Benchmarking machine learning models on multi-centre eICU critical care dataset

Short-term vital parameter forecasting in the intensive care unit: A benchmark study leveraging data from patients after cardiothoracic surgery

Patients in an Intensive Care Unit (ICU) are closely and continuously monitored, and many machine learning (ML) solutions have been proposed to predict specific outcomes like death, bleeding, or organ failure. Forecasting of vital parameters is a more general approach to ML-based patient monitoring, but the literature on its feasibility and robust benchmarks of achievable accuracy are scarce. We implemented five univariate statistical models (the naïve model, the Theta method, exponential smoothing, the autoregressive integrated moving average model, and an autoregressive single-layer neural network), two univariate neural networks (N-BEATS and N-HiTS), and two multivariate neural networks designed for sequential data (a recurrent neural network with gated recurrent unit, GRU, and a Transformer network) to produce forecasts for six vital parameters recorded at five-minute intervals during intensive care monitoring. Vital parameters were the diastolic, systolic, and mean arterial blood pressure, central venous pressure, peripheral oxygen saturation (measured by non-invasive pulse oximetry) and heart rate, and forecasts were made for 5 through 120 minutes into the future. Patients used in this study recovered from cardiothoracic surgery in an ICU. The patient cohort used for model development (n = 22,348) and internal testing (n = 2,483) originated from a heart center in Germany, while a patient sub-set from the eICU collaborative research database, an American multicenter ICU cohort, was used for external testing (n = 7,477). The GRU was the predominant method in this study. Uni- and multivariate neural network models proved to be superior to univariate statistical models across vital parameters and forecast horizons, and their advantage steadily became more pronounced for increasing forecast horizons. With this study, we established an extensive set of benchmarks for forecast performance in the ICU. Our findings suggest that supplying physicians with short-term forecasts of vital parameters in the ICU is feasible, and that multivariate neural networks are most suited for the task due to their ability to learn patterns across thousands of patients.

Multimodal fusion network for ICU patient outcome prediction

Over the past decades, massive Electronic Health Records (EHRs) have been accumulated in Intensive Care Unit (ICU) and many other healthcare scenarios. The rich and comprehensive information recorded presents an exceptional opportunity for patient outcome predictions. Nevertheless, due to the diversity of data modalities, EHRs exhibit a heterogeneous characteristic, raising a difficulty to organically leverage information from various modalities. It is an urgent need to capture the underlying correlations among different modalities. In this paper, we propose a novel framework named Multimodal Fusion Network (MFNet) for ICU patient outcome prediction. First, we incorporate multiple modality-specific encoders to learn different modality representations. Notably, a graph guided encoder is designed to capture underlying global relationships among medical codes, and a text encoder with pre-fine-tuning strategy is adopted to extract appropriate text representations. Second, we propose to pairwise merge multimodal representations with a tailored hierarchical fusion mechanism. The experiments conducted on the eICU-CRD dataset validate that MFNet achieves superior performance on mortality prediction and Length of Stay (LoS) prediction compared with various representative and state-of-the-art baselines. Moreover, comprehensive ablation study demonstrates the effectiveness of each component of MFNet.

Temporal-Spatial Correlation Attention Network for Clinical Data Analysis in Intensive Care Unit

Recent advancements in medical information technology have enabled electronic health records (EHRs) to store comprehensive clinical data which has ushered healthcare into the era of "big data". However, medical data are rather complicated, making problem-solving in healthcare be limited in scope and comprehensiveness. The rapid development of deep learning in recent years has opened up opportunities for leveraging big data in healthcare. In this article we introduce a temporal-spatial correlation attention network (TSCAN) to address various clinical characteristic prediction problems, including mortality prediction, length of stay prediction, physiologic decline detection, and phenotype classification. Leveraging the attention mechanism model's design, our approach efficiently identifies relevant items in clinical data and temporally correlated nodes based on specific tasks, resulting in improved prediction accuracy. Additionally, our method identifies crucial clinical indicators associated with significant outcomes, which can inform and enhance treatment options. Our experiments utilize data from the publicly accessible Medical Information Mart for Intensive Care (MIMIC-IV) database. Finally, our approach demonstrates notable performance improvements of 2.0% (metric) compared to other SOTA prediction methods. Specifically, we achieved an impressive 90.7% mortality rate prediction accuracy and 45.1% accuracy in length of stay prediction.

Safe and reliable transport of prediction models to new healthcare settings without the need to collect new labeled data

How can practitioners and clinicians know if a prediction model trained at a different institution can be safely used on their patient population? There is a large body of evidence showing that small changes in the distribution of the covariates used by prediction models may cause them to fail when deployed to new settings. This specific kind of dataset shift, known as covariate shift, is a central challenge to implementing existing prediction models in new healthcare environments. One solution is to collect additional labels in the target population and then fine tune the prediction model to adapt it to the characteristics of the new healthcare setting, which is often referred to as localization. However, collecting new labels can be expensive and time-consuming. To address these issues, we recast the core problem of model transportation in terms of uncertainty quantification, which allows one to know when a model trained in one setting may be safely used in a new healthcare environment of interest. Using methods from conformal prediction, we show how to transport models safely between different settings in the presence of covariate shift, even when all one has access to are covariates from the new setting of interest (e.g. no new labels). Using this approach, the model returns a prediction set that quantifies its uncertainty and is guaranteed to contain the correct label with a user-specified probability (e.g. 90%), a property that is also known as coverage. We show that a weighted conformal inference procedure based on density ratio estimation between the source and target populations can produce prediction sets with the correct level of coverage on real-world data. This allows users to know if a model's predictions can be trusted on their population without the need to collect new labeled data.

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

The core idea behind precision medicine is to pinpoint the subpopulations that differ from one another in terms of disease risk, drug responsiveness, and treatment outcomes due to differences in biology and other traits. Biomarkers are found through genomic sequencing. Multi-dimensional clinical and biological data are created using these biomarkers. Better analytic methods are needed for these multidimensional data, which can be accomplished by using artificial intelligence (AI). An updated review of 80 latest original publications is presented on four main fronts-preventive medicine, medication development, treatment outcomes, and diagnostic medicine-All these studies effectively illustrated the significance of AI in precision medicine. Artificial intelligence (AI) has revolutionized precision medicine by swiftly analyzing vast amounts of data to provide tailored treatments and predictive diagnostics. Through machine learning algorithms and high-resolution imaging, AI assists in precise diagnoses and early disease detection. AI's ability to decode complex biological factors aids in identifying novel therapeutic targets, allowing personalized interventions and optimizing treatment outcomes. Furthermore, AI accelerates drug discovery by navigating chemical structures and predicting drug-target interactions, expediting the development of life-saving medications. With its unrivaled capacity to comprehend and interpret data, AI stands as an invaluable tool in the pursuit of enhanced patient care and improved health outcomes. It's evident that AI can open a new horizon for precision medicine by translating complex data into actionable information. To get better results in this regard and to fully exploit the great potential of AI, further research is required on this pressing subject.

Introducing the BlendedICU dataset, the first harmonized, international intensive care dataset

OBJECTIVE

This study introduces the BlendedICU dataset, a massive dataset of international intensive care data. This dataset aims to facilitate generalizability studies of machine learning models, as well as statistical studies of clinical practices in the intensive care units.

METHODS

Four publicly available and patient-level intensive care databases were used as source databases. A unique and customizable preprocessing pipeline extracted clinically relevant patient-related variables from each source database. The variables were then harmonized and standardized to the Observational Medical Outcomes Partnership (OMOP) Common Data Format. Finally, a brief comparison was carried out to explore differences in the source databases.

RESULTS

The BlendedICU dataset features 41 timeseries variables as well as the exposure times to 113 active ingredients extracted from the AmsterdamUMCdb, eICU, HiRID, and MIMIC-IV databases. This resulted in a database of more than 309000 intensive care admissions, spanning over 13 years and three countries. We found that data collection, drug exposure, and patient outcomes varied strongly between source databases.

CONCLUSION

The variability in data collection, drug exposure, and patient outcomes between the source databases indicated some dissimilarity in patient phenotypes and clinical practices between different intensive care units. This demonstrated the need for generalizability studies of machine learning models. This study provides the clinical data research community with essential data to build efficient and generalizable machine learning models, as well as to explore clinical practices in intensive care units around the world.

Patients' Views on AI for Risk Prediction in Shared Decision-Making for Knee Replacement Surgery: Qualitative Interview Study

BACKGROUND

The use of artificial intelligence (AI) in decision-making around knee replacement surgery is increasing, and this technology holds promise to improve the prediction of patient outcomes. Ambiguity surrounds the definition of AI, and there are mixed views on its application in clinical settings.

OBJECTIVE

In this study, we aimed to explore the understanding and attitudes of patients who underwent knee replacement surgery regarding AI in the context of risk prediction for shared clinical decision-making.

METHODS

This qualitative study involved patients who underwent knee replacement surgery at a tertiary referral center for joint replacement surgery. The participants were selected based on their age and sex. Semistructured interviews explored the participants' understanding of AI and their opinions on its use in shared clinical decision-making. Data collection and reflexive thematic analyses were conducted concurrently. Recruitment continued until thematic saturation was achieved.

RESULTS

Thematic saturation was achieved with 19 interviews and confirmed with 1 additional interview, resulting in 20 participants being interviewed (female participants: n=11, 55%; male participants: n=9, 45%; median age: 66 years). A total of 11 (55%) participants had a substantial postoperative complication. Three themes captured the participants' understanding of AI and their perceptions of its use in shared clinical decision-making. The theme Expectations captured the participants' views of themselves as individuals with the right to self-determination as they sought therapeutic solutions tailored to their circumstances, needs, and desires, including whether to use AI at all. The theme Empowerment highlighted the potential of AI to enable patients to develop realistic expectations and equip them with personalized risk information to discuss in shared decision-making conversations with the surgeon. The theme Partnership captured the importance of symbiosis between AI and clinicians because AI has varied levels of interpretability and understanding of human emotions and empathy.

CONCLUSIONS

Patients who underwent knee replacement surgery in this study had varied levels of familiarity with AI and diverse conceptualizations of its definitions and capabilities. Educating patients about AI through nontechnical explanations and illustrative scenarios could help inform their decision to use it for risk prediction in the shared decision-making process with their surgeon. These findings could be used in the process of developing a questionnaire to ascertain the views of patients undergoing knee replacement surgery on the acceptability of AI in shared clinical decision-making. Future work could investigate the accuracy of this patient group's understanding of AI, beyond their familiarity with it, and how this influences their acceptance of its use. Surgeons may play a key role in finding a place for AI in the clinical setting as the uptake of this technology in health care continues to grow.

Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning

As models based on machine learning continue to be developed for healthcare applications, greater effort is needed to ensure that these technologies do not reflect or exacerbate any unwanted or discriminatory biases that may be present in the data. Here we introduce a reinforcement learning framework capable of mitigating biases that may have been acquired during data collection. In particular, we evaluated our model for the task of rapidly predicting COVID-19 for patients presenting to hospital emergency departments and aimed to mitigate any site (hospital)-specific and ethnicity-based biases present in the data. Using a specialized reward function and training procedure, we show that our method achieves clinically effective screening performances, while significantly improving outcome fairness compared with current benchmarks and state-of-the-art machine learning methods. We performed external validation across three independent hospitals, and additionally tested our method on a patient intensive care unit discharge status task, demonstrating model generalizability.

LGTRL-DE: Local and Global Temporal Representation Learning with Demographic Embedding for in-hospital mortality prediction

Predicting the patient's in-hospital mortality from the historical Electronic Medical Records (EMRs) can assist physicians to make clinical decisions and assign medical resources. In recent years, researchers proposed many deep learning methods to predict in-hospital mortality by learning patient representations. However, most of these methods fail to comprehensively learn the temporal representations and do not sufficiently mine the contextual knowledge of demographic information. We propose a novel end-to-end approach based on Local and Global Temporal Representation Learning with Demographic Embedding (LGTRL-DE) to address the current issues for in-hospital mortality prediction. LGTRL-DE is enabled by (1) a local temporal representation learning module that captures the temporal information and analyzes the health status from a local perspective through a recurrent neural network with the demographic initialization and the local attention mechanism; (2) a Transformer-based global temporal representation learning module that extracts the interaction dependencies among clinical events; (3) a multi-view representation fusion module that fuses temporal and static information and generates the final patient's health representations. We evaluate our proposed LGTRL-DE on two public real-world clinical datasets (MIMIC-III and e-ICU). Experimental results show that LGTRL-DE achieves an area under receiver operating characteristic curve of 0.8685 and 0.8733 on the MIMIC-III and e-ICU datasets, respectively, outperforming state-of-the-art approaches.

