Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization

Yang, Meicheng; Wang, Xingyao; Gao, Hongxiang; Li, Yuwen; Liu, Xing; Li, Jianqing; Liu, Chengyu

doi:10.22489/cinc.2019.020

Cited by 17 publications

(16 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparative analysis of the results obtained by the proposed method with our previous works [19,38] and submission approaches [39][40][41][42][43][44][45][46] that reported the best results in the PhysioNet 2019 Challenge [18] is listed in Table 4.Most of these approaches utilized 5 or 10 fold cross-validation scheme and yielded utility scores in the range of 0.36-0.45.…”

Section: Discussionmentioning

confidence: 99%

An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data

Nesaragi¹,

Patidar²

2021

Infections and Sepsis Development

View full text Add to dashboard Cite

Early identification of individuals with sepsis is very useful in assisting clinical triage and decision-making, resulting in early intervention and improved outcomes. This study aims to develop an explainable machine learning model with the clinical interpretability to predict sepsis onset before 6 hours and validate with improved prediction risk power for every time interval since admission to the ICU. The retrospective observational cohort study is carried out using PhysioNet Challenge 2019 ICU data from three distinct hospital systems, viz. A, B, and C. Data from A and B were shared publicly for training and validation while sequestered data from all three cohorts were used for scoring. However, this study is limited only to publicly available training data. Training data contains 15,52,210 patient records of 40,336 ICU patients with up to 40 clinical variables (sourced for each hour of their ICU stay) divided into two datasets, based on hospital systems A and B. The clinical feature exploration and interpretation for early prediction of sepsis is achieved using the proposed framework, viz. the explainable Machine Learning model for Early Prediction of Sepsis (xMLEPS). A total of 85 features comprising the given 40 clinical variables augmented with 10 derived physiological features and 35 time-lag difference features are fed to xMLEPS for the said prediction task of sepsis onset. A ten-fold cross-validation scheme is employed wherein an optimal prediction risk threshold is searched for each of the 10 LightGBM models. These optimum threshold values are later used by the corresponding models to refine the predictive power in terms of utility score for the prediction of labels in each fold. The entire framework is designed via Bayesian optimization and trained with the resultant feature set of 85 features, yielding an average normalized utility score of 0.4214 and area under receiver operating characteristic curve of 0.8591 on publicly available training data. This study establish a practical and explainable sepsis onset prediction model for ICU data using applied ML approach, mainly gradient boosting. The study highlights the clinical significance of physiological inter-relations among the given and proposed clinical signs via feature importance and SHapley Additive exPlanations (SHAP) plots for visualized interpretation.

show abstract

Section: Discussionmentioning

confidence: 99%

An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data

Nesaragi¹,

Patidar²

2021

Infections and Sepsis Development

View full text Add to dashboard Cite

show abstract

“…The submission by Yang et al [11] achieved the highest area under ROC curve as well as the highest utility score on the competition's private dataset (data from a third hospital) [8]. This top performing approach has been incorporated in the current study to examine its clinical value below.…”

Section: Feature Valuation Experimentsmentioning

confidence: 96%

“…Section II of this paper incorporates the top approach from the PhysioNet 2019 competition [11]. Certain features based on clinicians' expertise used in this approach may not provide diagnostic benefit.…”

Section: Introductionmentioning

confidence: 99%

Practical Machine Learning-Based Sepsis Prediction

Pettinati¹,

Chen²,

Rajput³

et al. 2020

2020 42nd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Sepsis is a life-threatening clinical syndrome and one of the most expensive conditions treated in hospitals. It is challenging to detect due to the nonspecific clinical signs and the absence of gold standard diagnostics. However, early recognition of sepsis and optimal treatments for sepsis are of paramount importance to improve the condition's management and patient outcomes. This paper aims to delineate key aspects of current sepsis detection systems, including their dependency on clinical expert and laboratory biometric features requiring ongoing critical care intervention, the efficacy of vital sign measures, and the effect of the study population with respect to the precision of sepsis prediction. The AUROC performances of XGBoost models trained on a heterogenous ICU patient group (n=3932) showed significant degradations (p<0.05) as the expert and laboratory biomarker features are removed systematically and vital sign features taken in ICU settings are left. The performance of XGBoost models trained only with vital sign features on a more homogeneous group of ICU patients (n=1927) had a significantly (P<0.05) improved AUPRC to moderate level. The presented results highlight the importance of making a practical machine learning system for sepsis prediction by considering the availability of dominant features as well as personalizing sepsis prediction by configuring it to the specific demographics of a targeted population.

show abstract

“…Yang et al [20] proposed real-time ensemble technique using multi-feature fusion based on XGBoost learning and Bayesian optimization [21]. All features were selected except Bilirubin Direct (Bilirubin_direct), Troponin I, and Fibrinogen as these features have more than 99% missing values.…”

Section: Machine Learning Models For Sepsis Predictionmentioning

confidence: 99%

Comparative Study of Machine Learning Models for Onset Sepsis Prediction

Rayan

Alfonse

Salem

2021

Digital Transformation Technology

View full text Add to dashboard Cite

Sepsis is one of life-threatening diseases that is caused by unbalanced body response to some chemicals that the body release into its blood stream when fighting an infection. Early prediction of sepsis can decrease mortality rates. Machine learning techniques can improve the accuracy of early sepsis prediction. This paper presents a comparative study for recent machine learning models that can be used for sepsis prediction using datasets provided by international Challenge, named PhysioNet/Computing in Cardiology 2019.

show abstract

Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization

Cited by 17 publications

References 12 publications

An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data

An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data

Practical Machine Learning-Based Sepsis Prediction

Comparative Study of Machine Learning Models for Onset Sepsis Prediction

Contact Info

Product

Resources

About