A population-based observational study of patients with pulmonary disorders in intensive care unit

Interpretability-based machine learning for predicting the risk of death from pulmonary inflammation in Chinese intensive care unit patients

Objective

The objective of this research was to create a machine learning predictive model that could be easily interpreted in order to precisely determine the risk of premature death in patients receiving intensive care after pulmonary inflammation.

Methods

In this study, information from the China intensive care units (ICU) Open Source database was used to examine data from 2790 patients who had infections between January 2019 and December 2020. A 7:3 ratio was used to randomly assign the whole patient population to training and validation groups. This study used six machine learning techniques: logistic regression, random forest, gradient boosting tree, extreme gradient boosting tree (XGBoost), multilayer perceptron, and K-nearest neighbor. A cross-validation grid search method was used to search the parameters in each model. Eight metrics were used to assess the models' performance: accuracy, precision, recall, F1 score, area under the curve (AUC) value, Brier score, Jordon's index, and calibration slope. The machine methods were ranked based on how well they performed in each of these metrics. The best-performing models were selected for interpretation using both the Shapley Additive exPlanations (SHAP) and Local interpretable model-agnostic explanations (LIME) interpretable techniques.

Results

A subset of the study cohort's patients (120/1668, or 7.19%) died in the hospital following screening for inclusion and exclusion criteria. Using a cross-validated grid search to evaluate the six machine learning techniques, XGBoost showed good discriminative ability, achieving an accuracy score of 0.889 (0.874-0.904), precision score of 0.871 (0.849-0.893), recall score of 0.913 (0.890-0.936), F1 score of 0.891 (0.876-0.906), and AUC of 0.956 (0.939-0.973). Additionally, XGBoost exhibited excellent performance with a Brier score of 0.050, Jordon index of 0.947, and calibration slope of 1.074. It was also possible to create an interactive internet page using the XGBoost model.

Conclusion

By identifying patients at higher risk of early mortality, machine learning-based mortality risk prediction models have the potential to significantly improve patient care by directing clinical decision making and enabling early detection of survival and mortality issues in patients with pulmonary inflammation disease.

Machine learning-based prediction of in-ICU mortality in pneumonia patients

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO₂/FiO₂ ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Epidemiological profile and risk factors associated with death in patients receiving invasive mechanical ventilation in an adult intensive care unit from Brazil: a retrospective study

Introduction

Understanding the epidemiological profile and risk factors associated with invasive mechanical ventilation (IMV) is essential to manage the patients better and to improve health services. Therefore, our objective was to describe the epidemiological profile of adult patients in intensive care that required IMV in-hospital treatment. Also, to evaluate the risks associated with death and the influence of positive end-expiratory pressure (PEEP) and arterial oxygen pressure (PaO2) at admission in the clinical outcome.

Methods

We conducted an epidemiological study analyzing medical records of inpatients who received IMV from January 2016 to December 2019 prior to the Coronavirus Disease (COVID)-19 pandemic in Brazil. We considered the following characteristics in the statistical analysis: demographic data, diagnostic hypothesis, hospitalization data, and PEEP and PaO2 during IMV. We associated the patients' features with the risk of death using a multivariate binary logistic regression analysis. We adopted an alpha error of 0.05.

Results

We analyzed 1,443 medical records; out of those, 570 (39.5%) recorded the patients' deaths. The binary logistic regression was significant in predicting the patients' risk of death [X2(9) = 288.335; p < 0.001]. Among predictors, the most significant in relation to death risk were: age [elderly ≥65 years old; OR = 2.226 (95%CI = 1.728-2.867)]; male sex (OR = 0.754; 95%CI = 0.593-0.959); sepsis diagnosis (OR = 1.961; 95%CI = 1.481-2.595); need for elective surgery (OR = 0.469; 95%CI = 0.362-0.608); the presence of cerebrovascular accident (OR = 2.304; 95%CI = 1.502-3.534); time of hospital care (OR = 0.946; 95%CI = 0.935-0.956); hypoxemia at admission (OR = 1.635; 95%CI = 1.024-2.611), and PEEP >8 cmH2O at admission (OR = 2.153; 95%CI = 1.426-3.250).

Conclusion

The death rate of the studied intensive care unit was equivalent to that of other similar units. Regarding risk predictors, several demographic and clinical characteristics were associated with enhanced mortality in intensive care unit patients under mechanical ventilation, such as diabetes mellitus, systemic arterial hypertension, and older age. The PEEP >8 cmH2O at admission was also associated with increased mortality since this value is a marker of initially severe hypoxia.

Development and validation of a patient-reported outcome measure for patients with chronic respiratory failure: The CRF-PROM scale

Background

Various health‐related quality‐of‐life (HRQOL) tools are used to evaluate patients with chronic respiratory failure (CRF), but there is a relative lack of tools available for the evaluation of social support and treatment in these patients. The present study focused on the development of a systematic patient‐reported outcome measure (PROM) tool for use in patients with CRF.

Methods

The CRF‐PROM scale conceptual framework and item bank were generated after reviewing the corresponding literature and HRQOL scales, interviewing CRF patients and focus groups. After creation of the initial scale, the items in the scale were selected through two item selection theories, and the final scale was created. The reliability, validity and feasibility of the final scale were assessed.

Results

The CRF‐PROM scale includes four domains (i.e., physiological domain, psychological domain, social domain and therapeutic domain) and 10 dimensions. After the item selection process, the final scale included 50 items. Cronbach's α coefficients, which were all above 0.7, indicated the reliability of the scale. The results of structural validity met the relevant standards of confirmatory factor analysis. The response rates of the preinvestigation and the formal investigation were 93.3% and 97.6%, respectively.

Conclusions

The CRF‐PROM scale developed in the present study is effective and reliable. It could be used widely in the posthospital management of patients, in CRF studies and in clinical trials of new medical products and interventions.

Patient or Public Contribution

Participants from eight different hospitals and communities participated in the development or validation phase of the CRF‐PROM scale.

The Impact of Mechanical Ventilation Duration on the Readmission to Intensive Care Unit: A Population-Based Observational Study

Background

If the duration of mechanical ventilation (MV) is related with the intensive care unit (ICU) readmission must be clarified. The purpose of this study was to elucidate if prolonged MV duration increases ICU readmission rate.

Methods

The present observational cohort study analyzed national healthcare claims data from 2006 to 2015. Critically ill patients who received MV in the ICU were classified into five groups according to the MV duration: MV for <7 days, 7–13 days, 14–20 days, 21–27 days, and ≥28 days. The rate and risk of the ICU readmission were estimated according to the MV duration using the unadjusted and adjusted analyses.

Results

We found that 12,929 patients had at least one episode of MV in the ICU. There was a significant linear relationship between the MV duration and the ICU readmission (R²=0.85, p=0.025). The total readmission rate was significantly higher as the MV duration is prolonged (MV for <7 days, 13.9%; for 7–13 days, 16.7%; for 14–20 days, 19.4%; for 21–27 days, 20.4%; for ≥28 days, 35.7%; p<0.001). The analyses adjusted by covariables and weighted with the multinomial propensity scores showed similar results. In the adjusted regression analysis with a Cox proportional hazards model, the MV duration was significantly related to the ICU readmission (hazard ratio, 1.058 [95% confidence interval, 1.047–1.069], p<0.001).

Conclusion

The rate of readmission to the ICU was significantly higher in patients who received longer durations of the MV in the ICU. In the clinical setting, closer observation of patients discharged from the ICU after prolonged periods of MV is required.