The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms

Song, Jie; Yuan, Gao; Yin, Pengbin; Li, Yang; Yang, Li; Zhang, Jie; Su, Qingqing; Fu, Xiaojie; Pi, Hongying

doi:10.2147/rmhp.s297838

Cited by 36 publications

(38 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, the results are in line with those of Song et al (2021) who also established that the Random Forest model has a higher accuracy when compared to other models (20). In the study, Song et al (2021) built and tested machine learning models for predicting pressure ulcer nursing adverse event in order to find an optimal model which accurately predicts the occurrence of pressure ulcers (20). The models used to predict the occurrence of pressure ulcer are support vector machine, decision tree model, artificial neural network model, and random forest model.…”

Section: Discussionsupporting

confidence: 91%

Developing and validating a multivariable prediction model for predicting costs of colon surgery

Taha

Enodien

Ochs

et al. 2022

Preprint

View full text Add to dashboard Cite

Hospitals are faced with a burden to predict and therefore to calculate and also to manage various cost factors in regard to the patients and their treatments. Especially the increased costs which occur if a patient suffers from an anastomotic insufficiency. This can lead to an unavoidable deficit in the final revenue of these medical centers. This study aims to determine whether machine learning (ML) algorithms can predict the cost factors based on patients with and without colon anastomosis after colorectal surgery. For the forecasting, multiple predictors will be taken into the model to provide a tool which can be helpful for hospitals to manage their costs, which can end up in operating more cost effectively. This proof of principle will lay the groundwork for an efficient ML-based prediction tool based on multicenter data from a range of international centers in the subsequent phases of the study. With a % MAPE result of 18 to 25.6 the prediction if our model showed decent results in order to forecast the costs in regard to various diagnosed factors and surgery approaches. There is an urgent need for further studies on predicting cost factors, especially for cases with and without anastomotic leakage to minimize unnecessary costs for the hospitals.

show abstract

Section: Discussionsupporting

confidence: 91%

Developing and validating a multivariable prediction model for predicting costs of colon surgery

Taha

Enodien

Ochs

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, relationships between 72 h URVs and the variables may not be linear; therefore, adopting a nonlinear model was necessary. RF was used in our study because it is a robust classifier that is widely used [ 30 , 31 ]. XGB was also introduced in our study because of favorable performance with imbalanced data due to autoregulating class weight during training [ 32 , 33 ].…”

Section: Discussionmentioning

confidence: 99%

A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain

et al. 2021

View full text Add to dashboard Cite

Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs.

show abstract

“…22 Moreover, compared with visual detection, our model can improve the accuracy of pressure injury diagnosis to a certain extent. 41 This study has limitations. First, data were obtained from two hospitals, and the results may not be applicable to other patient groups.…”

Section: Discussionmentioning

confidence: 92%

“…A detection threshold of 0·88 indicates that the proposed model can assist in the clinical diagnosis of pressure injuries 22 . Moreover, compared with visual detection, our model can improve the accuracy of pressure injury diagnosis to a certain extent 41 …”

Section: Discussionmentioning

confidence: 95%

Application of an infrared thermography-based model to detect pressure injuries: a prospective cohort study

Jiang

Wang

et al. 2022

British Journal of Dermatology

View full text Add to dashboard Cite

Background It is challenging to detect pressure injuries at an early stage of their development. Objectives To assess the ability of an infrared thermography (IRT)‐based model, constructed using a convolution neural network, to reliably detect pressure injuries. Methods A prospective cohort study compared validity in patients with pressure injury (n = 58) and without pressure injury (n = 205) using different methods. Each patient was followed up for 10 days. Results The optimal cut‐off values of the IRT‐based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Kaplan–Meier curves and Cox proportional hazard regression model analysis showed that the risk of pressure injury increased 13‐fold 1 day before visual detection with a cut‐off value higher than 0·53 [hazard ratio (HR) 13·04, 95% confidence interval (CI) 6·32–26·91; P < 0·001]. The ability of the IRT‐based model to detect pressure injuries [area under the receiver operating characteristic curve (AUC)lag 0 days, 0·98, 95% CI 0·95–1·00] was better than that of other methods. Conclusions The IRT‐based model is a useful and reliable method for clinical dermatologists and nurses to detect pressure injuries. It can objectively and accurately detect pressure injuries 1 day before visual detection and is therefore able to guide prevention earlier than would otherwise be possible. What is already known about this topic? Detection of pressure injuries at an early stage is challenging. Infrared thermography can be used for the physiological and anatomical evaluation of subcutaneous tissue abnormalities. A convolutional neural network is increasingly used in medical imaging analysis. What does this study add? The optimal cut‐off values of the IRT‐based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Infrared thermography‐based models can be used by clinical dermatologists and nurses to detect pressure injuries at an early stage objectively and accurately.

show abstract

The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms

Cited by 36 publications

References 35 publications

Developing and validating a multivariable prediction model for predicting costs of colon surgery

Developing and validating a multivariable prediction model for predicting costs of colon surgery

A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain

Application of an infrared thermography-based model to detect pressure injuries: a prospective cohort study

Contact Info

Product

Resources

About