Algorithmic fairness in artificial intelligence for medicine and healthcare

In healthcare, the development and deployment of insufficiently fair systems of artificial intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models stratified across subpopulations have revealed inequalities in how patients are diagnosed, treated and billed. In this Perspective, we outline fairness in machine learning through the lens of healthcare, and discuss how algorithmic biases (in data acquisition, genetic variation and intra-observer labelling variability, in particular) arise in clinical workflows and the resulting healthcare disparities. We also review emerging technology for mitigating biases via disentanglement, federated learning and model explainability, and their role in the development of AI-based software as a medical device.

Integrating Structured and Unstructured EHR Data for Predicting Mortality by Machine Learning and Latent Dirichlet Allocation Method

An ICU is a critical care unit that provides advanced medical support and continuous monitoring for patients with severe illnesses or injuries. Predicting the mortality rate of ICU patients can not only improve patient outcomes, but also optimize resource allocation. Many studies have attempted to create scoring systems and models that predict the mortality of ICU patients using large amounts of structured clinical data. However, unstructured clinical data recorded during patient admission, such as notes made by physicians, is often overlooked. This study used the MIMIC-III database to predict mortality in ICU patients. In the first part of the study, only eight structured variables were used, including the six basic vital signs, the GCS, and the patient's age at admission. In the second part, unstructured predictor variables were extracted from the initial diagnosis made by physicians when the patients were admitted to the hospital and analyzed using Latent Dirichlet Allocation techniques. The structured and unstructured data were combined using machine learning methods to create a mortality risk prediction model for ICU patients. The results showed that combining structured and unstructured data improved the accuracy of the prediction of clinical outcomes in ICU patients over time. The model achieved an AUROC of 0.88, indicating accurate prediction of patient vital status. Additionally, the model was able to predict patient clinical outcomes over time, successfully identifying important variables. This study demonstrated that a small number of easily collectible structured variables, combined with unstructured data and analyzed using LDA topic modeling, can significantly improve the predictive performance of a mortality risk prediction model for ICU patients. These results suggest that initial clinical observations and diagnoses of ICU patients contain valuable information that can aid ICU medical and nursing staff in making important clinical decisions.

Privacy-preserving patient clustering for personalized federated learning

Federated Learning (FL) is a machine learning framework that enables multiple organizations to train a model without sharing their data with a central server. However, it experiences significant performance degradation if the data is non-identically independently distributed (non-IID). This is a problem in medical settings, where variations in the patient population contribute significantly to distribution differences across hospitals. Personalized FL addresses this issue by accounting for site-specific distribution differences. Clustered FL, a Personalized FL variant, was used to address this problem by clustering patients into groups across hospitals and training separate models on each group. However, privacy concerns remained as a challenge as the clustering process requires exchange of patient-level information. This was previously solved by forming clusters using aggregated data, which led to inaccurate groups and performance degradation. In this study, we propose Privacy-preserving Community-Based Federated machine Learning (PCBFL), a novel Clustered FL framework that can cluster patients using patient-level data while protecting privacy. PCBFL uses Secure Multiparty Computation, a cryptographic technique, to securely calculate patient-level similarity scores across hospitals. We then evaluate PCBFL by training a federated mortality prediction model using 20 sites from the eICU dataset. We compare the performance gain from PCBFL against traditional and existing Clustered FL frameworks. Our results show that PCBFL successfully forms clinically meaningful cohorts of low, medium, and high-risk patients. PCBFL outperforms traditional and existing Clustered FL frameworks with an average AUC improvement of 4.3% and AUPRC improvement of 7.8%.

Predicting length of stay in ICU and mortality with temporal dilated separable convolution and context-aware feature fusion

In healthcare, Intensive Care Unit (ICU) bed management is a necessary task because of the limited budget and resources. Predicting the remaining Length of Stay (LoS) in ICU and mortality can assist clinicians in managing ICU beds efficiently. This study proposes a deep learning method based on several successive Temporal Dilated Separable Convolution with Context-Aware Feature Fusion (TDSC-CAFF) modules, and a multi-view and multi-scale feature fusion for predicting the remaining LoS and mortality risk for ICU patients. In each TDSC-CAFF module, temporal dilated separable convolution is used to encode each feature separately, and context-aware feature fusion is proposed to capture comprehensive and context-aware feature representations from the input time-series features, static demographics, and the output of the last TDSC-CAFF module. The CAFF outputs of each module are accumulated to achieve multi-scale representations with different receptive fields. The outputs of TDSC and CAFF are concatenated with skip connection from the output of the last module and the original time-series input. The concatenated features are processed by the proposed Point-Wise convolution-based Attention (PWAtt) that captures the inter-feature context to generate the final temporal features. Finally, the final temporal features, the accumulated multi-scale features, the encoded diagnosis, and static demographic features are fused and then processed by fully connected layers to obtain prediction results. We evaluate our proposed method on two publicly available datasets: eICU and MIMIC-IV v1.0 for LoS and mortality prediction tasks. Experimental results demonstrate that our proposed method achieves a mean squared log error of 0.07 and 0.08 for LoS prediction, and an Area Under the Receiver Operating Characteristic Curve of 0.909 and 0.926 for mortality prediction, on eICU and MIMIC-IV v1.0 datasets, respectively, which outperforms several state-of-the-art methods.

E-CatBoost: An efficient machine learning framework for predicting ICU mortality using the eICU Collaborative Research Database

Improving the Intensive Care Unit (ICU) management network and building cost-effective and well-managed healthcare systems are high priorities for healthcare units. Creating accurate and explainable mortality prediction models helps identify the most critical risk factors in the patients' survival/death status and early detect the most in-need patients. This study proposes a highly accurate and efficient machine learning model for predicting ICU mortality status upon discharge using the information available during the first 24 hours of admission. The most important features in mortality prediction are identified, and the effects of changing each feature on the prediction are studied. We used supervised machine learning models and illness severity scoring systems to benchmark the mortality prediction. We also implemented a combination of SHAP, LIME, partial dependence, and individual conditional expectation plots to explain the predictions made by the best-performing model (CatBoost). We proposed E-CatBoost, an optimized and efficient patient mortality prediction model, which can accurately predict the patients' discharge status using only ten input features. We used eICU-CRD v2.0 to train and validate the models; the dataset contains information on over 200,000 ICU admissions. The patients were divided into twelve disease groups, and models were fitted and tuned for each group. The models' predictive performance was evaluated using the area under a receiver operating curve (AUROC). The AUROC scores were 0.86 [std:0.02] to 0.92 [std:0.02] for CatBoost and 0.83 [std:0.02] to 0.91 [std:0.03] for E-CatBoost models across the defined disease groups; if measured over the entire patient population, their AUROC scores were 7 to 18 and 2 to 12 percent higher than the baseline models, respectively. Based on SHAP explanations, we found age, heart rate, respiratory rate, blood urine nitrogen, and creatinine level as the most critical cross-disease features in mortality predictions.

A comparison of approaches to improve worst-case predictive model performance over patient subpopulations

Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations, potentially introducing or reinforcing inequities in care access and quality. Model training approaches that aim to maximize worst-case model performance across subpopulations, such as distributionally robust optimization (DRO), attempt to address this problem without introducing additional harms. We conduct a large-scale empirical study of DRO and several variations of standard learning procedures to identify approaches for model development and selection that consistently improve disaggregated and worst-case performance over subpopulations compared to standard approaches for learning predictive models from electronic health records data. In the course of our evaluation, we introduce an extension to DRO approaches that allows for specification of the metric used to assess worst-case performance. We conduct the analysis for models that predict in-hospital mortality, prolonged length of stay, and 30-day readmission for inpatient admissions, and predict in-hospital mortality using intensive care data. We find that, with relatively few exceptions, no approach performs better, for each patient subpopulation examined, than standard learning procedures using the entire training dataset. These results imply that when it is of interest to improve model performance for patient subpopulations beyond what can be achieved with standard practices, it may be necessary to do so via data collection techniques that increase the effective sample size or reduce the level of noise in the prediction problem.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

BACKGROUND

The term "data science" encompasses several methods, many of which are considered cutting edge and are being used to influence care processes across the world. Nursing is an applied science and a key discipline in health care systems in both clinical and administrative areas, making the profession increasingly influenced by the latest advances in data science. The greater informatics community should be aware of current trends regarding the intersection of nursing and data science, as developments in nursing practice have cross-professional implications.

OBJECTIVES

This study aimed to summarize the latest (calendar year 2020) research and applications of nursing-relevant patient outcomes and clinical processes in the data science literature.

METHODS

We conducted a rapid review of the literature to identify relevant research published during the year 2020. We explored the following 16 topics: (1) artificial intelligence/machine learning credibility and acceptance, (2) burnout, (3) complex care (outpatient), (4) emergency department visits, (5) falls, (6) health care-acquired infections, (7) health care utilization and costs, (8) hospitalization, (9) in-hospital mortality, (10) length of stay, (11) pain, (12) patient safety, (13) pressure injuries, (14) readmissions, (15) staffing, and (16) unit culture.

RESULTS

Of 16,589 articles, 244 were included in the review. All topics were represented by literature published in 2020, ranging from 1 article to 59 articles. Numerous contemporary data science methods were represented in the literature including the use of machine learning, neural networks, and natural language processing.

CONCLUSION

This review provides an overview of the data science trends that were relevant to nursing practice in 2020. Examinations of such literature are important to monitor the status of data science's influence in nursing practice.

Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning

Background: Acute respiratory distress syndrome (ARDS) is an intense inflammatory process of the lungs. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated the prediction of MV duration over time. We aimed at characterizing the best early scenario during the first two days in the intensive care unit (ICU) to predict MV duration after ARDS onset using supervised machine learning (ML) approaches. Methods: For model description, we extracted data from the first 3 ICU days after ARDS diagnosis from patients included in the publicly available MIMIC-III database. Disease progression was tracked along those 3 ICU days to assess lung severity according to Berlin criteria. Three robust supervised ML techniques were implemented using Python 3.7 (Light Gradient Boosting Machine (LightGBM); Random Forest (RF); and eXtreme Gradient Boosting (XGBoost)) for predicting MV duration. For external validation, we used the publicly available multicenter database eICU. Results: A total of 2466 and 5153 patients in MIMIC-III and eICU databases, respectively, received MV for >48 h. Median MV duration of extracted patients was 6.5 days (IQR 4.4–9.8 days) in MIMIC-III and 5.0 days (IQR 3.0–9.0 days) in eICU. LightGBM was the best model in predicting MV duration after ARDS onset in MIMIC-III with a root mean square error (RMSE) of 6.10–6.41 days, and it was externally validated in eICU with RMSE of 5.87–6.08 days. The best early prediction model was obtained with data captured in the 2nd day. Conclusions: Supervised ML can make early and accurate predictions of MV duration in ARDS after onset over time across ICUs. Supervised ML models might have important implications for optimizing ICU resource utilization and high acute cost reduction of MV.

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

BACKGROUND

Mechanical Ventilation (MV) is a complex and central treatment process in the care of critically ill patients. It influences acid-base balance and can also cause prognostically relevant biotrauma by generating forces and liberating reactive oxygen species, negatively affecting outcomes. In this work we evaluate the use of a Recurrent Neural Network (RNN) modelling to predict outcomes of mechanically ventilated patients, using standard mechanical ventilation parameters.

METHODS

We performed our analysis on VENTILA dataset, an observational, prospective, international, multi-centre study, performed to investigate the effect of baseline characteristics and management changes over time on the all-cause mortality rate in mechanically ventilated patients in ICU. Our cohort includes 12,596 adult patients older than 18, associated with 12,755 distinct admissions in ICUs across 37 countries and receiving invasive and non-invasive mechanical ventilation. We carry out four different analysis. Initially we select typical mechanical ventilation parameters and evaluate the machine learning model on both, the overall cohort and a subgroup of patients admitted with respiratory disorders. Furthermore, we carry out sensitivity analysis to evaluate whether inclusion of variables related to the function of other organs, improve the predictive performance of the model for both the overall cohort as well as the subgroup of patients with respiratory disorders.

RESULTS

Predictive performance of RNN-based model was higher with Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.72 (± 0.01) and Average Precision (AP) of 0.57 (± 0.01) in comparison to RF and LR for the overall patient dataset. Higher predictive performance was recorded in the subgroup of patients admitted with respiratory disorders with AUC of 0.75 (± 0.02) and AP of 0.65 (± 0.03). Inclusion of function of other organs further improved the performance to AUC of 0.79 (± 0.01) and AP 0.68 (± 0.02) for the overall patient dataset and AUC of 0.79 (± 0.01) and AP 0.72 (± 0.02) for the subgroup with respiratory disorders.

CONCLUSION

The RNN-based model demonstrated better performance than RF and LR in patients in mechanical ventilation and its subgroup admitted with respiratory disorders. Clinical studies are needed to evaluate whether it impacts decision-making and patient outcomes.

TRIAL REGISTRATION

NCT02731898 ( https://clinicaltrials.gov/ct2/show/NCT02731898 ), prospectively registered on April 8, 2016.