Features Derived From Blood Pressure Predict Elevated Intracranial Pressure in Critically Ill Children (original) (raw)
Related papers
Scientific Reports
Clinicians frequently observe hemodynamic changes preceding elevated intracranial pressure events. We employed a machine learning approach to identify novel and differentially expressed features associated with elevated intracranial pressure events in children with severe brain injuries. Statistical features from physiologic data streams were derived from non-overlapping 30-min analysis windows prior to 21 elevated intracranial pressure events; 200 records without elevated intracranial pressure events were used as controls. Ten Monte Carlo simulations with training/testing splits provided performance benchmarks for 4 machine learning approaches. XGBoost yielded the best performing predictive models. Shapley Additive Explanations analyses demonstrated that a majority of the top 20 contributing features consistently derived from blood pressure data streams up to 240 min prior to elevated intracranial events. The best performing prediction model was using the 30–60 min analysis window;...
Critical Care Medicine, 2013
Objective: Intracranial pressure monitoring is standard of care after severe traumatic brain injury. Episodes of increased intracranial pressure are secondary injuries associated with poor outcome. We developed a model to predict increased intracranial pressure episodes 30 mins in advance, by using the dynamic characteristics of continuous intracranial pressure and mean arterial pressure monitoring. In addition, we hypothesized that performance of current models to predict longterm neurological outcome could be substantially improved by adding dynamic characteristics of continuous intracranial pressure and mean arterial pressure monitoring during the first 24 hrs in the ICU. Design: Prognostic modeling. Noninterventional, observational, retrospective study. Setting and Patients: The Brain Monitoring with Information Technology dataset consisted of 264 traumatic brain injury patients admitted to 22 neuro-ICUs from 11 European countries. Interventions: None. Measurements: Predictive models were built with multivariate logistic regression and Gaussian processes, a machine learning technique. Predictive attributes were Corticosteroid Randomisation After Significant Head Injury-basic and International Mission for Prognosis and Clinical Trial design in TBI-core predictors, together with time-series summary statistics of minute-by-minute mean arterial pressure and intracranial pressure.
Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients
IEEE Journal of Translational Engineering in Health and Medicine
Structured Abstract-Objective: Abnormal elevation of intracranial pressure (ICP) can cause dangerous or even fatal outcomes. The early detection of high intracranial pressure events can be crucial in saving lives in an intensive care unit (ICU). Despite many applications of machine learning (ML) techniques related to clinical diagnosis, ML applications for continuous ICP detection or short-term predictions have been rarely reported. This study proposes an efficient method of applying an artificial recurrent neural network on the early prediction of ICP evaluation continuously for TBI patients. Methods: After ICP data preprocessing, the learning model is generated for thirteen patients to continuously predict the ICP signal occurrence and classify events for the upcoming 10 minutes by inputting the previous 20-minutes of the ICP signal. Results: As the overall model performance, the average accuracy is 94.62%, the average sensitivity is 74.91%, the average specificity is 94.83%, and the average root mean square error is approximately 2.18 mmHg. Conclusion: This research addresses a significant clinical problem with the management of traumatic brain injury patients. The machine learning model data enables early prediction of ICP continuously in a real-time fashion, which is crucial for appropriate clinical interventions. The results show that our machine learning-based model has high adaptive performance, accuracy, and efficiency. INDEX TERMS Computer-assisted decision making, intracranial pressure, intracranial hypertension, machine learning, traumatic brain injury. Clinical and Translational Impact Statement-Continuous detection of short-term future high ICP incidents might help save lives of TBI patients. The detection algorithm can also be integrated into infusion pumps for automated intravenous injection treatments.
2021
Background: Traumatic brain injury (TBI) causes temporary or permanent alteration in brain functions. Generally, at intensive care units (ICU), intracranial pressure (ICP) is monitored and treated to avoid increases in ICP with associated secondary insults and poor clinical outcome. The aim of this study was to develop and evaluate a model which could predict future ICP levels of individual patients during their treatment in the ICU, and thus help the treating clinician to take proper actions before secondary injuries occure. Methods: A simple, explainable, probabilistic Markov model was developed for the prediction task of ICP≥20 mmHg. Predictions were made for consecutive 10-minute intervals during the following hour, based on the preceding hour of ICP data. An easily implementable enhancement method was also developed and applied to compensate for imbalance in the data. The model was evaluated in a randomized and leave-one-out fashion on data from 29 patients with severe TBI. Res...
Early prediction of hemodynamic interventions in the intensive care unit using machine learning
Critical Care, 2021
Background Timely recognition of hemodynamic instability in critically ill patients enables increased vigilance and early treatment opportunities. We develop the Hemodynamic Stability Index (HSI), which highlights situational awareness of possible hemodynamic instability occurring at the bedside and to prompt assessment for potential hemodynamic interventions. Methods We used an ensemble of decision trees to obtain a real-time risk score that predicts the initiation of hemodynamic interventions an hour into the future. We developed the model using the eICU Research Institute (eRI) database, based on adult ICU admissions from 2012 to 2016. A total of 208,375 ICU stays met the inclusion criteria, with 32,896 patients (prevalence = 18%) experiencing at least one instability event where they received one of the interventions during their stay. Predictors included vital signs, laboratory measurements, and ventilation settings. Results HSI showed significantly better performance compared ...
Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model
American Journal of Critical Care, 2018
Background Hospital-acquired pressure injuries are a serious problem among critical care patients. Some can be prevented by using measures such as specialty beds, which are not feasible for every patient because of costs. However, decisions about which patient would benefit most from a specialty bed are difficult because results of existing tools to determine risk for pressure injury indicate that most critical care patients are at high risk. Objective To develop a model for predicting development of pressure injuries among surgical critical care patients. Methods Data from electronic health records were divided into training (67%) and testing (33%) data sets, and a model was developed by using a random forest algorithm via the R package "randomforest. " Results Among a sample of 6376 patients, hospital-acquired pressure injuries of stage 1 or greater (outcome variable 1) developed in 516 patients (8.1%) and injuries of stage 2 or greater (outcome variable 2) developed in 257 (4.0%). Random forest models were developed to predict stage 1 and greater and stage 2 and greater injuries by using the testing set to evaluate classifier performance. The area under the receiver operating characteristic curve for both models was 0.79. Conclusion This machine-learning approach differs from other available models because it does not require clinicians to input information into a tool (eg, the Braden Scale). Rather, it uses information readily available in electronic health records. Next steps include testing in an independent sample and then calibration to optimize specificity.
Modeling and prediction of pressure injury in hospitalized patients using artificial intelligence
BMC Medical Informatics and Decision Making
BackgroundHospital-acquired pressure injuries (PIs) induce significant patient suffering, inflate healthcare costs, and increase clinical co-morbidities. PIs are mostly due to bed-immobility, sensory impairment, bed positioning, and length of hospital stay. In this study, we use electronic health records and administrative data to examine the contributing factors to PI development using artificial intelligence (AI).MethodsWe used advanced data science techniques to first preprocess the data and then train machine learning classifiers to predict the probability of developing PIs. The AI training was based on large, incongruent, incomplete, heterogeneous, and time-varying data of hospitalized patients. Both model-based statistical methods and model-free AI strategies were used to forecast PI outcomes and determine the salient features that are highly predictive of the outcomes.ResultsOur findings reveal that PI prediction by model-free techniques outperform model-based forecasts. The ...
Neurotrauma reports, 2022
The current approach to intracranial hypertension and brain tissue hypoxia is reactive, based on fixed thresholds. We used statistical machine learning on high-frequency intracranial pressure (ICP) and partial brain tissue oxygen tension (PbtO 2) data obtained from the BOOST-II trial with the goal of constructing robust quantitative models to predict ICP/PbtO 2 crises. We derived the following machine learning models: logistic regression (LR), elastic net, and random forest. We split the data set into 70-30% for training and testing and utilized a discrete-time survival analysis framework and 5-fold hyperparameter optimization strategy for all models. We compared model performances on discrimination between events and non-events of increased ICP or low PbtO 2 with the area under the receiver operating characteristic (AUROC) curve. We further analyzed clinical utility through a decision curve analysis (DCA). When considering discrimination, the number of features, and interpretability, we identified the RF model that combined the most recent ICP reading, episode number, and longitudinal trends over the preceding 30 min as the best performing for predicting ICP crisis events within the next 30 min (AUC 0.78). For PbtO 2 , the LR model utilizing the most recent reading, episode number, and longitudinal trends over the preceding 30 min was the best performing (AUC, 0.84). The DCA showed clinical usefulness for wide risk of thresholds for both ICP and PbtO 2 predictions. Acceptable alerting thresholds could range from 20% to 80% depending on a patientspecific assessment of the benefit-risk ratio of a given intervention in response to the alert.
Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features
Military Medicine, 2021
Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in te...
A Computational Model to Predict Brain Trauma Outcome in the Intensive Care Unit
medRxiv, 2020
Objectives: To predict short-term outcomes of critically ill patients with traumatic brain injury (TBI) by training machine learning classifiers on two large intensive care databases Design: Retrospective analysis of observational data. Patients: Patients in the multicenter Philips eICU and single-center Medical Information Mart for Intensive Care-III (MIMIC-III) databases with a primary admission diagnosis of TBI, who were in intensive care for >24h. Interventions: None. Measurements and Main Results: We identified 1,689 and 126 qualifying TBI patients in eICU and MIMIC-III, respectively. Generalized Linear Models were used to predict mortality and neurological function at ICU discharge using features derived from clinical, laboratory, medication and physiological time series data obtained in the first 24 hours after ICU admission. Models were trained, tested and validated in eICU then validated externally in MIMIC-III. Model discrimination determined by area under the receiver ...