Dataset Information

Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance.

ABSTRACT: BACKGROUND:Current outcomes prediction tools are largely based on and limited by regression methods. Utilization of machine learning (ML) methods that can handle multiple diverse inputs could strengthen predictive abilities and improve patient outcomes. Inpatient length of stay (LOS) is one such outcome that serves as a surrogate for patient disease severity and resource utilization. OBJECTIVE:To develop a novel method to systematically rank, select, and combine ML algorithms to build a model that predicts LOS following craniotomy for brain tumor. METHODS:A training dataset of 41?222 patients who underwent craniotomy for brain tumor was created from the National Inpatient Sample. Twenty-nine ML algorithms were trained on 26 preoperative variables to predict LOS. Trained algorithms were ranked by calculating the root mean square logarithmic error (RMSLE) and top performing algorithms combined to form an ensemble. The ensemble was externally validated using a dataset of 4592 patients from the National Surgical Quality Improvement Program. Additional analyses identified variables that most strongly influence the ensemble model predictions. RESULTS:The ensemble model predicted LOS with RMSLE of .555 (95% confidence interval, .553-.557) on internal validation and .631 on external validation. Nonelective surgery, preoperative pneumonia, sodium abnormality, or weight loss, and non-White race were the strongest predictors of increased LOS. CONCLUSION:An ML ensemble model predicts LOS with good performance on internal and external validation, and yields clinical insights that may potentially improve patient outcomes. This systematic ML method can be applied to a broad range of clinical problems to improve patient care.

SUBMITTER: Muhlestein WE

PROVIDER: S-EPMC7137462 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance.

Muhlestein Whitney E WE Akagi Dallin S DS Davies Jason M JM Chambless Lola B LB

Neurosurgery 20190901 3

<h4>Background</h4>Current outcomes prediction tools are largely based on and limited by regression methods. Utilization of machine learning (ML) methods that can handle multiple diverse inputs could strengthen predictive abilities and improve patient outcomes. Inpatient length of stay (LOS) is one such outcome that serves as a surrogate for patient disease severity and resource utilization.<h4>Objective</h4>To develop a novel method to systematically rank, select, and combine ML algorithms to b ...[more]

PMID: 30113665

Similar Datasets

Project description:Purpose Predictive analytics (PA) is a new trending approach in the field of healthcare that uses machine learning to build a prediction model using supervised learning algorithms. Isolated coronary artery bypass grafting (iCABG), an open-heart surgery, is commonly performed in the treatment of coronary heart disease. Aim The aim of this study was to develop and evaluate a model to predict postoperative length of stay (PLoS) for iCABG patients using supervised machine learning techniques, and to identify the features with the highest contribution to the model. Methods This is a retrospective study that uses historic data of adult patients who underwent isolated CABG (iCABG). After initial data pre-processing, data imputation using the kNN method was applied. The study used five prediction models using Naïve Bayes, Decision Tree, Random Forest, Logistic Regression and k Nearest Neighbor algorithms. Data imbalance was managed using the following widely used methods: oversampling, undersampling, “Both”, and random over-sampling examples (ROSE). The features selection process was conducted using the Boruta method. Two techniques were applied to examine the performance of the models, (70%, 30%) split and cross-validation, respectively. Models were evaluated by comparing their performance using AUC and other metrics. Results In the final dataset, six distinct features and 621 instances were used to develop the models. A total of 20 models were developed using R statistical software. The model generated using Random Forest with “Both” resampling method and cross-validation technique was deemed the best fit (AUC=0.81; F1 score=0.82; and recall=0.82). Attributes found to be highly predictive of PLoS were pulmonary artery systolic, age, height, EuroScore II, intra-aortic balloon pump used, and complications during operation. Conclusion This study demonstrates the significance and effectiveness of building a model that predicts PLoS for iCABG patients using patient specifications and pre-/intra-operative measures.

Project description:BackgroundThe population of persons seeking medical care is linguistically diverse in the United States. Language barriers can adversely affect a patient's ability to explain their symptoms. Among hospitalized patients, these barriers may lead to higher readmission rates and longer hospitalizations. Trained interpreters help overcome communication barriers; however, interpreter usage among patients is suboptimal.ObjectiveTo investigate differences among patients with limited English proficiency (LEP) in their length of stay (LOS) and 30-day readmission rate associated with their receiving professional interpretation at admission or discharge.DesignWe analyzed the rates of interpretation at admission and discharge of all LEP patients admitted to a tertiary care hospital over a three-year period. We calculated length of stay in days and as log of LOS. We also examined 30-day readmission. Using multivariable regression models, we explored differences among patients who received interpretation at admission, discharge, or both, controlling for patient characteristics, including age, illness severity, language, and gender.ParticipantsAll LEP patients admitted between May 1, 2004 and April 30, 2007.Main measuresLength of hospital stay as related to use of professional interpreters; readmission to the hospital within 30 days.Key resultsOf the 3071 patients included in the study, 39 % received language interpretation on both admission and discharge date. Patients who did not receive professional interpretation at admission or both admission/discharge had an increase in their LOS of between 0.75 and 1.47 days, compared to patients who had an interpreter on both day of admission and discharge (P<0.02). Patients receiving interpretation at admission and/or discharge were less likely than patients receiving no interpretation to be readmitted with 30 days.ConclusionsThe length of a hospital stay for LEP patients was significantly longer when professional interpreters were not used at admission or both admission/discharge.

Dataset Information

Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance.

Publications

Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets