Prediction and visualization of acute kidney injury in intensive care unit using one-dimensional convolutional neural networks based on routinely collected data

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.

Continuous Risk Estimation of Acute Kidney Failure with Dense Temporal Data for ICU Patients

Acute kidney failure is a dangerous complication for ICU patients, and it is difficult to identify at early stage with conventional medical analysis. In recent years, machine learning approaches have been applied to tackle medical diagnosis tasks with great performance. In this work, we deploy machine learning models for early detection of acute kidney failure that can handle static, temporal, sparse and dense data of ICU patients. We investigate different pre-processing methods for patient data to achieve higher prediction performance and how they influence the contribution of different physiological signals in the prediction process.

Bibliometric and visual analysis of machine learning-based research in acute kidney injury worldwide

Background

Acute kidney injury (AKI) is a serious clinical complication associated with adverse short-term and long-term outcomes. In recent years, with the rapid popularization of electronic health records and artificial intelligence machine learning technology, the detection rate and treatment of AKI have been greatly improved. At present, there are many studies in this field, and a large number of articles have been published, but we do not know much about the quality of research production in this field, as well as the focus and trend of current research.

Methods

Based on the Web of Science Core Collection, studies reporting machine learning-based AKI research that were published from 2013 to 2022 were retrieved and collected after manual review. VOSviewer and other software were used for bibliometric visualization analysis, including publication trends, geographical distribution characteristics, journal distribution characteristics, author contributions, citations, funding source characteristics, and keyword clustering.

Results

A total of 336 documents were analyzed. Since 2018, publications and citations have increased dramatically, with the United States (143) and China (101) as the main contributors. Regarding authors, Bihorac, A and Ozrazgat-Baslanti, T from the Kansas City Medical Center have published 10 articles. Regarding institutions, the University of California (18) had the most publications. Approximately 1/3 of the publications were published in Q1 and Q2 journals, of which Scientific Reports (19) was the most prolific journal. Tomašev et al.'s study that was published in 2019 has been widely cited by researchers. The results of cluster analysis of co-occurrence keywords suggest that the construction of AKI prediction model related to critical patients and sepsis patients is the research frontier, and XGBoost algorithm is also popular.

Conclusion

This study first provides an updated perspective on machine learning-based AKI research, which may be beneficial for subsequent researchers to choose suitable journals and collaborators and may provide a more convenient and in-depth understanding of the research basis, hotspots and frontiers.

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

Acute kidney injury (AKI) is a serious clinical comorbidity with clear short-term and long-term prognostic implications for inpatients. The diversity of risk factors for AKI has been recognized in previous studies, and a series of predictive models have been developed using traditional statistical methods in conjunction with its preventability, but they have failed to meet the expectations in limited clinical applications, the rapid spread of electronic health records and artificial intelligence machine learning technology has brought new hope for the construction of AKI prediction models. In this article, we systematically review the definition and classification of machine learning methods, modeling ideas and evaluation methods, and the characteristics and current status of modeling studies. According to the modeling objectives, we subdivided them into critical care medical setting models, all medical environment models, special surgery models, special disease models, and special nephrotoxin exposure models. As the first review article to comprehensively summarize and analyze machine learning prediction models for AKI, we aim to objectively describe the advantages and disadvantages of machine learning approaches to modeling, and help other researchers more quickly and intuitively understand the current status of modeling research, inspire ideas and learn from experience, so as to guide and stimulate more research and more in-depth exploration in the future, which will ultimately provide greater help to improve the overall status of AKI diagnosis and treatment.

Intelligent injury prediction for traumatic airway obstruction

Airway obstruction is one of the crucial causes of death in trauma patients during the first aid. It is extremely challenging to accurately treat a great deal of casualties with airway obstruction in hospitals. The diagnosis of airway obstruction in an emergency mostly relies on the medical experience of physicians. In this paper, we propose the feature selection approach genetic algorithm-mean decrease impurity (GA-MDI) to effectively minimize the number of features as well as ensure the accuracy of prediction. Furthermore, we design a multi-modal neural network, called fully convolutional network with squeeze-and-excitation and multilayer perceptron (FCN-SE + MLP), to help physicians to predict the severity of airway obstruction. We validate the effectiveness of the proposed feature selection approach and multi-modal model on the emergency medical database from the Chinese General Hospital of the PLA. The experimental results show that GA-MDI outperforms the existing feature selection algorithms, while it is also validated that the model FCN-SE + MLP can effectively and accurately achieve the prediction of the severity of airway obstruction, which can assist clinicians in making treatment decisions for airway obstruction casualties.

A time-aware attention model for prediction of acute kidney injury after pediatric cardiac surgery

OBJECTIVE

Acute kidney injury (AKI) is a common complication after pediatric cardiac surgery, and the early detection of AKI may allow for timely preventive or therapeutic measures. However, current AKI prediction researches pay less attention to time information among time-series clinical data and model building strategies that meet complex clinical application scenario. This study aims to develop and validate a model for predicting postoperative AKI that operates sequentially over individual time-series clinical data.

