scholarly journals A novel model to label delirium in an intensive care unit from clinician actions

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Caitlin E. Coombes ◽  
Kevin R. Coombes ◽  
Naleef Fareed
Keyword(s):  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Goodness Of Fit ◽  
Prediction Models ◽  
Support Vector ◽  
Data Set ◽  
Biological Validation ◽  
Public Data ◽  
Electronic Health

Abstract Background In the intensive care unit (ICU), delirium is a common, acute, confusional state associated with high risk for short- and long-term morbidity and mortality. Machine learning (ML) has promise to address research priorities and improve delirium outcomes. However, due to clinical and billing conventions, delirium is often inconsistently or incompletely labeled in electronic health record (EHR) datasets. Here, we identify clinical actions abstracted from clinical guidelines in electronic health records (EHR) data that indicate risk of delirium among intensive care unit (ICU) patients. We develop a novel prediction model to label patients with delirium based on a large data set and assess model performance. Methods EHR data on 48,451 admissions from 2001 to 2012, available through Medical Information Mart for Intensive Care-III database (MIMIC-III), was used to identify features to develop our prediction models. Five binary ML classification models (Logistic Regression; Classification and Regression Trees; Random Forests; Naïve Bayes; and Support Vector Machines) were fit and ranked by Area Under the Curve (AUC) scores. We compared our best model with two models previously proposed in the literature for goodness of fit, precision, and through biological validation. Results Our best performing model with threshold reclassification for predicting delirium was based on a multiple logistic regression using the 31 clinical actions (AUC 0.83). Our model out performed other proposed models by biological validation on clinically meaningful, delirium-associated outcomes. Conclusions Hurdles in identifying accurate labels in large-scale datasets limit clinical applications of ML in delirium. We developed a novel labeling model for delirium in the ICU using a large, public data set. By using guideline-directed clinical actions independent from risk factors, treatments, and outcomes as model predictors, our classifier could be used as a delirium label for future clinically targeted models.

scholarly journals Intelligent Management of Sepsis in the Intensive Care Unit

2012 ◽  
pp. 1-16
Author(s):  
Vicent J. Ribas ◽  
Juan Carlos Ruiz-Rodríguez ◽  
Alfredo Vellido
Keyword(s):  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Support Vector ◽  
Clinical Settings ◽  
Svm Model ◽  
Intelligent Management ◽  
Alternative Techniques ◽  
Research Challenge ◽  
Mortality Predictors

Sepsis is a transversal pathology and one of the main causes of death in the Intensive Care Unit (ICU). It has in fact become the tenth most common cause of death in western societies. Its mortality rates can reach up to 60% for Septic Shock, its most acute manifestation. For these reasons, the prediction of the mortality caused by Sepsis is an open and relevant medical research challenge. This problem requires prediction methods that are robust and accurate, but also readily interpretable. This is paramount if they are to be used in the demanding context of real-time decision making at the ICU. In this brief contribution, three different methods are presented. One is based on a variant of the well-known support vector machine (SVM) model and provides and automated ranking of relevance of the mortality predictors while the other two are based on logistic-regression and logistic regression over latent Factors. The reported results show that the methods presented outperform in terms of accuracy alternative techniques currently in use in clinical settings, while simultaneously assessing the relative impact of individual pathology indicators.

scholarly journals Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Comparative Machine Learning Study (Preprint)

2020 ◽  
Author(s):  
Sujeong Hur ◽  
Ji Young Min ◽  
Junsang Yoo ◽  
Kyunga Kim ◽  
Chi Ryang Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Patient Safety ◽  
Intensive Care ◽  
Predictive Value ◽  
Prediction Models ◽  
Support Vector ◽  
Unplanned Extubation ◽  
Electronic Health Record Data ◽  
Icu Patients

