Random forest for automatic assessment of heart failure severity in a telemonitoring scenario

Guidi, G.; Pettenati, Maria Chiara; Miniati, Roberto; Iadanza, Ernesto

doi:10.1109/embc.2013.6610229

Cited by 24 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 Random forest is also advantageous because it is powerful when data are missing, a common problem in clinical data obtained from EHRs. 8,9 In addition, random forest is relatively unaffected by moderate correlations among variables, an important characteristic because correlations among clinical variables are common in health research, and excising correlated variables can result in data destruction that introduces bias. 20 …”

Section: Discussionmentioning

confidence: 99%

“…The advantages of a random-forest approach are that all of the data can be used for training and validation while avoiding the decision-tree tendency to overfit the model and that the approach is relatively powerful when multicollinearity occurs and when data are missing. 8,9 The purpose of our study was to use a big-data/machine-learning approach to develop a model for predicting pressure injuries among critical care patients.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model

Alderden¹,

Pepper²,

Wilson³

et al. 2018

Am J Crit Care

137

126

View full text Add to dashboard Cite

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. (American Journal of Critical Care. 2018; 27:461–468)

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model

Alderden¹,

Pepper²,

Wilson³

et al. 2018

Am J Crit Care

137

126

View full text Add to dashboard Cite

show abstract

“…Both DSSs for Layer 1 and Layer 2 were based on Random Forest [ 21 ], i.e., the machine learning technique that yielded the best results in our previous study [ 22 ] and in other classification-tree-based approaches [ 23 ]. In this work, we maintained the internal parameters of the Random Forest used previously [ 22 ] in order to test the ability of such a setting to perform on a different dataset. The parameters used in this study were:…”

Section: Methodsmentioning

confidence: 99%

A multi-layer monitoring system for clinical management of Congestive Heart Failure

Guidi

Pollonini

Dacso

et al. 2015

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundCongestive Heart Failure (CHF) is a serious cardiac condition that brings high risks of urgent hospitalization and death. Remote monitoring systems are well-suited to managing patients suffering from CHF, and can reduce deaths and re-hospitalizations, as shown by the literature, including multiple systematic reviews.MethodsThe monitoring system proposed in this paper aims at helping CHF stakeholders make appropriate decisions in managing the disease and preventing cardiac events, such as decompensation, which can lead to hospitalization or death. Monitoring activities are stratified into three layers: scheduled visits to a hospital following up on a cardiac event, home monitoring visits by nurses, and patient's self-monitoring performed at home using specialized equipment. Appropriate hardware, desktop and mobile software applications were developed to enable a patient's monitoring by all stakeholders. For the first two layers, we designed and implemented a Decision Support System (DSS) using machine learning (Random Forest algorithm) to predict the number of decompensations per year and to assess the heart failure severity based on a variety of clinical data. For the third layer, custom-designed sensors (the Blue Scale system) for electrocardiogram (EKG), pulse transit times, bio-impedance and weight allowed frequent collection of CHF-related data in the comfort of the patient's home.We also performed a short-term Heart Rate Variability (HRV) analysis on electrocardiograms self-acquired by 15 healthy volunteers and compared the obtained parameters with those of 15 CHF patients from PhysioNet's PhysioBank archives.ResultsWe report numerical performances of the DSS, calculated as multiclass accuracy, sensitivity and specificity in a 10-fold cross-validation. The obtained average accuracies are: 71.9% in predicting the number of decompensations and 81.3% in severity assessment. The most serious class in severity assessment is detected with good sensitivity and specificity (0.87 / 0.95), while, in predicting decompensation, high specificity combined with good sensitivity prevents false alarms. The HRV parameters extracted from the self-measured EKG using the Blue Scale system of sensors are comparable with those reported in the literature about healthy people.ConclusionsThe performance of DSSs trained with new patients confirmed the results of previous work, and emphasizes the strong correlation between some CHF markers, such as brain natriuretic peptide (BNP) and ejection fraction (EF), with the outputs of interest. Comparing HRV parameters from healthy volunteers with HRV parameters obtained from PhysioBank archives, we confirm the literature that considers the HRV a promising method for distinguishing healthy from CHF patients.

show abstract

“…The proposed system, designed using the same approach applied in previous research by the authors on Heart Failure CDSS [24][25][26][27][28], enables the evaluation and classification of the results of pulmonary function tests, with good performance, compared to the current state of the art. Therefore, this system can be used in many clinical applications.…”

Section: Resultsmentioning

confidence: 99%

An automatic system supporting clinical decision for chronic obstructive pulmonary disease

2019

View full text Add to dashboard Cite

This paper presents a system supporting clinical decisions for patients with Chronic Obstructive Pulmonary Disease (COPD). The system should partially fill the gaps highlighted during an analysis of the current state of the art of Clinical Decision Support Systems (CDSS) for telemonitoring patients affected by COPD. The first step taken was to replicate the performance of similar decision support systems found in the scientific literature. Using physiological parameters drawn from respiratory function tests on 414 patients, two predictive models were created using two machine-learning algorithms: neural network and support vector machine. Performance was comparable to that described in the literature. The results made it possible to affirm that the data available were sufficient to evaluate the extent of respiratory deficit. The next step was to create a new predictive model with better performance than previously obtained. The C5.0 Machine Learning Algorithm was chosen for the development of the model. The resulting performance on the data available was significantly better than with the two previous models. This new predictive model, called COPD, was then implemented in a user interface created using Java programming language. The new software developed, which enables the evaluation and classification of respiratory test results and which can be used in many clinical applications, provides excellent performance compared to the current state of the art.

show abstract

Random forest for automatic assessment of heart failure severity in a telemonitoring scenario

Cited by 24 publications

References 9 publications

Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model

Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model

A multi-layer monitoring system for clinical management of Congestive Heart Failure

An automatic system supporting clinical decision for chronic obstructive pulmonary disease

Contact Info

Product

Resources

About