-years overall mortality rates. Results During index hospitalization for cardiac surgery, clinical VTs were documented in 184 patients (1.7%), which included 74 sustained VTs (SusVT, ≥30 seconds) and 110 non-sustained VTs (NSVT). Those patients with SusVT and NSVT showed higher in-hospital mortality compared to those without VTs (31.1% vs. 24.5% vs. 2.0% for SusVT, NSVT, and no VT, respectively, P<0.001). During follow-up after discharge from index hospitalization, patients with SusVT showed higher 5-years mortality than those without VTs, while patients with NSVT did not showed significant differences (22.0% vs. 11.7% vs. 9.2%, P<0.001). In the subgroup of patients with sustained VT who were discharged from index hospitalization (n=51), those with recurrent VTs (>24 hours apart from initial episode) were at higher 5-years mortality rate compared to those without (40.7% vs. 15.8%, P=0.018). Conclusion Patients with SusVT and NSVT were at higher risk of in-hospital mortality, and patients with SusVT were associated with higher risk of long-term mortality. The mortality risk was even higher in those with recurrent episodes of VTs. Acknowledgement/Funding None

Predicting Undesired Treatment Outcome in Mental Healthcare: Machine Learning Study (Preprint)

2019 ◽  
Author(s):  
Kasper Van Mens ◽  
Joran Lokkerbol ◽  
Richard Janssen ◽  
Robert de Lange ◽  
Bea Tiemens
Keyword(s):  
Machine Learning ◽  
Treatment Outcome ◽  
Mental Health Treatment ◽  
Mental Healthcare ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Trade Off ◽  
Trade Offs ◽  
Outcome Monitoring ◽  
Extreme Gradient Boosting

BACKGROUND It remains a challenge to predict which treatment will work for which patient in mental healthcare. OBJECTIVE In this study we compare machine algorithms to predict during treatment which patients will not benefit from brief mental health treatment and present trade-offs that must be considered before an algorithm can be used in clinical practice. METHODS Using an anonymized dataset containing routine outcome monitoring data from a mental healthcare organization in the Netherlands (n = 2,655), we applied three machine learning algorithms to predict treatment outcome. The algorithms were internally validated with cross-validation on a training sample (n = 1,860) and externally validated on an unseen test sample (n = 795). RESULTS The performance of the three algorithms did not significantly differ on the test set. With a default classification cut-off at 0.5 predicted probability, the extreme gradient boosting algorithm showed the highest positive predictive value (ppv) of 0.71(0.61 – 0.77) with a sensitivity of 0.35 (0.29 – 0.41) and area under the curve of 0.78. A trade-off can be made between ppv and sensitivity by choosing different cut-off probabilities. With a cut-off at 0.63, the ppv increased to 0.87 and the sensitivity dropped to 0.17. With a cut-off of at 0.38, the ppv decreased to 0.61 and the sensitivity increased to 0.57. CONCLUSIONS Machine learning can be used to predict treatment outcomes based on routine monitoring data.This allows practitioners to choose their own trade-off between being selective and more certain versus inclusive and less certain.

scholarly journals Evaluation of Three Different Machine Learning Methods for Object-Based Artificial Terrace Mapping—A Case Study of the Loess Plateau, China

2021 ◽  
Vol 13 (5) ◽  
pp. 1021
Author(s):  
Hu Ding ◽  
Jiaming Na ◽  
Shangjing Jiang ◽  
Jie Zhu ◽  
Kai Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Loess Plateau ◽  
Water Conservation ◽  
Nearest Neighbor ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
The Loess Plateau ◽  
Object Based ◽  
Extreme Gradient Boosting

Artificial terraces are of great importance for agricultural production and soil and water conservation. Automatic high-accuracy mapping of artificial terraces is the basis of monitoring and related studies. Previous research achieved artificial terrace mapping based on high-resolution digital elevation models (DEMs) or imagery. As a result of the importance of the contextual information for terrace mapping, object-based image analysis (OBIA) combined with machine learning (ML) technologies are widely used. However, the selection of an appropriate classifier is of great importance for the terrace mapping task. In this study, the performance of an integrated framework using OBIA and ML for terrace mapping was tested. A catchment, Zhifanggou, in the Loess Plateau, China, was used as the study area. First, optimized image segmentation was conducted. Then, features from the DEMs and imagery were extracted, and the correlations between the features were analyzed and ranked for classification. Finally, three different commonly-used ML classifiers, namely, extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN), were used for terrace mapping. The comparison with the ground truth, as delineated by field survey, indicated that random forest performed best, with a 95.60% overall accuracy (followed by 94.16% and 92.33% for XGBoost and KNN, respectively). The influence of class imbalance and feature selection is discussed. This work provides a credible framework for mapping artificial terraces.

Risk scoring by CHADS2 and CHA2DS2-VASc as predictors for long-term outcomes after surgical ablation for atrial fibrillation

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
D Lauritzen ◽  
H.J Vodstrup ◽  
T.D Christensen ◽  
M Onat ◽  
R Christensen ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Cardiac Surgery ◽  
Isolation Procedure ◽  
Survival Times ◽  
Long Term Outcomes ◽  
Surgical Ablation ◽  
Follow Up Study ◽  
Risk Scoring

Abstract Background Following catheter ablation for atrial fibrillation (AF), CHADS2 and CHA2DS2-VASc have utility in predicting long-term outcomes. However, it is currently unknown if the same holds for patients undergoing surgical ablation. Purpose To determine whether CHADS2 and CHA2DS2-VASc predict long-term outcomes after surgical ablation in concomitance with other cardiac surgery. Methods In this prospective, follow-up study, we included patients who underwent biatrial ablation - or pulmonary vein isolation procedure concomitantly with other cardiac surgery between 2004 and 2018. CHADS2 and CHA2DS2-VASc scores were assessed prior to surgery and categorized in groups as 0–1, 2–4 or ≥5. Outcomes were death, AF, and AF-related death. Follow-up was ended in April 2019. Results A total of 587 patients with a mean age of 68.7±0.4 years were included. Both CHADS2 and CHA2DS2-VASc scores were predictors of survival p=0.005 and p&lt;0.001, respectively (Figure). For CHADS2, mean survival times were 5.9±3.7 years for scores 0–1, 5.0±3.0 years for scores 2–4 and 4.3±2.6 years for scores ≥5. For CHA2DS2-VASc mean survival times were 7.3±4.0 years for scores 0–1, 5.6±2.9 years for scores 2–4 and 4.8±2.1 years for scores ≥5. The incidence of death was 20.1% for CHADS2 0–1, 24.8% for CHADS2 2–4, and 35.3% for CHADS2 ≥5, p=0.186. The incidence of AF was 50.2% for CHADS2 0–1, 47.9% for CHADS2 2–4, and 76.5% for CHADS2 ≥5, p=0.073. The incidence of AF related death was 13.0% for CHADS2 0–1, 16.8% for CHADS2 2–4, and 35.3% for CHADS2 ≥5, p=0.031. The incidence of death was 16.8% for CHA2DS2-VASc 0–1, 26.2% for CHA2DS2-VASc 2–4, and 45.0% for CHA2DS2-VASc ≥5, p=0.001. The incidence of AF was 49.6% for CHA2DS2-VASc 0–1, 52.5% for CHA2DS2-VASc 2–4, and 72.5% for CHA2DS2-VASc ≥5, p=0.035. The incidence of AF related death was 12.2% for CHA2DS2-VASc 0–1, 16.0% for CHA2DS2-VASc 2–4, and 42.5% for CHA2DS2-VASc ≥5, p&lt;0.001. Conclusion Both CHADS2 and CHA2DS2-VASc scores predict long-term outcomes after surgical ablation for AF. However, CHA2DS2-VASc was superior in predicting death, AF, and AF-related death. Survival curves Funding Acknowledgement Type of funding source: None

scholarly journals A Machine Learning Method for Predicting Vegetation Indices in China

2021 ◽  
Vol 13 (6) ◽  
pp. 1147
Author(s):  
Xiangqian Li ◽  
Wenping Yuan ◽  
Wenjie Dong
Keyword(s):  
Machine Learning ◽  
Growing Season ◽  
Crop Growth ◽  
Spatiotemporal Distribution ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Severe Drought ◽  
Vegetation Growth ◽  
Extreme Gradient Boosting ◽  
Boosting Method

To forecast the terrestrial carbon cycle and monitor food security, vegetation growth must be accurately predicted; however, current process-based ecosystem and crop-growth models are limited in their effectiveness. This study developed a machine learning model using the extreme gradient boosting method to predict vegetation growth throughout the growing season in China from 2001 to 2018. The model used satellite-derived vegetation data for the first month of each growing season, CO2 concentration, and several meteorological factors as data sources for the explanatory variables. Results showed that the model could reproduce the spatiotemporal distribution of vegetation growth as represented by the satellite-derived normalized difference vegetation index (NDVI). The predictive error for the growing season NDVI was less than 5% for more than 98% of vegetated areas in China; the model represented seasonal variations in NDVI well. The coefficient of determination (R2) between the monthly observed and predicted NDVI was 0.83, and more than 69% of vegetated areas had an R2 > 0.8. The effectiveness of the model was examined for a severe drought year (2009), and results showed that the model could reproduce the spatiotemporal distribution of NDVI even under extreme conditions. This model provides an alternative method for predicting vegetation growth and has great potential for monitoring vegetation dynamics and crop growth.

Sign in / Sign up

Export Citation Format

Share Document