Development and internal validation of a simple prognostic score for early sepsis risk stratification in the emergency department

Liu, Bofu; Li, Dongze; Cheng, Yisong; Yu, Jing; Yu, Jie-Ping; Zhang, Qin; Liu, Yanmei; Cao, Yu

doi:10.1136/bmjopen-2020-046009

Cited by 7 publications

(3 citation statements)

References 28 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MV was described as a requirement for invasive or non-invasive ventilation as a consequence of hypoxic respiratory failure. 14 Patients were separated into survival and non-survival groups based on their 7-day survival status.…”

Section: Methodsmentioning

confidence: 99%

Analysis of the Value of the Blood Urea Nitrogen to Albumin Ratio as a Predictor of Mortality in Patients with Sepsis

Han¹,

Cheng²,

Liao³

et al. 2022

JIR

Self Cite

View full text Add to dashboard Cite

At present, simple, accurate, and efficient prognostic tools for the evaluation of cases with early-stage sepsis in the emergency department (ED) are lacking. An increased blood urea nitrogen to albumin ratio (BAR) has previously been shown to be a valuable biomarker with predictive utility in several diseases. The relationship between BAR and sepsis patient outcomes, however, is not well-understood. This exploration was thus developed for the exploration of the link between BAR values and the short-term prognosis of cases with sepsis. Methods: This was a retrospective cohort research of sepsis cases admitted to the West China Hospital of Sichuan University ED from July 2015 to June 2016. Laboratory data were collected upon ED admission, and 7-day all-cause mortality was the primary study endpoint. Relationships between BAR values and APACE II and SOFA scores were generated assessed with correlation coefficient heatmaps. Independent risk factors were identified through multivariate analyses, with the curves of receiver operating characteristic (ROC) being employed to gauge the value of BAR as a predictor of the risk of mortality in sepsis cases. Results: In sum, 801 patients participated in the present investigation. BAR values were strongly correlated with APACHE II and SOFA scores. In a multivariate logistic regression assessment, BAR was identified as an independent predictor of mortality among patients with sepsis (HR=1.032, 95% CI: 1.010-1.055, P=0.004). BAR exhibited an AUC of 0.741 (95% CI: 0.688-0.793, P<0.001) when used to predict patient mortality risk, with 5.27 being the optimal BAR cut-off. Conclusion:We found that BAR can be used as a reliable biomarker to predict mortality in patients with sepsis.

show abstract

Section: Methodsmentioning

confidence: 99%

Analysis of the Value of the Blood Urea Nitrogen to Albumin Ratio as a Predictor of Mortality in Patients with Sepsis

Han¹,

Cheng²,

Liao³

et al. 2022

JIR

Self Cite

View full text Add to dashboard Cite

show abstract

“…MV was defined by the need for non-invasive or invasive ventilation owing to respiratory failure. 13 …”

Section: Methodsmentioning

confidence: 99%

Thrombo-Inflammatory Prognostic Scores Improve BISAP-Based Risk Stratification in Acute Pancreatitis Patients: A Retrospective Cohort Study

Han¹,

Cheng²,

Liao³

et al. 2022

JIR

Self Cite

View full text Add to dashboard Cite

Purpose The thrombo-inflammatory prognostic score (TIPS) and the bedside index for severity in acute pancreatitis (BISAP) are both scoring systems that enable the rapid prognostic assessment of early-stage acute pancreatitis (AP) patients, but the overall prognostic utility of these individual systems is limited. This study was thus developed to explore whether a combination of TIPS and BISAP scores would offer better insight to facilitate the risk stratification of AP patients. Methods This single-center retrospective cohort research evaluated AP cases referred to the emergency department from January 1, 2017 to September 30, 2017. The ability of TIPS scores to improve BISAP-based AP patient risk stratification was appraised employing the curves of receiver-operating characteristic (ROC) and decision curve analysis (DCA) approaches. The initial endpoint for this research was 28-day mortality, while secondary endpoints comprised intensive care unit admission (AICU) and mechanical ventilation (MV) over a 28-day follow-up period. Results Totally, 440 cases enrolled in the current study were divided at a ratio of 1:1 to derivation and validation cohorts. When estimating 28-day mortality, the combination of TIPS and BISAP (T-BISAP) improved the area under the curve (AUC) value in the derivation group from 0.809 to 0.903 (P < 0.05), in addition to similarly improving this AUC value from 0.709 to 0.853 (P < 0.05) in the validation cohort. Moreover, T-BISAP significantly improved the AUC values for 28-day AICU from 0.751 to 0.824 (P < 0.05) and the AUC values for 28-day MV from 0.755 to 0.808 (P < 0.05). A DCA approach revealed T-BISAP to exhibit higher net benefit when used for patient risk stratification as compared to BISAP alone. Conclusion The addition of TIPS scores to BISAP scores can enable prediction of 28-day adverse clinical outcomes with AP patients in the ED.

