Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review.
Ontology highlight
ABSTRACT:
SUBMITTER: Syed M
PROVIDER: S-EPMC8112729 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Intensive care unit (ICU) care is expensive for patients and providers, and utilization and spending on ICU resources have increased. The No Surprises Act, passed in 2022, specifically prohibits balance billing by ICU specialists (intensivists) for emergency and most non-emergency care. The potential economic impact of this remains unclear, given few data exist on the magnitude of balance billing in the ICU. Using the MarketScan Commercial (IBM) database, we studied hospitalizations in which ICU care was provided ("ICU hospitalizations") between 2010 and 2019. Hospitalizations were characterized as fully in-network, fully out-of-network, or "mixed" (contained both in- and out-of-network services). The share of "mixed" hospitalizations among all ICU hospitalizations rose from 26% to 33% over the study period. Over half of these mixed hospitalizations contained out-of-network services specifically delivered within the ICU. Total hospitalization spending averaged $81 047, with ICU spending averaging $15 799. On average, 11% of ICU spending within these hospitalizations was out-of-network. Patients were plausibly balance-billed in approximately one-third of ICU hospitalizations, for thousands of dollars per hospitalization. Given that the No Surprises Act prevents this type of balance billing, the portended revenue loss may lead to changes in provider negotiations with insurers concerning network status and prices, which could affect the care patients receive.
| S-EPMC10932732 | biostudies-literature
Project description:Objective: Predicting prognosis of in-hospital patients is critical. However, it is challenging to accurately predict the life and death of certain patients at certain period. To determine whether machine learning algorithms could predict in-hospital death of critically ill patients with considerable accuracy and identify factors contributing to the prediction power. Materials and Methods: Using medical data of 1,384 patients admitted to the Surgical Intensive Care Unit (SICU) of our institution, we investigated whether machine learning algorithms could predict in-hospital death using demographic, laboratory, and other disease-related variables, and compared predictions using three different algorithmic methods. The outcome measurement was the incidence of unexpected postoperative mortality which was defined as mortality without pre-existing not-for-resuscitation order that occurred within 30 days of the surgery or within the same hospital stay as the surgery. Results: Machine learning algorithms trained with 43 variables successfully classified dead and live patients with very high accuracy. Most notably, the decision tree showed the higher classification results (Area Under the Receiver Operating Curve, AUC = 0.96) than the neural network classifier (AUC = 0.80). Further analysis provided the insight that serum albumin concentration, total prenatal nutritional intake, and peak dose of dopamine drug played an important role in predicting the mortality of SICU patients. Conclusion: Our results suggest that machine learning algorithms, especially the decision tree method, can provide information on structured and explainable decision flow and accurately predict hospital mortality in SICU hospitalized patients.
| S-EPMC8044535 | biostudies-literature
Project description:BackgroundTimely 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.MethodsWe 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.ResultsHSI showed significantly better performance compared to single parameters like systolic blood pressure and shock index (heart rate/systolic blood pressure) and showed good generalization across patient subgroups. HSI AUC was 0.82 and predicted 52% of all hemodynamic interventions with a lead time of 1-h with a specificity of 92%. In addition to predicting future hemodynamic interventions, our model provides confidence intervals and a ranked list of clinical features that contribute to each prediction. Importantly, HSI can use a sparse set of physiologic variables and abstains from making a prediction when the confidence is below an acceptable threshold.ConclusionsThe HSI algorithm provides a single score that summarizes hemodynamic status in real time using multiple physiologic parameters in patient monitors and electronic medical records (EMR). Importantly, HSI is designed for real-world deployment, demonstrating generalizability, strong performance under different data availability conditions, and providing model explanation in the form of feature importance and prediction confidence.
