Use of electronic critical care flow sheet data to predict unplanned extubation in ICUs

Predicting intubation for intensive care units patients: A deep learning approach to improve patient management

OBJECTIVE

For patients in the Intensive Care Unit (ICU), the timing of intubation has a significant association with patients' outcomes. However, accurate prediction of the timing of intubation remains an unsolved challenge due to the noisy, sparse, heterogeneous, and unbalanced nature of ICU data. In this study, our objective is to develop a workflow for pre-processing ICU data and to develop a customized deep learning model to predict the need for intubation.

METHODS

To improve the prediction accuracy, we transform the intubation prediction task into a time series classification task. We carefully design a sequence of data pre-processing steps to handle the multimodal noisy data. Firstly, we discretize the sequential data and address missing data using interpolation. Next, we employ a sampling strategy to address data imbalance and standardize the data to facilitate faster model convergence. Furthermore, we employ the feature selection technique and propose an ensemble model to combine features learned by different deep learning models.

RESULTS

The performance is evaluated on Medical Information Mart for Intensive Care (MIMIC)-III, an ICU dataset. Our proposed Deep Feature Fusion method achieves an area under the curve (AUC) of the receiver operating curve (ROC) of 0.8953, surpassing the performance of other deep learning and traditional machine learning models.

CONCLUSION

Our proposed Deep Feature Fusion method proves to be a viable approach for predicting intubation and outperforms other deep learning and classical machine learning models. The study confirms that high-frequency time-varying indicators, particularly Mean Blood Pressure (MeanBP) and peripheral oxygen saturation (SpO2), are significant risk factors for predicting intubation.

Risk Factors and Predictive Models for Peripherally Inserted Central Catheter Unplanned Extubation in Patients With Cancer: Prospective, Machine Learning Study

BACKGROUND

Cancer indeed represents a significant public health challenge, and unplanned extubation of peripherally inserted central catheter (PICC-UE) is a critical concern in patient safety. Identifying independent risk factors and implementing high-quality assessment tools for early detection in high-risk populations can play a crucial role in reducing the incidence of PICC-UE among patients with cancer. Precise prevention and treatment strategies are essential to improve patient outcomes and safety in clinical settings.

OBJECTIVE

This study aims to identify the independent risk factors associated with PICC-UE in patients with cancer and to construct a predictive model tailored to this group, offering a theoretical framework for anticipating and preventing PICC-UE in these patients.

METHODS

Prospective data were gathered from January to December 2022, encompassing patients with cancer with PICC at Xiangya Hospital, Central South University. Each patient underwent continuous monitoring until the catheter's removal. The patients were categorized into 2 groups: the UE group (n=3107) and the non-UE group (n=284). Independent risk factors were identified through univariate analysis, the least absolute shrinkage and selection operator (LASSO) algorithm, and multivariate analysis. Subsequently, the 3391 patients were classified into a train set and a test set in a 7:3 ratio. Utilizing the identified predictors, 3 predictive models were constructed using the logistic regression, support vector machine, and random forest algorithms. The ultimate model was selected based on the receiver operating characteristic (ROC) curve and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) synthesis analysis. To further validate the model, we gathered prospective data from 600 patients with cancer at the Affiliated Hospital of Qinghai University and Hainan Provincial People's Hospital from June to December 2022. We assessed the model's performance using the area under the curve of the ROC to evaluate differentiation, the calibration curve for calibration capability, and decision curve analysis (DCA) to gauge the model's clinical applicability.

RESULTS

Independent risk factors for PICC-UE in patients with cancer were identified, including impaired physical mobility (odds ratio [OR] 2.775, 95% CI 1.951-3.946), diabetes (OR 1.754, 95% CI 1.134-2.712), surgical history (OR 1.734, 95% CI 1.313-2.290), elevated D-dimer concentration (OR 2.376, 95% CI 1.778-3.176), targeted therapy (OR 1.441, 95% CI 1.104-1.881), surgical treatment (OR 1.543, 95% CI 1.152-2.066), and more than 1 catheter puncture (OR 1.715, 95% CI 1.121-2.624). Protective factors were normal BMI (OR 0.449, 95% CI 0.342-0.590), polyurethane catheter material (OR 0.305, 95% CI 0.228-0.408), and valved catheter (OR 0.639, 95% CI 0.480-0.851). The TOPSIS synthesis analysis results showed that in the train set, the composite index (Ci) values were 0.00 for the logistic model, 0.82 for the support vector machine model, and 0.85 for the random forest model. In the test set, the Ci values were 0.00 for the logistic model, 1.00 for the support vector machine model, and 0.81 for the random forest model. The optimal model, constructed based on the support vector machine, was obtained and validated externally. The ROC curve, calibration curve, and DCA curve demonstrated that the model exhibited excellent accuracy, stability, generalizability, and clinical applicability.

CONCLUSIONS

In summary, this study identified 10 independent risk factors for PICC-UE in patients with cancer. The predictive model developed using the support vector machine algorithm demonstrated excellent clinical applicability and was validated externally, providing valuable support for the early prediction of PICC-UE in patients with cancer.

STformer: Spatial-Temporal Transformer for early Warning of Unplanned Extubation in ICU

Patients' Unplanned Extubation (UEX) is dangerous in the intensive care units (ICU), it is necessary to make early warning of UEX. However, the low fine-grained action of UEX and complexity of ICU environment make early warning a great challenging by using RGB video data. To address this issue, we propose a novel lightweight Spatial-Temporal Transformer (STformer) for early warning of patients' UEX action in the ICU. Specially, the SlowFast is used to extract patient's spatial-temporal features initially. Then, in order to improve the representation of features, we introduce spatial attention to enhance the spatial representation of fine-grained actions, and capture the long-term dependency of motions through temporal attention. Finally, a spatial-temporal joint attention is used to reconstruct and strengthen spatial and temporal information. Experiment results illustrate state-of-the-art performance of our STformer on ICU monitory datasets. While ensuring the accuracy of early warning, the computational complexity of STformer are also light.

Clinical application and evaluation of a new type of tracheal catheter fixation belt

AIM

To evaluate a new fixation band for tracheal catheter in intensive care unit.

DESIGN

A cross-sectional study.

METHODS

A total of 90 patients admitted to the ICU between August 2018-February 2019 were enrolled in the study. Patients were randomly divided into experimental group and control group (N = 45/per each group). 3 M strong adhesive tape and a new tracheal catheter fixation band were applied to patients in two groups, respectively. The fixation effect, incidence of mucosal pressure injury and nursing cost were evaluated.

RESULTS

Forty-three patients from the experimental group and 42 patients from the control group participated in this study. Mild, moderate and severe catheter dislocation happened in 2, 0, 0 cases in the experimental group, and 6, 3 and 2 cases in the control group, respectively; the difference was statistically significant. The rates of mucosal pressure injury were 4.7% and 21.4%, which was significantly different, and the experiment group had a lower average daily nursing cost related to tracheal intubation.

CONCLUSIONS

The new tracheal catheter fixation band, which allows for accurate fixation, is simple to operate, may reduce the incidence of mucosal pressure injury, decrease the nursing cost and improve the patients' comfort in clinical practice.

Validation of a Risk Assessment Tool for Unplanned Endotracheal Extubation: An Observational Study

The purpose of this study was to validate and determine the sensitivity and specificity of the risk assessment tool for unplanned endotracheal extubation. Unplanned endotracheal extubation is a common adverse event. The rate of unplanned endotracheal extubation is an indicator to measure patient safety and medical quality. This study was conducted in five intensive care units in a tertiary-A hospital. A total of 227 samples encounters were obtained from 147 unique patients. The content validity was 0.91, and the item content validity ranged from 0.80 to 1.00. Cronbach's α was .58, the interrater reliability was .93. The area under the curve was 0.89 (95% CI [0.84, 0.94], p < 0.01), the sensitivity was 87.80%, and the specificity was 74.20%. This tool presented good reliability and validity and can be used to assess the risk of unplanned endotracheal extubation in patients with artificial airways.

Risk Management In Intensive Care Units With Artificial Intelligence Technologies: Systematic Review of Prediction Models Using Electronic Health Records

Background and aim: Clinical risk assessments should be made to protect patients from negative outcomes, and the definition, frequency and severity of the risk should be determined. The information contained in the electronic health records (EHRs) can use in different areas such as risk prediction, estimation of treatment effect ect. Many prediction models using artificial intelligence (AI) technologies that can be used in risk assessment have been developed. The aim of this study is to bring together the researches on prediction models developed with AI technologies using the EHRs of patients hospitalized in the intensive care unit (ICU) and to evaluate them in terms of risk management in healthcare. Methods: The study restricted the search to the Web of Science, Pubmed, Science Direct, and Medline databases to retrieve research articles published in English in 2010 and after. Studies with a prediction model using data obtained from EHRs in the ICU are included. The study focused solely on research conducted in ICU to predict a health condition that poses a significant risk to patient safety using artificial intellegence (AI) technologies. Results: Recognized prediction subcategories were mortality (n=6), sepsis (n=4), pressure ulcer (n=4), acute kidney injury (n=3), and other areas (n=10). It has been found that EHR-based prediction models are good risk management and decision support tools and adoption of such models in ICUs may reduce the prevalence of adverse conditions. Conclusions: The article results remarks that developed models was found to have higher performance and better selectivity than previously developed risk models, so they are better at predicting risks and serious adverse events in ICU. It is recommended to use AI based prediction models developed using EHRs in risk management studies. Future work is still needed to researches to predict different health conditions risks.

Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Retrospective, Comparative, Machine Learning Study

Background

Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care.

Objective

This study aimed to develop and validate prediction models for UE in ICU patients using machine learning.

Methods

This study was conducted in an academic tertiary hospital in Seoul, Republic of Korea. The hospital had approximately 2000 inpatient beds and 120 ICU beds. As of January 2019, the hospital had approximately 9000 outpatients on a daily basis. The number of annual ICU admissions was approximately 10,000. We conducted a retrospective study between January 1, 2010, and December 31, 2018. A total of 6914 extubation cases were included. We developed a UE prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model’s performance, we used the area under the receiver operating characteristic curve (AUROC). The sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were also determined for each model. For performance evaluation, we also used a calibration curve, the Brier score, and the integrated calibration index (ICI) to compare different models. The potential clinical usefulness of the best model at the best threshold was assessed through a net benefit approach using a decision curve.

Results

Among the 6914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was higher during the night shift as compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality were higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.763, and for SVM was 0.740.

Conclusions

We successfully developed and validated machine learning–based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787 and the sensitivity was 0.949, which was obtained using the RF algorithm. The RF model was well-calibrated, and the Brier score and ICI were 0.129 and 0.048, respectively. The proposed prediction model uses widely available variables to limit the additional workload on the clinician. Further, this evaluation suggests that the model holds potential for clinical usefulness.

Derivation and Validation of an Ensemble Model for the Prediction of Agitation in Mechanically Ventilated Patients Maintained Under Light Sedation

OBJECTIVES

Light sedation is recommended over deep sedation for invasive mechanical ventilation to improve clinical outcome but may increase the risk of agitation. This study aimed to develop and prospectively validate an ensemble machine learning model for the prediction of agitation on a daily basis.

DESIGN

Variables collected in the early morning were used to develop an ensemble model by aggregating four machine learning algorithms including support vector machines, C5.0, adaptive boosting with classification trees, and extreme gradient boosting with classification trees, to predict the occurrence of agitation in the subsequent 24 hours.

SETTING

The training dataset was prospectively collected in 95 ICUs from 80 Chinese hospitals on May 11, 2016, and the validation dataset was collected in 20 out of these 95 ICUs on December 16, 2019.

PATIENTS

Invasive mechanical ventilation patients who were maintained under light sedation for 24 hours prior to the study day and who were to be maintained at the same sedation level for the next 24 hours.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

A total of 578 invasive mechanical ventilation patients from 95 ICUs in 80 Chinese hospitals, including 459 in the training dataset and 119 in the validation dataset, were enrolled. Agitation was observed in 36% (270/578) of the invasive mechanical ventilation patients. The stepwise regression model showed that higher body temperature (odds ratio for 1°C increase: 5.29; 95% CI, 3.70-7.84; p < 0.001), greater minute ventilation (odds ratio for 1 L/min increase: 1.15; 95% CI, 1.02-1.30; p = 0.019), higher Richmond Agitation-Sedation Scale (odds ratio for 1-point increase: 2.43; 95% CI, 1.92-3.16; p < 0.001), and days on invasive mechanical ventilation (odds ratio for 1-d increase: 0.95; 95% CI, 0.93-0.98; p = 0.001) were independently associated with agitation in the subsequent 24 hours. In the validation dataset, the ensemble model showed good discrimination (area under the receiver operating characteristic curve, 0.918; 95% CI, 0.866-0.969) and calibration (Hosmer-Lemeshow test p = 0.459) in predicting the occurrence of agitation within 24 hours.

CONCLUSIONS

This study developed an ensemble model for the prediction of agitation in invasive mechanical ventilation patients under light sedation. The model showed good calibration and discrimination in an independent dataset.

Improving Prediction of Fall Risk Using Electronic Health Record Data With Various Types and Sources at Multiple Times

Inpatient falls are among the most common adverse events threatening patient safety. Although many studies have developed predictive models for fall risk, there are some drawbacks. First, most previous studies have relied on an incident-reporting system alone to identify fall events. Thus, it has been found that falls are more likely to be underreported. Second, there has been a controversy on how to select accurate representative values for patient status data across multiple times and various data sources in electronic health records. Given this background, this study used nurses' progress notes as a complementary data source to detect fall events. In addition, we developed criteria including coverage, currency, and granularity in order to integrate electronic health records data documented at multiple times in various data types and sources. Based on this methodology, we developed three models, logistic regression, Cox proportional hazard regression, and decision tree, to predict risk of patient falls and evaluate the predictive performance of these models by comparing the results to results from the Hendrich II Fall Risk Model. The findings of this study will be used in a clinical decision support system to predict risk of falling and provide evidence-based tailored recommendations in the future.