Dataset Information

Optimizing intensive care capacity using individual length-of-stay prediction models.

ABSTRACT:

Introduction

Effective planning of elective surgical procedures requiring postoperative intensive care is important in preventing cancellations and empty intensive care unit (ICU) beds. To improve planning, we constructed, validated and tested three models designed to predict length of stay (LOS) in the ICU in individual patients.

Methods

Retrospective data were collected from 518 consecutive patients who underwent oesophagectomy with reconstruction for carcinoma between January 1997 and April 2005. Three multivariable linear regression models for LOS, namely preoperative, postoperative and intra-ICU, were constructed using these data. Internal validation was assessed using bootstrap sampling in order to obtain validated estimates of the explained variance (r2). To determine the potential gain of the best performing model in day-to-day clinical practice, prospective data from a second cohort of 65 consecutive patients undergoing oesophagectomy between May 2005 and April 2006 were used in the model, and the predictive performance of the model was compared with prediction based on mean LOS.

Results

The intra-ICU model had an r2 of 45% after internal validation. Important prognostic variables for LOS included greater patient age, comorbidity, type of surgical approach, intraoperative respiratory minute volume and complications occurring within 72 hours in the ICU. The potential gain of the best model in day-to-day clinical practice was determined relative to mean LOS. Use of the model reduced the deficit number (underestimation) of ICU days by 65 and increased the excess number (overestimation) of ICU days by 23 for the cohort of 65 patients. A conservative analysis conducted in the second, prospective cohort of patients revealed that 7% more oesophagectomies could have been accommodated, and 15% of cancelled procedures could have been prevented.

Conclusion

Patient characteristics can be used to create models that will help in predicting LOS in the ICU. This will result in more efficient use of ICU beds and fewer cancellations.

SUBMITTER: Van Houdenhoven M

PROVIDER: S-EPMC2206463 | biostudies-literature | 2007

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optimizing intensive care capacity using individual length-of-stay prediction models.

Van Houdenhoven Mark M Nguyen Duy-Tien DT Eijkemans Marinus J MJ Steyerberg Ewout W EW Tilanus Hugo W HW Gommers Diederik D Wullink Gerhard G Bakker Jan J Kazemier Geert G

Critical care (London, England) 20070101 2

<h4>Introduction</h4>Effective planning of elective surgical procedures requiring postoperative intensive care is important in preventing cancellations and empty intensive care unit (ICU) beds. To improve planning, we constructed, validated and tested three models designed to predict length of stay (LOS) in the ICU in individual patients.<h4>Methods</h4>Retrospective data were collected from 518 consecutive patients who underwent oesophagectomy with reconstruction for carcinoma between January 1 ...[more]

PMID: 17389032

Similar Datasets

Project description:BackgroundPost-operative heart transplantation patients often require admission to an intensive care unit (ICU). Early prediction of the ICU length of stay (ICU-LOS) of these patients is of great significance and can guide treatment while reducing the mortality rate among patients. However, conventional linear models have tended to perform worse than non-linear models.Materials and methodsWe collected the clinical data of 365 patients from Wuhan Union Hospital who underwent heart transplantation surgery between April 2017 and August 2020. The patients were randomly divided into training data (N = 256) and test data (N = 109) groups. 84 clinical features were collected for each patient. Features were validated using the Least Absolute Shrinkage and Selection Operator (LASSO) regression's fivefold cross-validation method. We obtained Shapley Additive explanations (SHAP) values by executing package "shap" to interpret model predictions. Four machine learning models and logistic regression algorithms were developed. The area under the receiver operating characteristic curve (AUC-ROC) was used to compare the prediction performance of different models. Finally, for the convenience of clinicians, an online web-server was established and can be freely accessed via the website https://wuhanunion.shinyapps.io/PredictICUStay/.ResultsIn this study, 365 consecutive patients undergoing heart transplantation surgery for moderate (NYHA grade 3) or severe (NYHA grade 4) heart failure were collected in Wuhan Union Hospital from 2017 to 2020. The median age of the recipient patients was 47.2 years, while the median age of the donors was 35.58 years. 330 (90.4%) of the donor patients were men, and the average surgery duration was 260.06 min. Among this cohort, 47 (12.9%) had renal complications, 25 (6.8%) had hepatic complications, 11 (3%) had undergone chest re-exploration and 19 (5.2%) had undergone extracorporeal membrane oxygenation (ECMO). The following six important clinical features were selected using LASSO regression, and according to the result of SHAP, the rank of importance was (1) the use of extracorporeal membrane oxygenation (ECMO); (2) donor age; (3) the use of an intra-aortic balloon pump (IABP); (4) length of surgery; (5) high creatinine (Cr); and (6) the use of continuous renal replacement therapy (CRRT). The eXtreme Gradient Boosting (XGBoost) algorithm presented significantly better predictive performance (AUC-ROC = 0.88) than other models [Accuracy: 0.87; sensitivity: 0.98; specificity: 0.51; positive predictive value (PPV): 0.86; negative predictive value (NPV): 0.93].ConclusionUsing the XGBoost classifier with heart transplantation patients can provide an accurate prediction of ICU-LOS, which will not only improve the accuracy of clinical decision-making but also contribute to the allocation and management of medical resources; it is also a real-world example of precision medicine in hospitals.

Project description:Recent advances in emergency medicine and the co-ordinated delivery of trauma care mean more critically-injured patients now reach the hospital alive and survive life-saving operations. Indeed, between 2008 and 2017, the odds of surviving a major traumatic injury in the UK increased by nineteen percent. However, the improved survival rates of severely-injured patients have placed an increased burden on the healthcare system, with major trauma a common cause of intensive care unit (ICU) admissions that last ≥10 days. Improved understanding of the factors influencing patient outcomes is now urgently needed. We investigated the serum metabolomic profile of fifty-five major trauma patients across three post-injury phases: acute (days 0-4), intermediate (days 5-14) and late (days 15-112). Using ICU length of stay (LOS) as a clinical outcome, we aimed to determine whether the serum metabolome measured at days 0-4 post-injury for patients with an extended (≥10 days) ICU LOS differed from that of patients with a short (<10 days) ICU LOS. In addition, we investigated whether combining metabolomic profiles with clinical scoring systems would generate a variable that would identify patients with an extended ICU LOS with a greater degree of accuracy than models built on either variable alone. The number of metabolites unique to and shared across each time segment varied across acute, intermediate and late segments. A one-way ANOVA revealed the most variation in metabolite levels across the different time-points was for the metabolites lactate, glucose, anserine and 3-hydroxybutyrate. A total of eleven features were selected to differentiate between <10 days ICU LOS vs. >10 days ICU LOS. New Injury Severity Score (NISS), testosterone, and the metabolites cadaverine, urea, isoleucine, acetoacetate, dimethyl sulfone, syringate, creatinine, xylitol, and acetone form the integrated biomarker set. Using metabolic enrichment analysis, we found valine, leucine and isoleucine biosynthesis, glutathione metabolism, and glycine, serine and threonine metabolism were the top three pathways differentiating ICU LOS with a p < 0.05. A combined model of NISS and testosterone and all nine selected metabolites achieved an AUROC of 0.824. Differences exist in the serum metabolome of major trauma patients who subsequently experience a short or prolonged ICU LOS in the acute post-injury setting. Combining metabolomic data with anatomical scoring systems allowed us to discriminate between these two groups with a greater degree of accuracy than that of either variable alone.

Dataset Information

Optimizing intensive care capacity using individual length-of-stay prediction models.

Introduction

Methods

Results

Conclusion

Publications

Optimizing intensive care capacity using individual length-of-stay prediction models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets