Dataset Information

A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation.

ABSTRACT:

Background

Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease.

Objective

Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department.

Methods

Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics.

Results

The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics.

Conclusions

The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19.

SUBMITTER: Bolourani S

PROVIDER: S-EPMC7879728 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation.

Bolourani Siavash S Brenner Max M Wang Ping P McGinn Thomas T Hirsch Jamie S JS Barnaby Douglas D Zanos Theodoros P TP

Journal of medical Internet research 20210210 2

<h4>Background</h4>Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease.<h4>Objective</h4>Our objective is to derive a machine learning model that predicts respiratory ...[more]

PMID: 33476281

Similar Datasets

Project description:BackgroundClose to 1 in 5 patients admitted to a skilled nursing facility (SNF) are readmitted to the acute hospital within 30 days, and a substantial percentage are readmitted within 2 days of the SNF admission. These rapid returns to the hospital may provide insights for improving care transitions between the acute hospital and the SNF.ObjectivesTo describe the characteristics of SNF to hospital transfers that occur within 48 hours and 30 days of SNF admission based on root cause analyses (RCAs) performed by SNF staff, and identify potential areas of focus for improving transitions between hospitals and SNFs.DesignTrained staff from SNFs enrolled in a randomized, controlled clinical trial of the INTERACT (Interventions to Reduce Acute Care Transfers) quality improvement program performed retrospective RCAs on hospital transfers during a 12-month implementation period.SettingSNFs from across the United States.Participants64 of 88 SNFs randomized to the intervention group submitted RCAs.InterventionsSNFs were implementing the INTERACT quality improvement program.MeasuresData were abstracted from the INTERACT Quality Improvement (QI) tool, a structured, retrospective RCA on hospital transfers.ResultsAmong 4658 transfers for which data on the time between SNF admission and hospital transfer were available, 353 (8%) occurred within 48 hours of SNF admission, 524 (11%) 3 to 6 days after SNF admission, 1450 (31%) 7 to 29 days after SNF admission, and 2331 (50%) occurred 30 days or longer after admission. Comparisons between transfers that occurred within 48 hours and within 30 days of SNF admission to transfers that occurred 30 days or longer after SNF admission revealed several statistically significant differences between patient risk factors for transfer, symptoms and signs precipitating the transfers, and other characteristics of the transfers. Hospitalization in the last 30 days and year was significantly more common among those with rapid returns to the hospital. Shortness of breath was significantly more common among those transferred within 48 hours or 30 days, and falls, functional decline, suspected respiratory infection, and new urinary incontinence less common. SNF staff rated a higher proportion of transfers within 30 days versus 30 days or longer as potentially preventable (25.1% vs 21.5%, P = .005). Case descriptions derived from the QI tools of transfers back to the hospital within 48 hours of SNF admission illustrate several factors underlying these rapid returns to the hospital.ConclusionRCAs on transfers back to the hospital shortly after SNF admission provide insights into strategies that both hospitals and SNFs can consider in collaborative efforts to reduce potentially avoidable hospital readmissions.

Project description:BackgroundThere is no generalizable transcriptomics signature of pediatric acute respiratory distress syndrome. Our goal was to identify a whole blood differential gene expression signature for pediatric acute hypoxemic respiratory failure (AHRF) using transcriptomic microarrays within twenty-four hours of diagnosis. We used publicly available human whole-blood gene expression arrays of a Berlin-defined pediatric acute respiratory distress syndrome (GSE147902) cohort and a sepsis-triggered AHRF (GSE66099) cohort within twenty-four hours of diagnosis and compared those children with a PaO2/FiO2 < 200 to those with a PaO2/FiO2 ≥ 200.ResultsWe used stability selection, a bootstrapping method of 100 simulations using logistic regression as a classifier, to select differentially expressed genes associated with a PaO2/FiO2 < 200 vs. PaO2/FiO2 ≥ 200. The top-ranked genes that contributed to the AHRF signature were selected in each dataset. Genes common to both of the top 1,500 ranked gene lists were selected for pathway analysis. Pathway and network analysis was performed using the Pathway Network Analysis Visualizer (PANEV) and Reactome was used to perform an over-representation gene network analysis of the top-ranked genes common to both cohorts. Changes in metabolic pathways involved in energy balance, fundamental cellular processes such as protein translation, mitochondrial function, oxidative stress, immune signaling, and inflammation are differentially regulated early in pediatric ARDS and sepsis-induced AHRF compared to both healthy controls and to milder acute hypoxemia. Specifically, fundamental pathways related to the severity of hypoxemia emerged and included (1) ribosomal and eukaryotic initiation of factor 2 (eIF2) regulation of protein translation and (2) the nutrient, oxygen, and energy sensing pathway, mTOR, activated via PI3K/AKT signaling.ConclusionsCellular energetics and metabolic pathways are important mechanisms to consider to further our understanding of the heterogeneity and underlying pathobiology of moderate and severe pediatric acute respiratory distress syndrome. Our findings are hypothesis generating and support the study of metabolic pathways and cellular energetics to understand heterogeneity and underlying pathobiology of moderate and severe acute hypoxemic respiratory failure in children.

Project description:BackgroundNoninvasive ventilation (NIV) has been widely used in critically ill patients after extubation. However, NIV failure is associated with poor outcomes. This study aimed to determine early predictors of NIV failure and to construct an accurate machine-learning model to identify patients at risks of NIV failure after extubation in intensive care units (ICUs).MethodsPatients who underwent NIV after extubation in the eICU Collaborative Research Database (eICU-CRD) were included. NIV failure was defined as need for invasive ventilatory support (reintubation or tracheotomy) or death after NIV initiation. A total of 93 clinical and laboratory variables were assessed, and the recursive feature elimination algorithm was used to select key features. Hyperparameter optimization was conducted with an automated machine-learning toolkit called Neural Network Intelligence. A machine-learning model called Categorical Boosting (CatBoost) was developed and compared with nine other models. The model was then prospectively validated among patients enrolled in the Cardiac Surgical ICU of Zhongshan Hospital, Fudan University.ResultsOf 929 patients included in the eICU-CRD cohort, 248 (26.7%) had NIV failure. The time from extubation to NIV, age, Glasgow Coma Scale (GCS) score, heart rate, respiratory rate, mean blood pressure (MBP), saturation of pulse oxygen (SpO2), temperature, glucose, pH, pressure of oxygen in blood (PaO2), urine output, input volume, ventilation duration, and mean airway pressure were selected. After hyperparameter optimization, our model showed the greatest accuracy in predicting NIV failure (AUROC: 0.872 [95% CI 0.82-0.92]) among all predictive methods in an internal validation. In the prospective validation cohort, our model was also superior (AUROC: 0.846 [95% CI 0.80-0.89]). The sensitivity and specificity in the prediction group is 89% and 75%, while in the validation group they are 90% and 70%. MV duration and respiratory rate were the most important features. Additionally, we developed a web-based tool to help clinicians use our model.ConclusionsThis study developed and prospectively validated the CatBoost model, which can be used to identify patients who are at risk of NIV failure. Thus, those patients might benefit from early triage and more intensive monitoring.Trial registrationNCT03704324. Registered 1 September 2018, https://register.Clinicaltrialsgov .

Dataset Information

A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation.

Background

Objective

Methods

Results

Conclusions

Publications

A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets