Adding Continuous Vital Sign Information to Static Clinical Data Improves the Prediction of Length of Stay After Intubation: A Data-Driven Machine Learning Approach

Abstract

BACKGROUND: Bedside monitors in the ICU routinely measure and collect patients' physiologic data in real time to continuously assess the health status of patients who are critically ill. With the advent of increased computational power and the ability to store and rapidly process big data sets in recent years, these physiologic data show promise in identifying specific outcomes and/or events during patients' ICU hospitalization. METHODS: We introduced a methodology designed to automatically extract information from continuous-in-time vital sign data collected from bedside monitors to predict if a patient will experience a prolonged stay (length of stay) on mechanical ventilation, defined as >4 d, in a pediatric ICU. RESULTS: Continuous-in-time vital signs information and clinical history data were retrospectively collected for 284 ICU subjects from their first 24 h on mechanical ventilation from a medical-surgical pediatric ICU at Boston Children's Hospital. Multiple machine learning models were trained on multiple subsets of these subjects to predict the likelihood that each of these subjects would experience a long stay. We evaluated the predictive power of our models strictly on unseen hold-out validation sets of subjects. Our methodology achieved model performance of >83% (area under the curve) by using only vital sign information as input, and performances of 90% (area under the curve) by combining vital sign information with subjects' static clinical data readily available in electronic health records. We implemented this approach on 300 independently trained experiments with different choices of training and hold-out validation sets to ensure the consistency and robustness of our results in our study sample. The predictive power of our approach outperformed recent efforts that used deep learning to predict a similar task. CONCLUSIONS: Our proposed workflow may prove useful in the design of scalable approaches for real-time predictive systems in ICU environments, exploiting real-time vital sign information from bedside monitors. (ClinicalTrials.gov registration NCT02184208.

Early Prediction of Mortality, Severity, and Length of Stay in the Intensive Care Unit of Sepsis Patients Based on Sepsis 3.0 by Machine Learning Models

“…Staziaki et al ( 22 ) reported that SVM and ANN models combining CT findings and clinical parameters improved the prediction of length of stay and ICU admission in torso trauma. Castineira et al ( 23 ) added continuous vital sign information to static clinical data to improve the prediction of length of stay after intubation. Even ELM has been used to determine whether the patient can be discharged within 10 days ( 24 ).…”

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

“…We identified 26 studies regarding the prediction of the hospital length of stay that used data science methods. Twenty-three studies used a retrospective cohort design, 126 133 159 173 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 while three were prospective cohort studies. 129 195 196 Data sources mostly used administrative databases 126 133 179 180 182 186 191 192 194 and EHRs, 129 133 176 183 184 188 190 192 196 while other studies used publicly available datasets, 159 173 178 187 189 data warehouses and registries, 133 177 180 195 paper clinical notes, 193 paper patient records, 185 research electronic data capture systems, 188 trial datasets, 181 questionnaires, 196 and routine bedside monitors.…”

“…129 195 196 Data sources mostly used administrative databases 126 133 179 180 182 186 191 192 194 and EHRs, 129 133 176 183 184 188 190 192 196 while other studies used publicly available datasets, 159 173 178 187 189 data warehouses and registries, 133 177 180 195 paper clinical notes, 193 paper patient records, 185 research electronic data capture systems, 188 trial datasets, 181 questionnaires, 196 and routine bedside monitors. 176 Sample sizes ranged from 143 to 2,997,249 patients. Study populations included surgical patients, 133 159 177 179 181 182 183 195 196 ICU patients, 173 176 178 187 189 190 medical-surgical patients, 126 129 180 191 patients presenting to the ED, 184 188 193 194 and psychiatric patients.…”

“…176 Sample sizes ranged from 143 to 2,997,249 patients. Study populations included surgical patients, 133 159 177 179 181 182 183 195 196 ICU patients, 173 176 178 187 189 190 medical-surgical patients, 126 129 180 191 patients presenting to the ED, 184 188 193 194 and psychiatric patients. 185 186 192 Most studies were conducted using U.S. patient data, 129 133 159 173 176 177 178 181 182 183 187 189 191 while other studies used patient data from Australia, 126 179 193 194 Brazil, 186 188 Canada, 195 196 China, 180 England, 190 Germany, 192 Switzerland, 185 and Taiwan.…”

Machine learning in patient flow: a review

“…Children are also a cohort of patients in which there can be great variability in LOS. To address this, Castiñeira et al ( 2020 ) use a gradient boosted tree to classify whether or not a child will be a long-stay patient in the paediatric ICU (with long-stay being defined as a stay of greater than 4 d). They also use the static model for a dynamic problem approach by extracting features from the time-series of the patient’s vital signs and repeatedly feeding these to the classifier.…”