| S-EPMC8590869 | biostudies-literature
Project description:RationalePatients transferred from the intensive care unit to the wards who are later readmitted to the intensive care unit have increased length of stay, healthcare expenditure, and mortality compared with those who are never readmitted. Improving risk stratification for patients transferred to the wards could have important benefits for critically ill hospitalized patients.ObjectivesWe aimed to use a machine-learning technique to derive and validate an intensive care unit readmission prediction model with variables available in the electronic health record in real time and compare it to previously published algorithms.MethodsThis observational cohort study was conducted at an academic hospital in the United States with approximately 600 inpatient beds. A total of 24,885 intensive care unit transfers to the wards were included, with 14,962 transfers (60%) in the training cohort and 9,923 transfers (40%) in the internal validation cohort. Patient characteristics, nursing assessments, International Classification of Diseases, Ninth Revision codes from prior admissions, medications, intensive care unit interventions, diagnostic tests, vital signs, and laboratory results were extracted from the electronic health record and used as predictor variables in a gradient-boosted machine model. Accuracy for predicting intensive care unit readmission was compared with the Stability and Workload Index for Transfer score and Modified Early Warning Score in the internal validation cohort and also externally using the Medical Information Mart for Intensive Care database (n = 42,303 intensive care unit transfers).ResultsEleven percent (2,834) of discharges to the wards were later readmitted to the intensive care unit. The machine-learning-derived model had significantly better performance (area under the receiver operating curve, 0.76) than either the Stability and Workload Index for Transfer score (area under the receiver operating curve, 0.65), or Modified Early Warning Score (area under the receiver operating curve, 0.58; P value < 0.0001 for all comparisons). At a specificity of 95%, the derived model had a sensitivity of 28% compared with 15% for Stability and Workload Index for Transfer score and 7% for the Modified Early Warning Score. Accuracy improvements with the derived model over Modified Early Warning Score and Stability and Workload Index for Transfer were similar in the Medical Information Mart for Intensive Care-III cohort.ConclusionsA machine learning approach to predicting intensive care unit readmission was significantly more accurate than previously published algorithms in both our internal validation and the Medical Information Mart for Intensive Care-III cohort. Implementation of this approach could target patients who may benefit from additional time in the intensive care unit or more frequent monitoring after transfer to the hospital ward.
| S-EPMC6207111 | biostudies-literature
Project description:BackgroundMultiple organ dysfunction syndrome (MODS) is one of the leading causes of death in critically ill patients. MODS is the result of a dysregulated inflammatory response that can be triggered by various causes. Owing to the lack of an effective treatment for patients with MODS, early identification and intervention are the most effective strategies. Therefore, we have developed a variety of early warning models whose prediction results can be interpreted by Kernel SHapley Additive exPlanations (Kernel-SHAP) and reversed by diverse counterfactual explanations (DiCE). So we can predict the probability of MODS 12 h in advance, quantify the risk factors, and automatically recommend relevant interventions.MethodsWe used various machine learning algorithms to complete the early risk assessment of MODS, and used a stacked ensemble to improve the prediction performance. The kernel-SHAP algorithm was used to quantify the positive and minus factors corresponding to the individual prediction results, and finally, the DiCE method was used to automatically recommend interventions. We completed the model training and testing based on the MIMIC-III and MIMIC-IV databases, in which the sample features in the model training included the patients' vital signs, laboratory test results, test reports, and data related to the use of ventilators.ResultsThe customizable model called SuperLearner, which integrated multiple machine learning algorithms, had the highest authenticity of screening, and its Yordon index (YI), sensitivity, accuracy, and utility_score on the MIMIC-IV test set were 0.813, 0.884, 0.893, and 0.763, respectively, which were all maximum values of eleven models. The area under the curve of the deep-wide neural network (DWNN) model on the MIMIC-IV test set was 0.960, and the specificity was 0.935, which were both the maximum values of all these models. The Kernel-SHAP algorithm combined with SuperLearner was used to determine the minimum value of glasgow coma scale (GCS) in the current hour (OR = 0.609, 95% CI 0.606-0.612), maximum value of MODS score corresponding to GCS in the past 24 h (OR = 2.632, 95% CI 2.588-2.676), and maximum score of MODS corresponding to creatinine in the past 24 h (OR = 3.281, 95% CI 3.267-3.295) were generally the most influential factors.ConclusionThe MODS early warning model based on machine learning algorithms has considerable application value, and the prediction efficiency of SuperLearner is superior to those of SubSuperLearner, DWNN, and other eight common machine learning models. Considering that the attribution analysis of Kernel-SHAP is a static analysis of the prediction results, we introduce the DiCE algorithm to automatically recommend counterfactuals to reverse the prediction results, which will be an important step towards the practical application of automatic MODS early intervention.Supplementary informationThe online version contains supplementary material available at 10.1186/s40537-023-00719-2.
| S-EPMC10158675 | biostudies-literature
Project description:ObjectiveThe predictors of in-hospital mortality for intensive care units (ICUs)-admitted heart failure (HF) patients remain poorly characterised. We aimed to develop and validate a prediction model for all-cause in-hospital mortality among ICU-admitted HF patients.DesignA retrospective cohort study.Setting and participantsData were extracted from the Medical Information Mart for Intensive Care (MIMIC-III) database. Data on 1177 heart failure patients were analysed.MethodsPatients meeting the inclusion criteria were identified from the MIMIC-III database and randomly divided into derivation (n=825, 70%) and a validation (n=352, 30%) group. Independent risk factors for in-hospital mortality were screened using the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression models in the derivation sample. Multivariate logistic regression analysis was used to build prediction models in derivation group, and then validated in validation cohort. Discrimination, calibration and clinical usefulness of the predicting model were assessed using the C-index, calibration plot and decision curve analysis. After pairwise comparison, the best performing model was chosen to build a nomogram according to the regression coefficients.ResultsAmong the 1177 admissions, in-hospital mortality was 13.52%. In both groups, the XGBoost, LASSO regression and Get With the Guidelines-Heart Failure (GWTG-HF) risk score models showed acceptable discrimination. The XGBoost and LASSO regression models also showed good calibration. In pairwise comparison, the prediction effectiveness was higher with the XGBoost and LASSO regression models than with the GWTG-HF risk score model (p<0.05). The XGBoost model was chosen as our final model for its more concise and wider net benefit threshold probability range and was presented as the nomogram.ConclusionsOur nomogram enabled good prediction of in-hospital mortality in ICU-admitted HF patients, which may help clinical decision-making for such patients.
| S-EPMC8311359 | biostudies-literature
Project description: Not available
| S-EPMC9334735 | biostudies-literature
Project description:The number of critically ill patients has increased globally along with the rise in emergency visits. Mortality prediction for critical patients is vital for emergency care, which affects the distribution of emergency resources. Traditional scoring systems are designed for all emergency patients using a classic mathematical method, but risk factors in critically ill patients have complex interactions, so traditional scoring cannot as readily apply to them. As an accurate model for predicting the mortality of emergency department critically ill patients is lacking, this study's objective was to develop a scoring system using machine learning optimized for the unique case of critical patients in emergency departments. We conducted a retrospective cohort study in a tertiary medical center in Beijing, China. Patients over 16 years old were included if they were alive when they entered the emergency department intensive care unit system from February 2015 and December 2015. Mortality up to 7 days after admission into the emergency department was considered as the primary outcome, and 1624 cases were included to derive the models. Prospective factors included previous diseases, physiologic parameters, and laboratory results. Several machine learning tools were built for 7-day mortality using these factors, for which their predictive accuracy (sensitivity and specificity) was evaluated by area under the curve (AUC). The AUCs were 0.794, 0.840, 0.849 and 0.822 respectively, for the SVM, GBDT, XGBoost and logistic regression model. In comparison with the SAPS 3 model (AUC?=?0.826), the discriminatory capability of the newer machine learning methods, XGBoost in particular, is demonstrated to be more reliable for predicting outcomes for emergency department intensive care unit patients.
| S-EPMC7708467 | biostudies-literature
Project description:Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.
| S-EPMC8584535 | biostudies-literature