MATERIALS AND METHODS

A retrospective cohort of 3386 pediatric patients extracted from PIC database was used for training, calibrating, and testing purposes. A time-aware deep learning model was developed and evaluated from 3 clinical perspectives that use different data collection windows and prediction windows to answer different AKI prediction questions encountered in clinical practice. We compared our model with existing state-of-the-art models from 3 clinical perspectives using the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision-recall curve (PR AUC).

RESULTS

Our proposed model significantly outperformed the existing state-of-the-art models with an improved average performance for any AKI prediction from the 3 evaluation perspectives. This model predicted 91% of all AKI episodes using data collected at 24 h after surgery, resulting in a ROC AUC of 0.908 and a PR AUC of 0.898. On average, our model predicted 83% of all AKI episodes that occurred within the different time windows in the 3 evaluation perspectives. The calibration performance of the proposed model was substantially higher than the existing state-of-the-art models.

CONCLUSIONS

This study showed that a deep learning model can accurately predict postoperative AKI using perioperative time-series data. It has the potential to be integrated into real-time clinical decision support systems to support postoperative care planning.

Opportunities in digital health and electronic health records for acute kidney injury care

PURPOSE OF REVIEW

The field of digital health is evolving rapidly with applications relevant to the prediction, detection and management of acute kidney injury (AKI). This review will summarize recent publications in these areas.

RECENT FINDINGS

Machine learning (ML) approaches have been applied predominantly for AKI prediction, but also to identify patients with AKI at higher risk of adverse outcomes, and to discriminate different subgroups (subphenotypes) of AKI. There have been multiple publications in this area, but a smaller number of ML models have robust external validation or the ability to run in real-time in clinical systems. Recent studies of AKI alerting systems and clinical decision support systems continue to demonstrate variable results, which is likely to result from differences in local context and implementation strategies. In the design of AKI alerting systems, choice of baseline creatinine has a strong effect on performance of AKI detection algorithms.

SUMMARY

Further research is required to overcome barriers to the validation and implementation of ML models for AKI care. Simpler electronic systems within the electronic medical record can lead to improved care in some but not all settings, and careful consideration of local context and implementation strategy is recommended.

Use of proton pump inhibitors and macrolide antibiotics and risk of acute kidney injury: a self-controlled case series study

BACKGROUND

Proton pump inhibitors (PPIs) are widely used for the treatment of gastrointestinal disorders such as peptic ulcer disease and dyspepsia. However, several studies have suggested that PPI use increases the risk of acute kidney injury (AKI). PPIs are often concomitantly used with antibiotics, such as macrolides and penicillins for Helicobacter pylori eradication. Although macrolide antibiotics are considered to have relatively low nephrotoxicity, they are well known to increase the risk of AKI due to drug-drug interactions. In this study, we aimed to investigate the association between PPI use and the development of AKI. We also evaluated the effect of concomitant use of PPIs and macrolide antibiotics on the risk of AKI.

METHODS

This self-controlled case series study was conducted using electronic medical records at Kyoto University Hospital. We identified patients who were prescribed at least one PPI and macrolide antibiotic between January 2014 and December 2019 and underwent blood examinations at least once a year. An adjusted incident rate ratio (aIRR) of AKI with PPI use or concomitant use macrolide antibiotics with PPIs was estimated using a conditional Poisson regression model controlled for the estimated glomerular filtration rate at the beginning of observation and use of potentially nephrotoxic antibiotics.

RESULTS

Of the 3,685 individuals who received PPIs and macrolide antibiotics, 766 patients with episodes of stage 1 or higher AKI were identified. Any stage of AKI was associated with PPI use (aIRR, 1.80 (95% confidence interval (CI) 1.60 to 2.04)). Stage 2 or higher AKI was observed in 279 cases, with an estimated aIRR of 2.01 (95% CI 1.57 to 2.58, for PPI use). For the period of concomitant use of macrolide antibiotics with PPIs compared with the period of PPIs alone, an aIRR of stage 1 or higher AKI was estimated as 0.82 (95% CI 0.60 to 1.13).

CONCLUSIONS

Our findings added epidemiological information for the association between PPI use and an increased risk of stage 1 or higher AKI. However, we did not detect an association between the concomitant use of macrolide antibiotics and an increased risk of AKI in PPI users.

