scholarly journals Developing machine learning models for predicting intensive care unit resource use during the COVID-19 pandemic

2021 ◽  
Author(s):  
Stephan Slot Lorenzen ◽  
Mads Nielsen ◽  
Espen Jimenez-Solem ◽  
Tonny Studsgaard Petersen ◽  
Anders Perner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Random Forest ◽  
Characteristic Curve ◽  
Receiver Operator Characteristic Curve ◽  
Coefficient Of Determination ◽  
Icu Admission ◽  
Future Design ◽  
Forecasting Models ◽  
Regional Area

ABSTRACT Importance: The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. Objective: We investigate whether Machine Learning (ML) can be used for predictions of intensive care requirements 5 and 10 days into the future. Design: Retrospective design where health Records from 34,012 SARS-CoV-2 positive patients was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 5, 10). Setting: Two Danish regions, encompassing approx. 2.5 million citizens. Participants: All patients from the bi-regional area with a registered positive SARS-CoV-2 test from March 2020 to January 2021. Main outcomes: Prediction of future 5- and 10-day requirements of ICU admission and ventilator use. Mortality was also predicted. Results. Models predicted 5-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) of 0.986 and 5-day risk of use of ventilation with an ROC-AUC of 0.995. The corresponding 5-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) of 0.930 and use of ventilation with an R2 of 0.934. Performance was comparable but slightly reduced for 10-day forecasting models. Conclusions. Random Forest-based modelling can be used for accurate 5- and 10-day forecasting predictions of ICU resource requirements.

scholarly journals Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Stephan Sloth Lorenzen ◽  
Mads Nielsen ◽  
Espen Jimenez-Solem ◽  
Tonny Studsgaard Petersen ◽  
Anders Perner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Random Forest ◽  
Characteristic Curve ◽  
Fixed Number ◽  
Receiver Operator Characteristic Curve ◽  
Coefficient Of Determination ◽  
Icu Admission ◽  
Forecasting Models ◽  
The Future

AbstractThe COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.

scholarly journals Mortality Prediction in Cerebral Hemorrhage Patients Using Machine Learning Algorithms in Intensive Care Units

2021 ◽  
Vol 11 ◽  
Author(s):  
Ximing Nie ◽  
Yuan Cai ◽  
Jingyi Liu ◽  
Xiran Liu ◽  
Jiahui Zhao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Random Forest ◽  
Hospital Mortality ◽  
Intensive Care Units ◽  
Cerebral Hemorrhage ◽  
Characteristic Curve ◽  
Learning Algorithms ◽  
Mortality Prediction ◽  
Machine Learning Algorithms

Objectives: This study aims to investigate whether the machine learning algorithms could provide an optimal early mortality prediction method compared with other scoring systems for patients with cerebral hemorrhage in intensive care units in clinical practice.Methods: Between 2008 and 2012, from Intensive Care III (MIMIC-III) database, all cerebral hemorrhage patients monitored with the MetaVision system and admitted to intensive care units were enrolled in this study. The calibration, discrimination, and risk classification of predicted hospital mortality based on machine learning algorithms were assessed. The primary outcome was hospital mortality. Model performance was assessed with accuracy and receiver operating characteristic curve analysis.Results: Of 760 cerebral hemorrhage patients enrolled from MIMIC database [mean age, 68.2 years (SD, ±15.5)], 383 (50.4%) patients died in hospital, and 377 (49.6%) patients survived. The area under the receiver operating characteristic curve (AUC) of six machine learning algorithms was 0.600 (nearest neighbors), 0.617 (decision tree), 0.655 (neural net), 0.671(AdaBoost), 0.819 (random forest), and 0.725 (gcForest). The AUC was 0.423 for Acute Physiology and Chronic Health Evaluation II score. The random forest had the highest specificity and accuracy, as well as the greatest AUC, showing the best ability to predict in-hospital mortality.Conclusions: Compared with conventional scoring system and the other five machine learning algorithms in this study, random forest algorithm had better performance in predicting in-hospital mortality for cerebral hemorrhage patients in intensive care units, and thus further research should be conducted on random forest algorithm.

Knee Muscle Force Estimating Model Using Machine Learning Approach

2020 ◽  
Author(s):  
Anurag Sohane ◽  
Ravinder Agarwal
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Muscle Force ◽  
Vastus Lateralis ◽  
Input Parameter ◽  
Research Work ◽  
Cost Effective ◽  
Coefficient Of Determination ◽  
Muscle Forces ◽  
Knee Muscle

Abstract Various simulation type tools and conventional algorithms are being used to determine knee muscle forces of human during dynamic movement. These all may be good for clinical uses, but have some drawbacks, such as higher computational times, muscle redundancy and less cost-effective solution. Recently, there has been an interest to develop supervised learning-based prediction model for the computationally demanding process. The present research work is used to develop a cost-effective and efficient machine learning (ML) based models to predict knee muscle force for clinical interventions for the given input parameter like height, mass and angle. A dataset of 500 human musculoskeletal, have been trained and tested using four different ML models to predict knee muscle force. This dataset has obtained from anybody modeling software using AnyPyTools, where human musculoskeletal has been utilized to perform squatting movement during inverse dynamic analysis. The result based on the datasets predicts that the random forest ML model outperforms than the other selected models: neural network, generalized linear model, decision tree in terms of mean square error (MSE), coefficient of determination (R2), and Correlation (r). The MSE of predicted vs actual muscle forces obtained from the random forest model for Biceps Femoris, Rectus Femoris, Vastus Medialis, Vastus Lateralis are 19.92, 9.06, 5.97, 5.46, Correlation are 0.94, 0.92, 0.92, 0.94 and R2 are 0.88, 0.84, 0.84 and 0.89 for the test dataset, respectively.

scholarly journals Early Prediction of Seven-Day Mortality in Intensive Care Unit Using a Machine Learning Model: Results from the SPIN-UTI Project

2021 ◽  
Vol 10 (5) ◽  
pp. 992
Author(s):  
Martina Barchitta ◽  
Andrea Maugeri ◽  
Giuliana Favara ◽  
Paolo Marco Riela ◽  
Giovanni Gallo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Intensive Care Units ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Support Vector ◽  
Icu Admission ◽  
Risk Of Death ◽  
Saps Ii ◽  
Svm Algorithm

Patients in intensive care units (ICUs) were at higher risk of worsen prognosis and mortality. Here, we aimed to evaluate the ability of the Simplified Acute Physiology Score (SAPS II) to predict the risk of 7-day mortality, and to test a machine learning algorithm which combines the SAPS II with additional patients’ characteristics at ICU admission. We used data from the “Italian Nosocomial Infections Surveillance in Intensive Care Units” network. Support Vector Machines (SVM) algorithm was used to classify 3782 patients according to sex, patient’s origin, type of ICU admission, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II, presence of invasive devices, trauma, impaired immunity, antibiotic therapy and onset of HAI. The accuracy of SAPS II for predicting patients who died from those who did not was 69.3%, with an Area Under the Curve (AUC) of 0.678. Using the SVM algorithm, instead, we achieved an accuracy of 83.5% and AUC of 0.896. Notably, SAPS II was the variable that weighted more on the model and its removal resulted in an AUC of 0.653 and an accuracy of 68.4%. Overall, these findings suggest the present SVM model as a useful tool to early predict patients at higher risk of death at ICU admission.

scholarly journals Identification of candidate biomarkers of liver hydatid disease via microarray profiling, bioinformatics analysis, and machine learning

2021 ◽  
Vol 49 (3) ◽  
pp. 030006052199398
Author(s):  
Jinwu Peng ◽  
Zhili Duan ◽  
Yamin Guo ◽  
Xiaona Li ◽  
Xiaoqin Luo ◽  
...  
Keyword(s):  
Random Forest ◽  
Hydatid Disease ◽  
Characteristic Curve ◽  
Receiver Operator Characteristic Curve ◽  
Random Forest Model ◽  
Hepatic Hydatid Disease ◽  
Forest Model ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Microarray Profiling

