scholarly journals XGBoost Algorithm Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information (Preprint)

10.2196/30770 ◽  
2021 ◽  
Author(s):  
Hyoungju Yun ◽  
Jinwook Choi ◽  
Jeong Ho Park
Keyword(s):  
Emergency Department ◽  
Critical Care ◽  
Adult Patients ◽  
Care Outcome ◽  
Initial Triage

XGBoost Algorithm Prediction of Critical Care Outcome For Adult Patients Presenting To Emergency Department Using Initial Triage Information (Preprint)

2021 ◽  
Author(s):  
Hyoungju Yun ◽  
Jinwook Choi ◽  
Jeong Ho Park
Keyword(s):  
Machine Learning ◽  
Blood Pressure ◽  
Emergency Department ◽  
Critical Care ◽  
Adult Patients ◽  
Baseline Model ◽  
Discriminative Performance ◽  
Extreme Gradient Boosting ◽  
Lemeshow Test ◽  
Care Outcome

BACKGROUND Emergency department (ED) triage system to classify and prioritize patients at high risk from less urgent continues to be a challenge. OBJECTIVE This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcome for adult patients using information collected during ED triage and compare the performance with that of the baseline model using Korean Triage and Acuity Scale (KTAS). METHODS To predict the need of critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation and level of consciousness. The baseline model with KTAS was developed using logistic regression and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by area under the receiver operating characteristic curve(AUC). The ability of calibration with Hosmer–Lemeshow test and reclassification with net reclassification index (NRI) were evaluated. The calibration plot and partial dependence plot were used in analysis. RESULTS The AUC of the model with the full set of variables (0.833–0.861) was better than that of the baseline model (0.796). The XGB model of AUC 0.861 (0.848, 0.874, 95% CI) showed a higher discriminative performance than DNN model of 0.833(0.819, 0.848). The XGB and DNN models proved better reclassification than the baseline model with positive net reclassification index. The XGB models was well calibrated (Hosmer-Lemeshow test p>0.05); however, the DNN showed poor calibration power (H-L test p<0.001). We further interpreted non-linear association between variables and critical care prediction. CONCLUSIONS Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.

Case Report: When all claims that it is necrotizing fasciitis but Point of care ultrasound (POCUS) proves the opposite!

POCUS Journal ◽  
2018 ◽  
Vol 3 (1) ◽  
pp. 13-14
Author(s):  
Hadiel Kaiyasah, MD, MRCS (Glasgow), ABHS-GS ◽  
Maryam Al Ali, MBBS
Keyword(s):  
Emergency Department ◽  
Critical Care ◽  
Case Report ◽  
Soft Tissue ◽  
Necrotizing Fasciitis ◽  
Soft Tissue Infection ◽  
Critical Care Unit ◽  
Point Of Care ◽  
Point Of Care Ultrasound ◽  
Soft Tissue Infections

Soft tissue ultrasound (ST-USS) has been shown to be of utmost importance in assessing patients with soft tissue infections in the emergency department or critical care unit. It aids in guiding the management of soft tissue infection based on the sonographic findings.

scholarly journals Interpreting Anion Gap Values in Adult and Pediatric Patients: Examining the Reference Interval

2019 ◽  
Vol 5 (1) ◽  
pp. 126-135
Author(s):  
Nadia Ayala-Lopez ◽  
Roa Harb
Keyword(s):  
Emergency Department ◽  
Intensive Care ◽  
Pediatric Patients ◽  
Reference Interval ◽  
Adult Patients ◽  
Anion Gap ◽  
Moderate Degree ◽  
New Haven ◽  
Repeated Testing ◽  
Median Percent Change

Abstract Background The anion gap is primarily used in the diagnosis of acid-base disorders. We conducted a study to determine the anion gap reference interval in our patient population, investigated the workup of abnormal vs normal anion gaps, and examined the anion gap variation upon repeated testing. Methods A retrospective review was performed on 17137 adult and pediatric patients who presented to Yale-New Haven Hospital outpatient clinics, emergency department, or intensive care units between 2012 and 2017. Results We derived a new reference interval of 7 to 18 mmol/L with a median of 13 mmol/L in healthy adults with no significant differences owing to partitioning by sex or age. Based on the new reference interval, 5%, 23%, and 18% of healthy, emergency department, and intensive care unit adult patients, respectively, were misclassified as having high values with the previous interval of 6 to 16 mmol/L. However, there were no significant differences in the number of tests ordered in patients with anion gaps above and below the upper limit of the previous reference interval. The majority of increased anion gaps that were repeated normalized by 12 h. In a subgroup of healthy adult patients with annual testing, the median percent change in each patient's anion gap from 2015 to 2016 was approximately 13%. Conclusions The anion gap should be used with an appropriate reference interval to avoid misclassification. There may be a moderate degree of individuality that argues for comparing the anion gap with its baseline value in the same patient pending further studies that formally derive its biological variation.

scholarly journals Multicountry survey of emergency and critical care medicine physicians’ fluid resuscitation practices for adult patients with early septic shock

BMJ Open ◽  
2016 ◽  
Vol 6 (7) ◽  
pp. e010041 ◽  
Author(s):  
Lauralyn McIntyre ◽  
Brian H Rowe ◽  
Timothy S Walsh ◽  
Alasdair Gray ◽  
Yaseen Arabi ◽  
...  
Keyword(s):  
Septic Shock ◽  
Critical Care ◽  
Fluid Resuscitation ◽  
Adult Patients ◽  
Critical Care Medicine
Sign in / Sign up

Export Citation Format

Share Document