A Novel Strategy for Predicting 72-h Mortality After Admission in Patients With Polytrauma: A Study on the Development and Validation of a Web-Based Calculator

Identifying patients at risk of prolonged hospital length of stay after total knee arthroplasty: A real-world study on the creation and validation of a cloud estimator

Accurate prediction of the length of stay for patients undergoing total knee arthroplasty (TKA) is critical for efficient medical resource allocation. This study aimed to create a user-friendly model to assist this estimation process. A secondary analysis was conducted on 2676 patients who underwent elective primary TKA at a tertiary academic medical center in Singapore from January 2013 to June 2014. The eligible patients (n = 2600) were randomly divided into a training cohort (n = 2081) and a validation cohort (n = 519), at a ratio of 4:1. A prolonged hospital stay was defined as exceeding six days. Multivariable logistic regression was used to develop a prediction model, and an online calculator was created to facilitate its application. The model's discrimination power, goodness-of-fit, and clinical applicability were evaluated. Additionally, models using other statistical methods were developed for performance comparison. The model includes predictors such as age, operation duration, history of cerebrovascular accidents, creatinine levels, procedure site, the American Society of Anesthesiologists Physical status, hemoglobin levels, and primary anesthesia type. The model demonstrated robust discrimination power with a C statistic of 0.70 (95% confidence interval, 0.64 to 0.75), satisfactory goodness-of-fit (Hosmer-Lemeshow test, P=0.286), and was applicable when thresholds were between 0.08 and 0.52, based on decision curve analysis. A predictive model was developed that can be used to identify patients who are likely to require an extended stay following TKA. This could assist in planning bed availability and guiding therapeutic decisions.

Development and Validation of Two Prediction Models for 72-Hour Mortality in High-Risk Trauma Patients Using a Benchmark Dataset: A Comparative Study of Logistic Regression and Neural Networks Models

Background Many studies have been conducted to develop scoring systems for trauma patients, with the majority using logistic regression (LR) models. Neural networks (NN), which is a machine learning algorithm, has a potential to increase the performance of these models. Objectives The aim of this study was to develop and validate two separate prediction models for 72-hour mortality of high-risk trauma patients using LR and NN and to compare the performances of these models in detail. We also aimed to share the SPSS calculators for our models. Materials and methods This is a retrospective, single-center study conducted using a benchmark dataset where the patients were retrospectively gathered from a level 1 trauma center. Patients older than 18 years of age, who had multiple injuries, and were treated at the University Hospital Zurich between January 1, 1996, and January 1, 2013, were included. Patients with a condition that may have an impact on the musculoskeletal system, with Injury Severity Score<16, and with missing outcome data were excluded. Results A total of 3,075 patients were included in the analysis. The area under the curve values of the LR and NN models for predicting 72-hour mortality in patients with high-risk trauma in the hold-out cohort were 0.859 (95% CI=0.836 to 0.883) and 0.856 (95% CI=0.831 to 0.880), respectively. There was no statistically significant difference in the performance of the models (p = 0.554, DeLong's test). Conclusion Both of the models showed good discrimination. Our study suggests that the NN and LR models we developed hold promise as screening tools for predicting 72-hour mortality in high-risk trauma patients. These models were made available to clinicians as clinical prediction tools via SPSS calculators. However, further external validation studies in diverse populations are necessary to substantiate their clinical utility. Moreover, in subsequent studies, it would be beneficial to derive NN models with substantial events per predictor variable to attain more robust and greater predictive accuracy. If the dataset is relatively limited, using LR seems to be a viable alternative.