Objectives Liver echinococcosis is a severe zoonotic disease caused by Echinococcus (tapeworm) infection, which is epidemic in the Qinghai region of China. Here, we aimed to explore biomarkers and establish a predictive model for the diagnosis of liver echinococcosis. Methods Microarray profiling followed by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analysis was performed in liver tissue from patients with liver hydatid disease and from healthy controls from the Qinghai region of China. A protein–protein interaction (PPI) network and random forest model were established to identify potential biomarkers and predict the occurrence of liver echinococcosis, respectively. Results Microarray profiling identified 1152 differentially expressed genes (DEGs), including 936 upregulated genes and 216 downregulated genes. Several previously unreported biological processes and signaling pathways were identified. The FCGR2B and CTLA4 proteins were identified by the PPI networks and random forest model. The random forest model based on FCGR2B and CTLA4 reliably predicted the occurrence of liver hydatid disease, with an area under the receiver operator characteristic curve of 0.921. Conclusion Our findings give new insight into gene expression in patients with liver echinococcosis from the Qinghai region of China, improving our understanding of hepatic hydatid disease.

scholarly journals Development of a machine learning model for predicting pediatric mortality in the early stages of intensive care unit admission

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bongjin Lee ◽  
Kyunghoon Kim ◽  
Hyejin Hwang ◽  
You Sun Kim ◽  
Eun Hee Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Validation Cohort ◽  
External Validation ◽  
Learning Model ◽  
Derivation Cohort ◽  
Icu Admission ◽  
Early Stages ◽  
Machine Learning Model

AbstractThe aim of this study was to develop a predictive model of pediatric mortality in the early stages of intensive care unit (ICU) admission using machine learning. Patients less than 18 years old who were admitted to ICUs at four tertiary referral hospitals were enrolled. Three hospitals were designated as the derivation cohort for machine learning model development and internal validation, and the other hospital was designated as the validation cohort for external validation. We developed a random forest (RF) model that predicts pediatric mortality within 72 h of ICU admission, evaluated its performance, and compared it with the Pediatric Index of Mortality 3 (PIM 3). The area under the receiver operating characteristic curve (AUROC) of RF model was 0.942 (95% confidence interval [CI] = 0.912–0.972) in the derivation cohort and 0.906 (95% CI = 0.900–0.912) in the validation cohort. In contrast, the AUROC of PIM 3 was 0.892 (95% CI = 0.878–0.906) in the derivation cohort and 0.845 (95% CI = 0.817–0.873) in the validation cohort. The RF model in our study showed improved predictive performance in terms of both internal and external validation and was superior even when compared to PIM 3.

scholarly journals Recurrent Clostridioides difficile infection can be predicted using inflammatory mediator and toxin activity levels

2020 ◽  
Vol 41 (S1) ◽  
pp. s77-s78
Author(s):  
Jonathan Motyka ◽  
Aline Penkevich ◽  
Vincent Young ◽  
Krishna Rao
Keyword(s):  
Machine Learning ◽  
Inflammatory Mediators ◽  
Inflammatory Mediator ◽  
Characteristic Curve ◽  
Receiver Operator Characteristic Curve ◽  
Sensitivity Analyses ◽  
Activity Levels ◽  
Clinical Criteria ◽  
Clostridioides Difficile ◽  
Potential Biomarker

Background:Clostridioides difficile infection (CDI) frequently recurs after initial treatment. Predicting recurrent CDI (rCDI) early in the disease course can assist clinicians in their decision making and improve outcomes. However, predictions based on clinical criteria alone are not accurate and/or do not validate other results. Here, we tested the hypothesis that circulating and stool-derived inflammatory mediators predict rCDI. Methods: Consecutive subjects with available specimens at diagnosis were included if they tested positive for toxigenic C. difficile (+enzyme immunoassay [EIA] for glutamate dehydrogenase and toxins A/B, with reflex to PCR for the tcdB gene for discordants). Stool was thawed on ice, diluted 1:1 in PBS with protease inhibitor, centrifuged, and used immediately. A 17-plex panel of inflammatory mediators was run on a Luminex 200 machine using a custom antibody-linked bead array. Prior to analysis, all measurements were normalized and log-transformed. Stool toxin activity levels were quantified using a custom cell-culture assay. Recurrence was defined as a second episode of CDI within 100 days. Ordination characterized variation in the panel between outcomes, tested with a permutational, multivariate ANOVA. Machine learning via elastic net regression with 100 iterations of 5-fold cross validation selected the optimal model and the area under the receiver operator characteristic curve (AuROC) was computed. Sensitivity analyses excluding those that died and/or lived >100 km away were performed. Results: We included 186 subjects, with 95 women (51.1%) and average age of 55.9 years (±20). More patients were diagnosed by PCR than toxin EIA (170 vs 55, respectively). Death, rCDI, and no rCDI occurred in 32 (17.2%), 36 (19.4%), and 118 (63.4%) subjects, respectively. Ordination revealed that the serum panel was associated with rCDI (P = .007) but the stool panel was not. Serum procalcitonin, IL-8, IL-6, CCL5, and EGF were associated with recurrence. The machine-learning models using the serum panel predicted rCDI with AuROCs between 0.74 and 0.8 (Fig. 1). No stool inflammatory mediators independently predicted rCDI. However, stool IL-8 interacted with toxin activity to predict rCDI (Fig. 2). These results did not change significantly upon sensitivity analysis. Conclusions: A panel of serum inflammatory mediators predicted rCDI with up to 80% accuracy, but the stool panel alone was less successful. Incorporating toxin activity levels alongside inflammatory mediator measurements is a novel, promising approach to studying stool-derived biomarkers of rCDI. This approach revealed that stool IL-8 is a potential biomarker for rCDI. These results need to be confirmed both with a larger dataset and after adjustment for clinical covariates.Funding: NoneDisclosure: Vincent Young is a consultant for Bio-K+ International, Pantheryx, and Vedanta Biosciences.

scholarly journals Machine learning for identification of surgeries with high risks of cancellation

2018 ◽  
Vol 26 (1) ◽  
pp. 141-155 ◽  
Author(s):  
Li Luo ◽  
Fengyi Zhang ◽  
Yao Yao ◽  
RenRong Gong ◽  
Martina Fu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Predictive Value ◽  
Operating Characteristic ◽  
Sampling Methods ◽  
Characteristic Curve ◽  
Support Vector ◽  
Chi Square ◽  
Stable Performance ◽  
Operating Characteristic Curve

Surgery cancellations waste scarce operative resources and hinder patients’ access to operative services. In this study, the Wilcoxon and chi-square tests were used for predictor selection, and three machine learning models – random forest, support vector machine, and XGBoost – were used for the identification of surgeries with high risks of cancellation. The optimal performances of the identification models were as follows: sensitivity − 0.615; specificity − 0.957; positive predictive value − 0.454; negative predictive value − 0.904; accuracy − 0.647; and area under the receiver operating characteristic curve − 0.682. Of the three models, the random forest model achieved the best performance. Thus, the effective identification of surgeries with high risks of cancellation is feasible with stable performance. Models and sampling methods significantly affect the performance of identification. This study is a new application of machine learning for the identification of surgeries with high risks of cancellation and facilitation of surgery resource management.

scholarly journals Machine Learning-based in-hospital Mortality Prediction Models for Patients With Acute Coronary Syndrome

2020 ◽  
Author(s):  
Jun Ke ◽  
Yiwei Chen ◽  
Xiaoping Wang ◽  
Zhiyong Wu ◽  
qiongyao Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Hospital Mortality ◽  
Operating Characteristic ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Multivariate Logistic Regression Analysis ◽  
Hdl Cholesterol ◽  
Coronary Syndrome

Abstract BackgroundThe purpose of this study is to identify the risk factors of in-hospital mortality in patients with acute coronary syndrome (ACS) and to evaluate the performance of traditional regression and machine learning prediction models.MethodsThe data of ACS patients who entered the emergency department of Fujian Provincial Hospital from January 1, 2017 to March 31, 2020 for chest pain were retrospectively collected. The study used univariate and multivariate logistic regression analysis to identify risk factors for in-hospital mortality of ACS patients. The traditional regression and machine learning algorithms were used to develop predictive models, and the sensitivity, specificity, and receiver operating characteristic curve were used to evaluate the performance of each model.ResultsA total of 7810 ACS patients were included in the study, and the in-hospital mortality rate was 1.75%. Multivariate logistic regression analysis found that age and levels of D-dimer, cardiac troponin I, N-terminal pro-B-type natriuretic peptide (NT-proBNP), lactate dehydrogenase (LDH), high-density lipoprotein (HDL) cholesterol, and calcium channel blockers were independent predictors of in-hospital mortality. The study found that the area under the receiver operating characteristic curve of the models developed by logistic regression, gradient boosting decision tree (GBDT), random forest, and support vector machine (SVM) for predicting the risk of in-hospital mortality were 0.963, 0.960, 0.963, and 0.959, respectively. Feature importance evaluation found that NT-proBNP, LDH, and HDL cholesterol were top three variables that contribute the most to the prediction performance of the GBDT model and random forest model.ConclusionsThe predictive model developed using logistic regression, GBDT, random forest, and SVM algorithms can be used to predict the risk of in-hospital death of ACS patients. Based on our findings, we recommend that clinicians focus on monitoring the changes of NT-proBNP, LDH, and HDL cholesterol, as this may improve the clinical outcomes of ACS patients.

scholarly journals COVID outcome prediction in the emergency department (COPE): using retrospective Dutch hospital data to develop simple and valid models for predicting mortality and need for intensive care unit admission in patients who present at the emergency department with suspected COVID-19

BMJ Open ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. e051468
Author(s):  
David van Klaveren ◽  
Alexandros Rekkas ◽  
Jelmer Alsma ◽  
Rob J C G Verdonschot ◽  
Dick T J J Koning ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Outcome Prediction ◽  
Characteristic Curve ◽  
Hospital Death ◽  
Hospital Data ◽  
Dutch Hospital ◽  
Icu Admission ◽  
Second Wave

ObjectivesDevelop simple and valid models for predicting mortality and need for intensive care unit (ICU) admission in patients who present at the emergency department (ED) with suspected COVID-19.DesignRetrospective.SettingSecondary care in four large Dutch hospitals.ParticipantsPatients who presented at the ED and were admitted to hospital with suspected COVID-19. We used 5831 first-wave patients who presented between March and August 2020 for model development and 3252 second-wave patients who presented between September and December 2020 for model validation.Outcome measuresWe developed separate logistic regression models for in-hospital death and for need for ICU admission, both within 28 days after hospital admission. Based on prior literature, we considered quickly and objectively obtainable patient characteristics, vital parameters and blood test values as predictors. We assessed model performance by the area under the receiver operating characteristic curve (AUC) and by calibration plots.ResultsOf 5831 first-wave patients, 629 (10.8%) died within 28 days after admission. ICU admission was fully recorded for 2633 first-wave patients in 2 hospitals, with 214 (8.1%) ICU admissions within 28 days. A simple model—COVID outcome prediction in the emergency department (COPE)—with age, respiratory rate, C reactive protein, lactate dehydrogenase, albumin and urea captured most of the ability to predict death. COPE was well calibrated and showed good discrimination for mortality in second-wave patients (AUC in four hospitals: 0.82 (95% CI 0.78 to 0.86); 0.82 (95% CI 0.74 to 0.90); 0.79 (95% CI 0.70 to 0.88); 0.83 (95% CI 0.79 to 0.86)). COPE was also able to identify patients at high risk of needing ICU admission in second-wave patients (AUC in two hospitals: 0.84 (95% CI 0.78 to 0.90); 0.81 (95% CI 0.66 to 0.95)).ConclusionsCOPE is a simple tool that is well able to predict mortality and need for ICU admission in patients who present to the ED with suspected COVID-19 and may help patients and doctors in decision making.

Sign in / Sign up

Export Citation Format

Share Document