Explainable and efficient deep early warning system for cardiac arrest prediction from electronic health records

Cardiac arrest (CA) is a fatal acute event. The development of new CA early warning system based on time series of vital signs from electronic health records (EHR) has great potential to reduce CA damage. In this process, recursive architecture-based deep learning, as a powerful tool for time series data processing, enables automatically extract features from various monitoring clinical parameters and to further improve the performance for acute critical illness prediction. However, the unexplainable nature and excessive time caused by black box structure with poor parallelism are the limitations of its development, especially in the CA clinical application with strict requirement of emergency treatment and low hidden dangers. In this study, we present an explainable and efficient deep early warning system for CA prediction, which features are captured by an efficient temporal convolutional network (TCN) on EHR clinical parameters sequence and explained by deep Taylor decomposition (DTD) theoretical framework. To demonstrate the feasibility of our method and further evaluate its performance, prediction and explanation experiments were performed. Experimental results show that our method achieves superior CA prediction accuracy compared with standard national early warning score (NEWS), in terms of overall AUROC (0.850 Vs. 0.476) and F1-Score (0.750 Vs. 0.450). Furthermore, our method improves the interpretability and efficiency of deep learning-based CA early warning system. It provides the relevance of prediction results for each clinical parameter and about 1.7 times speed enhancement for system calculation compared with the long short-term memory network.

Account of Deep Learning-Based Ultrasonic Image Feature in the Diagnosis of Severe Sepsis Complicated with Acute Kidney Injury

This study was aimed at analyzing the diagnostic value of convolutional neural network models on account of deep learning for severe sepsis complicated with acute kidney injury and providing an effective theoretical reference for the clinical use of ultrasonic image diagnoses. 50 patients with severe sepsis complicated with acute kidney injury and 50 healthy volunteers were selected in this study. They all underwent ultrasound scans. Different deep learning convolutional neural network models dense convolutional network (DenseNet121), Google inception net (GoogLeNet), and Microsoft's residual network (ResNet) were used for training and diagnoses. Then, the diagnostic results were compared with professional image physicians' artificial diagnoses. The results showed that accuracy and sensitivity of the three deep learning algorithms were significantly higher than professional image physicians' artificial diagnoses. Besides, the error rates of the three algorithm models for severe sepsis complicated with acute kidney injury were significantly lower than professional physicians' artificial diagnoses. The areas under curves (AUCs) of the three algorithms were significantly higher than AUCs of doctors' diagnosis results. The loss function parameters of DenseNet121 and GoogLeNet were significantly lower than that of ResNet, with the statistically significant difference (P < 0.05). There was no significant difference in training time of ResNet, GoogLeNet, and DenseNet121 algorithms under deep learning, as the convergence was reached after 700 times, 700 times, and 650 times, respectively (P > 0.05). In conclusion, the value of the three algorithms on account of deep learning in the diagnoses of severe sepsis complicated with acute kidney injury was higher than professional physicians' artificial judgments and had great clinical value for the diagnoses and treatments of the disease.

Prediction of acute kidney injury in ICU with gradient boosting decision tree algorithms

PURPOSE

To predict acute kidney injury (AKI) in a large intensive care unit (ICU) database.

MATERIALS AND METHODS

A total of 30,020 ICU admissions with 17,222 AKI episodes were extracted from the Medical Information Mart from Intensive Care (MIMIC)-III database. These were randomly divided into a training set and an independent testing set in a ratio of 4:1. Data pertaining to demographics, admission information, vital signs, laboratory tests, critical illness scores, medications, comorbidities, and intervention measures were collected. Logistic regression, random forest, LightGBM, XGBoost, and an ensemble model was used for early prediction of AKI occurrence and important feature extraction. The SHAP analysis was adopted to reveal the impact of prediction for each feature.

RESULTS

The ensemble model had the best overall performance for predicting AKI before 24 h, 48 h and 72 h. The F1 values were 0.915, 0.893, and 0.878, respectively. AUCs were 0.923, 0.903, and 0.895, respectively.

CONCLUSIONS

Based on readily available electronic medical record (EMR) data, gradient boosting decision tree models are highly accurate at early AKI prediction in critically ill patients.

Advances in artificial intelligence and deep learning systems in ICU-related acute kidney injury

PURPOSE OF REVIEW

Acute kidney injury (AKI) affects nearly 60% of all patients admitted to ICUs. Large volumes of clinical, monitoring and laboratory data produced in ICUs allow the application of artificial intelligence analytics. The purpose of this article is to assimilate and critically evaluate recently published literature regarding artificial intelligence applications for predicting, diagnosing and subphenotyping AKI among critically ill patients.

RECENT FINDINGS

Among recent studies regarding artificial intelligence implementations for predicting, diagnosing and subphenotyping AKI among critically ill patients, there are many promising models, but few had external validation, clinical interpretability and high predictive performance. Deep learning techniques leveraging multimodal clinical data show great potential to provide continuous, accurate, early predictions of AKI risk, which could be implemented clinically to optimize preventive and early therapeutic management strategies.

SUMMARY

Use of consensus criteria, standard definitions and common data models could facilitate access to machine learning-ready data sets for external validation. The lack of interpretability, explainability, fairness and transparency of artificial intelligence models hinder their entrustment and clinical implementation; compliance with standardized reporting guidelines can mitigate these challenges.