BACKGROUND Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered as 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 an academic tertiary hospital in Seoul. The hospital had approximately 2,000 inpatient beds and 120 intensive care unit (ICU) beds. The number of patients, on daily basis, was approximately 9,000 for the out-patient. The number of annual ICU admission was approximately 10,000. We conducted a retrospective study between January 1, 2010 and December 31, 2018. A total of 6,914 extubation cases were included. We developed an unplanned extubation 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 area under the receiver operator characteristic curve (AUROC). Sensitivity, specificity, positive predictive value negative predictive value, and F1-score were also determined for each model. For performance evaluation, we also used calibration curve, the Brier score, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS Among the 6,914 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 more likely to occur during the night shift compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality was 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 0.762, 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, which was obtained using RF. CLINICALTRIAL N/A

scholarly journals Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1866 ◽  
Author(s):  
Liao ◽  
Wang ◽  
Zhang ◽  
Abbod ◽  
Shih ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Pseudomonas Aeruginosa ◽  
Intensive Care ◽  
Prediction Models ◽  
Support Vector ◽  
Ventilator Associated Pneumonia ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Pseudomonas Aeruginosa Infection

One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients’ data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models’ performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.

scholarly journals Novel Method of Atrial Fibrillation Case Identification and Burden Estimation Using the MIMIC-III Electronic Health Data Set

2019 ◽  
Vol 34 (10) ◽  
pp. 851-857 ◽  
Author(s):  
Eric Y. Ding ◽  
Daniella Albuquerque ◽  
Michael Winter ◽  
Sophia Binici ◽  
Jaclyn Piche ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Gold Standard ◽  
Onset Time ◽  
Data Set ◽  
Case Identification ◽  
Novel Method ◽  
Electronic Health ◽  
Mimic Iii

Background: Atrial fibrillation (AF) portends poor prognoses in intensive care unit patients with sepsis. However, AF research is challenging: Previous studies demonstrate that International Classification of Disease ( ICD) codes may underestimate the incidence of AF, but chart review is expensive and often not feasible. We aim to examine the accuracy of nurse-charted AF and its temporal precision in critical care patients with sepsis. Methods: Patients with sepsis with continuous electrocardiogram (ECG) waveforms were identified from the Medical Information Mart for Intensive Care (MIMIC-III) database, a de-identified, single-center intensive care unit electronic health record (EHR) source. We selected a random sample of ECGs of 6 to 50 hours’ duration for manual review. Nurse-charted AF occurrence and onset time and ICD-9-coded AF were compared to gold-standard ECG adjudication by a board-certified cardiac electrophysiologist blinded to AF status. Descriptive statistics were calculated for all variables in patients diagnosed with AF by nurse charting, ICD-9 code, or both. Results: From 142 ECG waveforms (58 AF and 84 sinus rhythm), nurse charting identified AF events with 93% sensitivity (95% confidence interval [CI]: 87%-100%) and 87% specificity (95% CI: 80%-94%) compared to the gold standard manual ECG review. Furthermore, nurse-charted AF onset time was within 1 hour of expert reader onset time for 85% of the reviewed tracings. The ICD-9 codes were 97% sensitive (95% CI: 88-100%) and 82% specific (95% CI: 74-90%) for incident AF during admission but unable to identify AF time of onset. Conclusion: Nurse documentation of AF in EHR is accurate and has high precision for determining AF onset to within 1 hour. Our study suggests that nurse-charted AF in the EHR represents a potentially novel method for AF case identification, timing, and burden estimation.

scholarly journals Prognostic nomogram for 30-day mortality of deep vein thrombosis patients in intensive care unit

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Runnan Shen ◽  
Ming Gao ◽  
Yangu Tao ◽  
Qinchang Chen ◽  
Guitao Wu ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Deep Vein Thrombosis ◽  
Prediction Models ◽  
Stepwise Logistic Regression ◽  
Internal Validation ◽  
Vein Thrombosis ◽  
New Models ◽  
Deep Vein

Abstract Background We aimed to use the Medical Information Mart for Intensive Care III database to build a nomogram to identify 30-day mortality risk of deep vein thrombosis (DVT) patients in intensive care unit (ICU). Methods Stepwise logistic regression and logistic regression with least absolute shrinkage and selection operator (LASSO) were used to fit two prediction models. Bootstrap method was used to perform internal validation. Results We obtained baseline data of 535 DVT patients, 91 (17%) of whom died within 30 days. The discriminations of two new models were better than traditional scores. Compared with simplified acute physiology score II (SAPSII), the predictive abilities of two new models were improved (Net reclassification improvement [NRI] > 0; Integrated discrimination improvement [IDI] > 0; P < 0.05). The Brier scores of two new models in training set were 0.091 and 0.108. After internal validation, corrected area under the curves for two models were 0.850 and 0.830, while corrected Brier scores were 0.108 and 0.114. The more concise model was chosen to make the nomogram. Conclusions The nomogram developed by logistic regression with LASSO model can provide an accurate prognosis for DVT patients in ICU.

scholarly journals Development of a national core dataset for the Iranian ICU patients outcome prediction: a comprehensive approach

2018 ◽  
Vol 25 (2) ◽  
pp. 71-76 ◽  
Author(s):  
Alireza Atashi ◽  
Leila Ahmadian ◽  
Zahra Rahmatinezhad ◽  
Mirmohammad Miri ◽  
Najmeh Nazeri ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Literature Review ◽  
National Survey ◽  
Outcome Prediction ◽  
Prediction Models ◽  
Literature Study ◽  
Data Set ◽  
Icu Patients ◽  
Core Dataset

ObjectiveTo define a core dataset for intensive care unit (ICU) patients outcome prediction in Iran. This core data set will lead us to design ICU outcome prediction models with the most effective parameters.MethodsA combination of literature review, national survey and expert consensus meetings were used. First, a literature review was performed by a general search in PubMed to find the most appropriate models for intensive care mortality prediction and their parameters. Second, in a national survey, experts from a couple of medical centres in all parts of Iran were asked to comment on a list of items retrieved from the earlier literature review study. In the next step, a multi-disciplinary committee of experts was installed. In four meetings, each data item was examined separately and included/excluded by committee consensus.ResultsThe combination of the literature review findings and experts’ consensus resulted in a draft dataset including 26 data items. Ninety-two percent of data items in the draft dataset were retrieved from the literature study and the others were suggested by the experts. The final dataset of 24 data items covers patient history and physical examination, chemistry, vital signs, oxygenations and some more specific parameters.ConclusionsThis dataset was designed to develop a nationwide prognostic model for predicting ICU mortality and length of stay. This dataset opens the door for creating standardised approaches in data collection in the Iranian intensive care unit estimation of resource utility.

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning

2019 ◽  
Vol 21 (9) ◽  
pp. 662-669 ◽  
Author(s):  
Junnan Zhao ◽  
Lu Zhu ◽  
Weineng Zhou ◽  
Lingfeng Yin ◽  
Yuchen Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Regression Tree ◽  
Large Data ◽  
Thrombin Inhibitors ◽  
Coagulation Cascade ◽  
Gradient Boosting ◽  
Support Vector ◽  
Data Set ◽  
Descriptor Selection

Background: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. Method: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. Results: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.

Hyperoxia is associated with adverse outcomes in the cardiac intensive care unit: insights from the Medical Information Mart for Intensive Care (MIMI-III) database

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
A.Y Lui ◽  
L Garber ◽  
M Vincent ◽  
L Celi ◽  
J Masip ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Hospital Mortality ◽  
Adverse Outcomes ◽  
Rank Test ◽  
Positive Pressure ◽  
Cardiac Intensive Care Unit ◽  
Multivariable Logistic Regression ◽  
Cardiac Intensive Care

Abstract Background Hyperoxia produces reactive oxygen species, apoptosis, and vasoconstriction, and is associated with adverse outcomes in patients with heart failure and cardiac arrest. Our aim was to evaluate the association between hyperoxia and mortality in patients (pts) receiving positive pressure ventilation (PPV) in the cardiac intensive care unit (CICU). Methods Patients admitted to our medical center CICU who received any PPV (invasive or non-invasive) from 2001 through 2012 were included. Hyperoxia was defined as time-weighted mean of PaO2 &gt;120mmHg and non-hyperoxia as PaO2 ≤120mmHg during CICU admission. Primary outcome was in-hospital mortality. Multivariable logistic regression was used to assess the association between hyperoxia and in-hospital mortality adjusted for age, female sex, Oxford Acute Severity of Illness Score, creatinine, lactate, pH, PaO2/FiO2 ratio, PCO2, PEEP, and estimated time spent on PEEP. Results Among 1493 patients, hyperoxia (median PaO2 147mmHg) during the CICU admission was observed in 702 (47.0%) pts. In-hospital mortality was 29.7% in the non-hyperoxia group and 33.9% in the hyperoxia group ((log rank test, p=0.0282, see figure). Using multivariable logistic regression, hyperoxia was independently associated with in-hospital mortality (OR 1.507, 95% CI 1.311–2.001, p=0.00508). Post-hoc analysis with PaO2 as a continuous variable was consistent with the primary analysis (OR 1.053 per 10mmHg increase in PaO2, 95% CI 1.024–1.082, p=0.0002). Conclusions In a large CICU cohort, hyperoxia was associated with increased mortality. Trials of titration of supplemental oxygen across the full spectrum of critically ill cardiac patients are warranted. Funding Acknowledgement Type of funding source: None

Risk factor identification and predictive models for central line requirements for patients on vasopressors

2021 ◽  
pp. 0310057X2110242
Author(s):  
Adrian D Haimovich ◽  
Ruoyi Jiang ◽  
Richard A Taylor ◽  
Justin B Belsky
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Central Venous Catheter ◽  
Single Agent ◽  
Composite Endpoint ◽  
Venous Catheter ◽  
Central Venous Catheters ◽  
Central Venous

Vasopressors are ubiquitous in intensive care units. While central venous catheters are the preferred route of infusion, recent evidence suggests peripheral administration may be safe for short, single-agent courses. Here, we identify risk factors and develop a predictive model for patient central venous catheter requirement using the Medical Information Mart for Intensive Care, a single-centre dataset of patients admitted to an intensive care unit between 2008 and 2019. Using prior literature, a composite endpoint of prolonged single-agent courses (>24 hours) or multi-agent courses of any duration was used to identify likely central venous catheter requirement. From a cohort of 69,619 intensive care unit stays, there were 17,053 vasopressor courses involving one or more vasopressors that met study inclusion criteria. In total, 3807 (22.3%) vasopressor courses involved a single vasopressor for less than six hours, 7952 (46.6%) courses for less than 24 hours and 5757 (33.8%) involved multiple vasopressors of any duration. Of these, 3047 (80.0%) less than six-hour and 6423 (80.8%) less than 24-hour single vasopressor courses used a central venous catheter. Logistic regression models identified associations between the composite endpoint and intubation (odds ratio (OR) 2.36, 95% confidence intervals (CI) 2.16 to 2.58), cardiac diagnosis (OR 0.72, CI 0.65 to 0.80), renal impairment (OR 1.61, CI 1.50 to 1.74), older age (OR 1.002, Cl 1.000 to 1.005) and vital signs in the hour before initiation (heart rate, OR 1.006, CI 1.003 to 1.009; oxygen saturation, OR 0.996, CI 0.993 to 0.999). A logistic regression model predicting the composite endpoint had an area under the receiver operating characteristic curve (standard deviation) of 0.747 (0.013) and an accuracy of 0.691 (0.012). This retrospective study reveals a high prevalence of short vasopressor courses in intensive care unit settings, a majority of which were administered using central venous catheters. We identify several important risk factors that may help guide clinicians deciding between peripheral and central venous catheter administration, and present a predictive model that may inform future prospective trials.

Sign in / Sign up

Export Citation Format

Share Document