Machine Learning Methods for Septic Shock Prediction

Darwiche, Aiman; Mukherjee, Sumitra

doi:10.1145/3293663.3293673

Cited by 10 publications

(12 citation statements)

References 99 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider the early prediction of septic shock using the MIMIC-III dataset, following the frameworks provided in recent data-driven works for data pre-processing [38,15,59,45,36]. Specifically, we use 14 commonly-utilized vital signs and lab results over a 2-hour observation window to predict whether a patient will develop septic shock in the next 4-hour window, which we refer to as the early prediction window (EPW) -details are provided in Appendix D.1.…”

Section: Mimic-iiimentioning

confidence: 99%

Gradient Importance Learning for Incomplete Observations

Gao

Wang

Amason

et al. 2021

Preprint

View full text Add to dashboard Cite

Although recent works have developed methods that can generate estimations (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks. This is particularly true if the data have large missingness rates or a small population. More importantly, the imputation error could be propagated into the prediction step that follows, causing the gradients used to train the prediction models to be biased. Consequently, in this work, we introduce the importance guided stochastic gradient descent (IGSGD) method to train multilayer perceptrons (MLPs) and long short-term memories (LSTMs) to directly perform inference from inputs containing missing values without imputation. Specifically, we employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation. This not only reduces bias but allows the model to exploit the underlying information behind missingness patterns. We test the proposed approach on real-world time-series (i.e., MIMIC-III), tabular data obtained from an eye clinic, and a standard dataset (i.e., MNIST), where our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.

show abstract

Section: Mimic-iiimentioning

confidence: 99%

Gradient Importance Learning for Incomplete Observations

Gao

Wang

Amason

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Scoring tools such as the Early Warning Score (MEWS), shock index, and quick Sequential Organ Failure Assessment (qSOFA) or Sequential Organ Failure Assessment (SOFA) are widely used in EDs (6)(7)(8). In addition, machine learning-based shock-prediction models are being studied (9)(10)(11)(12), and vital-sign information can be obtained in real time. A previous study reported the use of serial vital signs in predicting patient status in intensive care units (ICUs) or wards (13).…”

Section: Introductionmentioning

confidence: 99%

Early Prediction of Unexpected Latent Shock in the Emergency Department Using Vital Signs

Chang,

Jung,

et al. 2023

Shock

View full text Add to dashboard Cite

Objective/Introduction Sequential vital-sign information and trends in vital signs are useful for predicting changes in patient state. This study aims to predict latent shock by observing sequential changes in patient vital signs. Methods The dataset for this retrospective study contained a total of 93,194 emergency department (ED) visits from January 1, 2016, and December 31, 2020, and Medical Information Mart for Intensive Care (MIMIC)-IV-ED data. We further divided the data into training and validation datasets by random sampling without replacement at a 7:3 ratio. We carried out external validation with MIMIC-IV-ED. Our prediction model included logistic regression (LR), random forest (RF) classifier, a multi-layer perceptron (MLP), and a recurrent neural network (RNN). To analyze the model performance, we used area under the receiver operating characteristic curve (AUROC). Results Data of 89,250 visits of patients who met pre-specified criteria were used to develop a latent-shock prediction model. Data of 142,250 patient visits from MIMIC-IV-ED satisfying the same inclusion criteria were used for external validation of the prediction model. The AUROC values of prediction for latent shock were 0.822, 0.841, 0.852, and 0.830 with RNN, MLP, RF, and LR methods, respectively, at 3 h before latent shock. This is higher than the shock index or adjusted shock index. Conclusion We developed a latent shock prediction model based on 24 hours of vital-sign sequence that changed with time and predicted the results by individual.

show abstract

“…It is a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. Random forest (RF) has been used in biology and medicine, such as high-dimensional genetic or tissue microarray data and MIMIC-III [1][2][3][4][5][6]. It is specifically devised to operate quickly and efficiently over large datasets because of the simplification and it offers the highest prediction accuracy compared to other models in the setting of classification.…”

Section: Introductionmentioning

confidence: 99%

An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application

2023

View full text Add to dashboard Cite

The random forest algorithm could be enhanced and produce better results with a well-designed and organized feature selection phase. The dependency structure between the variables is considered to be the most important criterion behind selecting the variables to be used in the algorithm during the feature selection phase. As the dependency structure is mostly nonlinear, making use of a tool that considers nonlinearity would be a more beneficial approach. Copula-Based Clustering technique (CoClust) clusters variables with copulas according to nonlinear dependency. We show that it is possible to achieve a remarkable improvement in CPU times and accuracy by adding the CoClust-based feature selection step to the random forest technique. We work with two different large datasets, namely, the MIMIC-III Sepsis Dataset and the SMS Spam Collection Dataset. The first dataset is large in terms of rows referring to individual IDs, while the latter is an example of longer column length data with many variables to be considered. In the proposed approach, first, random forest is employed without adding the CoClust step. Then, random forest is repeated in the clusters obtained with CoClust. The obtained results are compared in terms of CPU time, accuracy and ROC (receiver operating characteristic) curve. CoClust clustering results are compared with K-means and hierarchical clustering techniques. The Random Forest, Gradient Boosting and Logistic Regression results obtained with these clusters and the success of RF and CoClust working together are examined.

show abstract

Machine Learning Methods for Septic Shock Prediction

Cited by 10 publications

References 99 publications

Gradient Importance Learning for Incomplete Observations

Gradient Importance Learning for Incomplete Observations

Early Prediction of Unexpected Latent Shock in the Emergency Department Using Vital Signs

An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application

Contact Info

Product

Resources

About