show abstract

“…Unlike previous studies that concentrated on patients with specific injuries in the ED, our study encompassed nearly all pediatric patients admitted to the PED. This approach has potential implications for the comprehensive management and resource allocation of pediatric emergency medical care [33][34][35].…”

Section: Principal Findingsmentioning

confidence: 99%

Characteristics and Admission Preferences of Pediatric Emergency Patients and Their Waiting Time Prediction Using Electronic Medical Record Data: Retrospective Comparative Analysis

Guo,

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background The growing number of patients visiting pediatric emergency departments could have a detrimental impact on the care provided to children who are triaged as needing urgent attention. Therefore, it has become essential to continuously monitor and analyze the admissions and waiting times of pediatric emergency patients. Despite the significant challenge posed by the shortage of pediatric medical resources in China’s health care system, there have been few large-scale studies conducted to analyze visits to the pediatric emergency room. Objective This study seeks to examine the characteristics and admission patterns of patients in the pediatric emergency department using electronic medical record (EMR) data. Additionally, it aims to develop and assess machine learning models for predicting waiting times for pediatric emergency department visits. Methods This retrospective analysis involved patients who were admitted to the emergency department of Children’s Hospital Capital Institute of Pediatrics from January 1, 2021, to December 31, 2021. Clinical data from these admissions were extracted from the electronic medical records, encompassing various variables of interest such as patient demographics, clinical diagnoses, and time stamps of clinical visits. These indicators were collected and compared. Furthermore, we developed and evaluated several computational models for predicting waiting times. Results In total, 183,024 eligible admissions from 127,368 pediatric patients were included. During the 12-month study period, pediatric emergency department visits were most frequent among children aged less than 5 years, accounting for 71.26% (130,423/183,024) of the total visits. Additionally, there was a higher proportion of male patients (104,147/183,024, 56.90%) compared with female patients (78,877/183,024, 43.10%). Fever (50,715/183,024, 27.71%), respiratory infection (43,269/183,024, 23.64%), celialgia (9560/183,024, 5.22%), and emesis (6898/183,024, 3.77%) were the leading causes of pediatric emergency room visits. The average daily number of admissions was 501.44, and 18.76% (34,339/183,204) of pediatric emergency department visits resulted in discharge without a prescription or further tests. The median waiting time from registration to seeing a doctor was 27.53 minutes. Prolonged waiting times were observed from April to July, coinciding with an increased number of arrivals, primarily for respiratory diseases. In terms of waiting time prediction, machine learning models, specifically random forest, LightGBM, and XGBoost, outperformed regression methods. On average, these models reduced the root-mean-square error by approximately 17.73% (8.951/50.481) and increased the R2 by approximately 29.33% (0.154/0.525). The SHAP method analysis highlighted that the features “wait.green” and “department” had the most significant influence on waiting times. Conclusions This study offers a contemporary exploration of pediatric emergency room visits, revealing significant variations in admission rates across different periods and uncovering certain admission patterns. The machine learning models, particularly ensemble methods, delivered more dependable waiting time predictions. Patient volume awaiting consultation or treatment and the triage status emerged as crucial factors contributing to prolonged waiting times. Therefore, strategies such as patient diversion to alleviate congestion in emergency departments and optimizing triage systems to reduce average waiting times remain effective approaches to enhance the quality of pediatric health care services in China.

show abstract

Development and internal validation of a simple prognostic score for early sepsis risk stratification in the emergency department

Cited by 7 publications

References 28 publications

Analysis of the Value of the Blood Urea Nitrogen to Albumin Ratio as a Predictor of Mortality in Patients with Sepsis

Analysis of the Value of the Blood Urea Nitrogen to Albumin Ratio as a Predictor of Mortality in Patients with Sepsis

Thrombo-Inflammatory Prognostic Scores Improve BISAP-Based Risk Stratification in Acute Pancreatitis Patients: A Retrospective Cohort Study

Characteristics and Admission Preferences of Pediatric Emergency Patients and Their Waiting Time Prediction Using Electronic Medical Record Data: Retrospective Comparative Analysis

Contact Info

Product

Resources

About