Dataset Information

Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan.

ABSTRACT:

Background

Machine learning (ML) model is increasingly used to predict short-term outcome in critically ill patients, but the study for long-term outcome is sparse. We used explainable ML approach to establish 30-day, 90-day and 1-year mortality prediction model in critically ill ventilated patients.

Methods

We retrospectively included patients who were admitted to intensive care units during 2015-2018 at a tertiary hospital in central Taiwan and linked with the Taiwanese nationwide death registration data. Three ML models, including extreme gradient boosting (XGBoost), random forest (RF) and logistic regression (LR), were used to establish mortality prediction model. Furthermore, we used feature importance, Shapley Additive exPlanations (SHAP) plot, partial dependence plot (PDP), and local interpretable model-agnostic explanations (LIME) to explain the established model.

Results

We enrolled 6994 patients and found the accuracy was similar among the three ML models, and the area under the curve value of using XGBoost to predict 30-day, 90-day and 1-year mortality were 0.858, 0.839 and 0.816, respectively. The calibration curve and decision curve analysis further demonstrated accuracy and applicability of models. SHAP summary plot and PDP plot illustrated the discriminative point of APACHE (acute physiology and chronic health exam) II score, haemoglobin and albumin to predict 1-year mortality. The application of LIME and SHAP force plots quantified the probability of 1-year mortality and algorithm of key features at individual patient level.

Conclusions

We used an explainable ML approach, mainly XGBoost, SHAP and LIME plots to establish an explainable 1-year mortality prediction ML model in critically ill ventilated patients.

SUBMITTER: Chan MC

PROVIDER: S-EPMC8953968 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan.

Chan Ming-Cheng MC Pai Kai-Chih KC Su Shao-An SA Wang Min-Shian MS Wu Chieh-Liang CL Chao Wen-Cheng WC

BMC medical informatics and decision making 20220325 1

<h4>Background</h4>Machine learning (ML) model is increasingly used to predict short-term outcome in critically ill patients, but the study for long-term outcome is sparse. We used explainable ML approach to establish 30-day, 90-day and 1-year mortality prediction model in critically ill ventilated patients.<h4>Methods</h4>We retrospectively included patients who were admitted to intensive care units during 2015-2018 at a tertiary hospital in central Taiwan and linked with the Taiwanese nationwi ...[more]

PMID: 35337303

Similar Datasets

Project description:ObjectivesCurrent mortality prediction models used in the intensive care unit (ICU) have a limited role for specific diseases such as influenza, and we aimed to establish an explainable machine learning (ML) model for predicting mortality in critically ill influenza patients using a real-world severe influenza data set.Study designA cross-sectional retrospective multicentre study in Taiwan SETTING: Eight medical centres in Taiwan.ParticipantsA total of 336 patients requiring ICU-admission for virology-proven influenza at eight hospitals during an influenza epidemic between October 2015 and March 2016.Primary and secondary outcome measuresWe employed extreme gradient boosting (XGBoost) to establish the prediction model, compared the performance with logistic regression (LR) and random forest (RF), demonstrated the feature importance categorised by clinical domains, and used SHapley Additive exPlanations (SHAP) for visualised interpretation.ResultsThe data set contained 76 features of the 336 patients with severe influenza. The severity was apparently high, as shown by the high Acute Physiology and Chronic Health Evaluation II score (22, 17 to 29) and pneumonia severity index score (118, 88 to 151). XGBoost model (area under the curve (AUC): 0.842; 95% CI 0.749 to 0.928) outperformed RF (AUC: 0.809; 95% CI 0.629 to 0.891) and LR (AUC: 0.701; 95% CI 0.573 to 0.825) for predicting 30-day mortality. To give clinicians an intuitive understanding of feature exploitation, we stratified features by the clinical domain. The cumulative feature importance in the fluid balance domain, ventilation domain, laboratory data domain, demographic and symptom domain, management domain and severity score domain was 0.253, 0.113, 0.177, 0.140, 0.152 and 0.165, respectively. We further used SHAP plots to illustrate associations between features and 30-day mortality in critically ill influenza patients.ConclusionsWe used a real-world data set and applied an ML approach, mainly XGBoost, to establish a practical and explainable mortality prediction model in critically ill influenza patients.

Project description:Objective: The number of patients requiring prolonged mechanical ventilation (PMV) is increasing worldwide, but the weaning outcome prediction model in these patients is still lacking. We hence aimed to develop an explainable machine learning (ML) model to predict successful weaning in patients requiring PMV using a real-world dataset. Methods: This retrospective study used the electronic medical records of patients admitted to a 12-bed respiratory care center in central Taiwan between 2013 and 2018. We used three ML models, namely, extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), to establish the prediction model. We further illustrated the feature importance categorized by clinical domains and provided visualized interpretation by using SHapley Additive exPlanations (SHAP) as well as local interpretable model-agnostic explanations (LIME). Results: The dataset contained data of 963 patients requiring PMV, and 56.0% (539/963) of them were successfully weaned from mechanical ventilation. The XGBoost model (area under the curve [AUC]: 0.908; 95% confidence interval [CI] 0.864-0.943) and RF model (AUC: 0.888; 95% CI 0.844-0.934) outperformed the LR model (AUC: 0.762; 95% CI 0.687-0.830) in predicting successful weaning in patients requiring PMV. To give the physician an intuitive understanding of the model, we stratified the feature importance by clinical domains. The cumulative feature importance in the ventilation domain, fluid domain, physiology domain, and laboratory data domain was 0.310, 0.201, 0.265, and 0.182, respectively. We further used the SHAP plot and partial dependence plot to illustrate associations between features and the weaning outcome at the feature level. Moreover, we used LIME plots to illustrate the prediction model at the individual level. Additionally, we addressed the weekly performance of the three ML models and found that the accuracy of XGBoost/RF was ~0.7 between weeks 4 and week 7 and slightly declined to 0.6 on weeks 8 and 9. Conclusion: We used an ML approach, mainly XGBoost, SHAP plot, and LIME plot to establish an explainable weaning prediction ML model in patients requiring PMV. We believe these approaches should largely mitigate the concern of the black-box issue of artificial intelligence, and future studies are warranted for the landing of the proposed model.

Project description:BackgroundOver the past decade, numerous studies on potential factors contributing to ventilation-induced lung injury have been carried out. Mechanical power has been pointed out as the parameter that encloses all ventilation-induced lung injury-contributing factors. However, studies conducted to date provide data regarding mechanical power during the early hours of mechanical ventilation that may not accurately reflect the impact of power throughout the period of mechanical ventilatory support on intensive care unit mortality.MethodsRetrospective observational study conducted at a single center in Spain. Patients admitted to the intensive care unit, > o = 18 years of age, and ventilated for over 24 h were included. We extracted the mechanical power values throughout the entire mechanical ventilation in controlled modes period from the clinical information system every 2 min. First, we calculate the cutoff-point for mechanical power beyond which there was a greater change in the probability of death. After, the sum of time values above the safe cut-off point was calculated to obtain the value in hours. We analyzed if the number of hours the patient was under ventilation with a mechanical power above the safe threshold was associated with intensive care unit mortality, invasive mechanical ventilation days, and intensive care unit length of stay. We repeated the analysis in different subgroups based on the degree of hypoxemia and in patients with SARS CoV-2 pneumonia.ResultsThe cut-off point of mechanical power at with there is a higher increase in intensive care unit mortality was 18 J/min. The greater the number of hours patients were under mechanical power > 18 J/min the higher the intensive care unit mortality in all the study population, in patients with SARS CoV-2 pneumonia and in mild to moderate hypoxemic respiratory failure. The risk of death in the intensive care unit increases 0.1% for each hour with mechanical power exceeding 18 J/min. The number of hours with mechanical power > 18 J/min also affected the days of invasive mechanical ventilation and intensive care unit length of stay.ConclusionsThe number of hours with mechanical power > 18 J/min is associated with mortality in the intensive care unit in critically ill patients. Continuous monitoring of mechanical power in controlled modes using an automated clinical information system could alert the clinician to this risk.

Dataset Information

Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan.

Background

Methods

Results

Conclusions

Publications

Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets