scholarly journals A Practical Triage and Risk Scoring for Prediction of Early Mortality in Polytrauma Patients: GAS-TRS

2021 ◽  
Author(s):  
Tian Xie ◽  
Shikai Wang ◽  
Nan Du ◽  
Qunxing Huang ◽  
Jianguo Wu ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Mortality Risk ◽  
Treatment Strategy ◽  
Early Mortality ◽  
Mediation Effect ◽  
Actual Condition ◽  
Individual Treatment ◽  
Ann Model ◽  
Early Assessment ◽  
Polytrauma Patients

Abstract Background Accurate evaluation of mortality risk in polytrauma patients is crucial for guiding the precision treatment strategy. There are few scales designed to provide an early assessment of mortality risk. However, the complexity of available scoring systems limits their application in pre-hospital care. Here, we established a GAS-TRS system to estimate the risk of early death for individual polytrauma patients and assess the early mortality risk in the individual patient.Methods We performed a secondary analysis from public Database. RCS and Multivariate Logistic regression analyses were used to screen potential prognostic factors for nomogram model. The VIF method examined multicollinearity, and VIF ≥ 5 suggested multicollinearity in this model. CMA was used to characterize the causality relationship in nomogram model. A four-layer back-propagation artificial neural network (BP-ANN) model was built by neuralnet package on R software. AUC of ROC analysis or F1 score were used to analyze the quality of predictive performance of GAS-TRS system. DCA and precision-recall curves were used to make up for the limitations of ROC curves.Results A total of 2406 patients were included in this analysis. Logistic regression analysis predicted four independent risk factors for nomogram model, including age (OR=1.03, 95%CI:1.02~1.03), GCS (OR=0.83, 95%CI:0.79~0.86), BE (OR=0.95, 95%CI:0.91~0.99) and serum lactic acid (OR=1.30, 95%CI:1.20~1.41) with an AUC of 0.88. Causal mediation analysis performed the mediation effect that lactate, age and BE accounted for 1.7%,0.7% and 3.0% indirect effect.The calibration curve showed model has good highly consistent with actual condition after bootstrapping. DCA showed the net benefit probability was between 2% and 85% and could bring more benefits for predicting early mortality.Then the input neurons were selected step by step in BP-ANN model. An optimal BP-ANN with an AUC of 0.91and AUPRC of 0.79 was established.Conclusion We established a GAS-TRS predictive system which includes a quick prognostic nomogram model and a precise BP-ANN model to evaluate early mortality within 72 hours for polytrauma patients. This scoring system might be practical and more efficient in identifying high-risk polytrauma patients. Moreover, this system may also guide triaging and precise initial individual treatment strategy for pre-hospital medical personnel.

scholarly journals An Artificial Neural Network–Based Pediatric Mortality Risk Score: Development and Performance Evaluation Using Data From a Large North American Registry (Preprint)

2020 ◽  
Author(s):  
Niema Ghanad Poor ◽  
Nicholas C West ◽  
Rama Syamala Sreepada ◽  
Srinivas Murthy ◽  
Matthias Görges
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Mortality Risk ◽  
Regression Models ◽  
Logistic Regression Model ◽  
Single Layer ◽  
Ann Model ◽  
Data Set ◽  
Using Data ◽  
Better Than

BACKGROUND In the pediatric intensive care unit (PICU), quantifying illness severity can be guided by risk models to enable timely identification and appropriate intervention. Logistic regression models, including the pediatric index of mortality 2 (PIM-2) and pediatric risk of mortality III (PRISM-III), produce a mortality risk score using data that are routinely available at PICU admission. Artificial neural networks (ANNs) outperform regression models in some medical fields. OBJECTIVE In light of this potential, we aim to examine ANN performance, compared to that of logistic regression, for mortality risk estimation in the PICU. METHODS The analyzed data set included patients from North American PICUs whose discharge diagnostic codes indicated evidence of infection and included the data used for the PIM-2 and PRISM-III calculations and their corresponding scores. We stratified the data set into training and test sets, with approximately equal mortality rates, in an effort to replicate real-world data. Data preprocessing included imputing missing data through simple substitution and normalizing data into binary variables using PRISM-III thresholds. A 2-layer ANN model was built to predict pediatric mortality, along with a simple logistic regression model for comparison. Both models used the same features required by PIM-2 and PRISM-III. Alternative ANN models using single-layer or unnormalized data were also evaluated. Model performance was compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC) and their empirical 95% CIs. RESULTS Data from 102,945 patients (including 4068 deaths) were included in the analysis. The highest performing ANN (AUROC 0.871, 95% CI 0.862-0.880; AUPRC 0.372, 95% CI 0.345-0.396) that used normalized data performed better than PIM-2 (AUROC 0.805, 95% CI 0.801-0.816; AUPRC 0.234, 95% CI 0.213-0.255) and PRISM-III (AUROC 0.844, 95% CI 0.841-0.855; AUPRC 0.348, 95% CI 0.322-0.367). The performance of this ANN was also significantly better than that of the logistic regression model (AUROC 0.862, 95% CI 0.852-0.872; AUPRC 0.329, 95% CI 0.304-0.351). The performance of the ANN that used unnormalized data (AUROC 0.865, 95% CI 0.856-0.874) was slightly inferior to our highest performing ANN; the single-layer ANN architecture performed poorly and was not investigated further. CONCLUSIONS A simple ANN model performed slightly better than the benchmark PIM-2 and PRISM-III scores and a traditional logistic regression model trained on the same data set. The small performance gains achieved by this two-layer ANN model may not offer clinically significant improvement; however, further research with other or more sophisticated model designs and better imputation of missing data may be warranted. CLINICALTRIAL

scholarly journals An Artificial Neural Network–Based Pediatric Mortality Risk Score: Development and Performance Evaluation Using Data From a Large North American Registry

10.2196/24079 ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. e24079
Author(s):  
Niema Ghanad Poor ◽  
Nicholas C West ◽  
Rama Syamala Sreepada ◽  
Srinivas Murthy ◽  
Matthias Görges
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Mortality Risk ◽  
Regression Models ◽  
Logistic Regression Model ◽  
Single Layer ◽  
Ann Model ◽  
Data Set ◽  
Using Data ◽  
Better Than

Background In the pediatric intensive care unit (PICU), quantifying illness severity can be guided by risk models to enable timely identification and appropriate intervention. Logistic regression models, including the pediatric index of mortality 2 (PIM-2) and pediatric risk of mortality III (PRISM-III), produce a mortality risk score using data that are routinely available at PICU admission. Artificial neural networks (ANNs) outperform regression models in some medical fields. Objective In light of this potential, we aim to examine ANN performance, compared to that of logistic regression, for mortality risk estimation in the PICU. Methods The analyzed data set included patients from North American PICUs whose discharge diagnostic codes indicated evidence of infection and included the data used for the PIM-2 and PRISM-III calculations and their corresponding scores. We stratified the data set into training and test sets, with approximately equal mortality rates, in an effort to replicate real-world data. Data preprocessing included imputing missing data through simple substitution and normalizing data into binary variables using PRISM-III thresholds. A 2-layer ANN model was built to predict pediatric mortality, along with a simple logistic regression model for comparison. Both models used the same features required by PIM-2 and PRISM-III. Alternative ANN models using single-layer or unnormalized data were also evaluated. Model performance was compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC) and their empirical 95% CIs. Results Data from 102,945 patients (including 4068 deaths) were included in the analysis. The highest performing ANN (AUROC 0.871, 95% CI 0.862-0.880; AUPRC 0.372, 95% CI 0.345-0.396) that used normalized data performed better than PIM-2 (AUROC 0.805, 95% CI 0.801-0.816; AUPRC 0.234, 95% CI 0.213-0.255) and PRISM-III (AUROC 0.844, 95% CI 0.841-0.855; AUPRC 0.348, 95% CI 0.322-0.367). The performance of this ANN was also significantly better than that of the logistic regression model (AUROC 0.862, 95% CI 0.852-0.872; AUPRC 0.329, 95% CI 0.304-0.351). The performance of the ANN that used unnormalized data (AUROC 0.865, 95% CI 0.856-0.874) was slightly inferior to our highest performing ANN; the single-layer ANN architecture performed poorly and was not investigated further. Conclusions A simple ANN model performed slightly better than the benchmark PIM-2 and PRISM-III scores and a traditional logistic regression model trained on the same data set. The small performance gains achieved by this two-layer ANN model may not offer clinically significant improvement; however, further research with other or more sophisticated model designs and better imputation of missing data may be warranted.

1331: A Quick Prognostic Nomogram Model to Predict Early Mortality Risk in Polytrauma Patients

2020 ◽  
Vol 49 (1) ◽  
pp. 672-672
Author(s):  
Tian Xie ◽  
Shikai Wang ◽  
Xiangda Zhang ◽  
Sihua Ou ◽  
Xiaoqiao Mo
Keyword(s):  
Mortality Risk ◽  
Early Mortality ◽  
Polytrauma Patients

Predicting wildfire vulnerability using logistic regression and artificial neural networks: a case study in Brazil's Federal District

2019 ◽  
Vol 28 (1) ◽  
pp. 35 ◽  
Author(s):  
Pablo Pozzobon de Bem ◽  
Osmar Abílio de Carvalho Júnior ◽  
Eraldo Aparecido Trondoli Matricardi ◽  
Renato Fontes Guimarães ◽  
Roberto Arnaldo Trancoso Gomes
Keyword(s):  
Logistic Regression ◽  
Characteristic Curve ◽  
Federal District ◽  
Burned Area ◽  
Ann Model ◽  
Wildfire Management ◽  
Explanatory Variables ◽  
Burned Areas ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Predicting the spatial distribution of wildfires is an important step towards proper wildfire management. In this work, we applied two data-mining models commonly used to predict fire occurrence – logistic regression (LR) and an artificial neural network (ANN) – to Brazil’s Federal District, located inside the Brazilian Cerrado. We used Landsat-based burned area products to generate the dependent variable, and nine different anthropogenic and environmental factors as explanatory variables. The models were optimised via feature selection for best area under receiver operating characteristic curve (AUC) and then validated with real burn area data. The models had similar performance, but the ANN model showed better AUC (0.77) and accuracy values when evaluating exclusively non-burned areas (73.39%), whereas it had worse accuracy overall (66.55%) when classifying burned areas, in which LR performed better (65.24%). Moreover, we compared the contribution of each variable to the models, adding some insight into the main causes of wildfires in the region. The main driving aspects of the burned area distribution were land-use type and elevation. The results showed good performance for both models tested. These studies are still scarce despite the importance of the Brazilian savanna.

scholarly journals Predictive Analysis of Employee Loyalty: A Comparative Study Using Logistic Regression Model and Artificial Neural Network

2019 ◽  
Vol 25 (3) ◽  
pp. 325-335
Author(s):  
Maria Zefanya Sampe ◽  
Eko Ariawan ◽  
I Wayan Ariawan
Keyword(s):  
Logistic Regression ◽  
Employee Turnover ◽  
Mean Squared Error ◽  
Working Hours ◽  
Retention Rates ◽  
Ann Model ◽  
Employee Loyalty ◽  
High Turnover ◽  
Kolmogorov Smirnov ◽  
Artificial Neural

Employee turnover is a common issue in any company. A high turnover phenomenon becomes a big problem that will certainly affect the performance of the company. Therefore, measuring employee turnover can be helpful to employers to improve employee retention rates and give them a head start on turnover. A study to analyze for employee loyalty has been carried out by using Logistic Regression (LR) and Artificial Neural Networks (ANN) model. Response variables such as satisfaction level, number of projects, average monthly working hours, employment period, working accident, promotion in the last 5 years, department, and salary level are used to model the employee turnover. Parameters such as accuracy, precision, sensitivity, Kolmogorov-Smirnov statistic, and Mean Squared Error (MSE) are used to compare both models.

scholarly journals A Systematic Review of Etiological Risk Factors Associated With Early Mortality Among National Football League Players

2018 ◽  
Vol 6 (12) ◽  
pp. 232596711881331 ◽  
Author(s):  
Arthur H. Owora ◽  
Brittany L. Kmush ◽  
Bhavneet Walia ◽  
Shane Sanders
Keyword(s):  
Risk Factors ◽  
Systematic Review ◽  
Mortality Risk ◽  
National Football League ◽  
The United States ◽  
Early Mortality ◽  
Male Population ◽  
Level Of Evidence ◽  
Factors Associated ◽  
Specific Mortality

Background: Multiple risks predispose professional football players to adverse health outcomes and, in extreme cases, early death; however, our understanding of etiological risk factors related to early mortality is limited. Purpose: To identify etiological risk factors associated with all-cause and cause-specific mortality among National Football League (NFL) players. Study Design: Systematic review; Level of evidence, 3. Methods: Articles examining all-cause and cause-specific mortality risk factors among previous NFL players were identified by systematically searching: PubMed, PsycINFO, Web of Science, and Google Scholar from 1990 to 2017. Study eligibility and quality were evaluated using the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) guidelines. Results: A total of 801 nonduplicated studies were identified through our search strategy. Of these, 9 studies examining 11 different risk factors were included in the systematic review. Overall, the risk of all-cause and cause-specific mortality was lower among NFL players than among the general male population in the United States. Nonwhite athletes, those in power positions, and those with a high playing-time body mass index (≥30 kg/m2) were associated with elevated all-cause and cardiovascular mortality risks. Conclusion: Methodological issues associated with the examined all-cause and cause-specific mortality risk factors preclude a definitive conclusion of etiological protective or risk effects. Comparison groups less prone to selection bias (“healthy worker effect”) and a life-course approach to the evaluation of suspected risk factors are warranted to identify etiological factors associated with early mortality among NFL players.

scholarly journals Multimorbidity and mortality

2018 ◽  
Vol 8 (1) ◽  
pp. 2235042X1880406 ◽  
Author(s):  
TG Willadsen ◽  
V Siersma ◽  
DR Nicolaisdóttir ◽  
R Køster-Rasmussen ◽  
DE Jarbøl ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Cohort Study ◽  
Prospective Cohort Study ◽  
High Mortality ◽  
Mortality Risk ◽  
Prospective Cohort ◽  
Excess Mortality ◽  
Sensory Organs ◽  
Danish Population ◽  
Increased Risk

Background: Knowledge about prevalent and deadly combinations of multimorbidity is needed. Objective: To determine the nationwide prevalence of multimorbidity and estimate mortality for the most prevalent combinations of one to five diagnosis groups. Furthermore, to assess the excess mortality of the combination of two groups compared to the product of mortality associated with the single groups. Design: A prospective cohort study using Danish registries and including 3.986.209 people aged ≥18 years on 1 January, 2000. Multimorbidity was defined as having diagnoses from at least 2 of 10 diagnosis groups: lung, musculoskeletal, endocrine, mental, cancer, neurological, gastrointestinal, cardiovascular, kidney, and sensory organs. Logistic regression (odds ratios, ORs) and ratio of ORs (ROR) were used to study mortality and excess mortality. Results: Prevalence of multimorbidity was 7.1% in the Danish population. The most prevalent combination was the musculoskeletal–cardiovascular (0.4%), which had double the mortality (OR, 2.03) compared to persons not belonging to any of the diagnosis groups but showed no excess mortality (ROR, 0.97). The neurological–cancer combination had the highest mortality (OR, 6.35), was less prevalent (0.07%), and had no excess mortality (ROR, 0.94). Cardiovascular–lung was moderately prevalent (0.2%), had high mortality (OR, 5.75), and had excess mortality (ROR, 1.18). Endocrine–kidney had high excess mortality (ROR, 1.81) and cancer–mental had low excess mortality (ROR, 0.66). Mortality increased with the number of groups. Conclusions: All combinations had increased mortality risk with some of them having up to a six-fold increased risk. Mortality increased with the number of diagnosis groups. Most combinations did not increase mortality above that expected, that is, were additive rather than synergistic.

scholarly journals A nomogram for predicting mortality in patients with COVID-19 and solid tumors: a multicenter retrospective cohort study

2020 ◽  
Vol 8 (2) ◽  
pp. e001314
Author(s):  
Chao Liu ◽  
Li Li ◽  
Kehan Song ◽  
Zhi-Ying Zhan ◽  
Yi Yao ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Solid Tumors ◽  
Neutrophil Count ◽  
Mortality Risk ◽  
Logistic Regression Model ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Lemeshow Test ◽  
Wbc Count

BackgroundIndividualized prediction of mortality risk can inform the treatment strategy for patients with COVID-19 and solid tumors and potentially improve patient outcomes. We aimed to develop a nomogram for predicting in-hospital mortality of patients with COVID-19 with solid tumors.MethodsWe enrolled patients with COVID-19 with solid tumors admitted to 32 hospitals in China between December 17, 2020, and March 18, 2020. A multivariate logistic regression model was constructed via stepwise regression analysis, and a nomogram was subsequently developed based on the fitted multivariate logistic regression model. Discrimination and calibration of the nomogram were evaluated by estimating the area under the receiver operator characteristic curve (AUC) for the model and by bootstrap resampling, a Hosmer-Lemeshow test, and visual inspection of the calibration curve.ResultsThere were 216 patients with COVID-19 with solid tumors included in the present study, of whom 37 (17%) died and the other 179 all recovered from COVID-19 and were discharged. The median age of the enrolled patients was 63.0 years and 113 (52.3%) were men. Multivariate logistic regression revealed that increasing age (OR=1.08, 95% CI 1.00 to 1.16), receipt of antitumor treatment within 3 months before COVID-19 (OR=28.65, 95% CI 3.54 to 231.97), peripheral white blood cell (WBC) count ≥6.93 ×109/L (OR=14.52, 95% CI 2.45 to 86.14), derived neutrophil-to-lymphocyte ratio (dNLR; neutrophil count/(WBC count minus neutrophil count)) ≥4.19 (OR=18.99, 95% CI 3.58 to 100.65), and dyspnea on admission (OR=20.38, 95% CI 3.55 to 117.02) were associated with elevated mortality risk. The performance of the established nomogram was satisfactory, with an AUC of 0.953 (95% CI 0.908 to 0.997) for the model, non-significant findings on the Hosmer-Lemeshow test, and rough agreement between predicted and observed probabilities as suggested in calibration curves. The sensitivity and specificity of the model were 86.4% and 92.5%.ConclusionIncreasing age, receipt of antitumor treatment within 3 months before COVID-19 diagnosis, elevated WBC count and dNLR, and having dyspnea on admission were independent risk factors for mortality among patients with COVID-19 and solid tumors. The nomogram based on these factors accurately predicted mortality risk for individual patients.

Sign in / Sign up

Export Citation Format

Share Document