scholarly journals Identification of Risk Factors Prospectively Associated With Musculoskeletal Injury in a Warrior Athlete Population

2020 ◽  
Vol 12 (6) ◽  
pp. 564-572 ◽  
Author(s):  
Deydre S. Teyhen ◽  
Scott W. Shaffer ◽  
Stephen L. Goffar ◽  
Kyle Kiesel ◽  
Robert J. Butler ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Injury Risk ◽  
Characteristic Curve ◽  
Musculoskeletal Injuries ◽  
Regression Equation ◽  
Individual Risk ◽  
Care Utilization ◽  
Chi Square Analysis ◽  
Logistic Regression Equation

Background: Musculoskeletal injuries are a primary source of disability. Understanding how risk factors predict injury is necessary to individualize and enhance injury reduction programs. Hypothesis: Because of the multifactorial nature of musculoskeletal injuries, multiple risk factors will provide a useful method of categorizing warrior athletes based on injury risk. Study Design: Prospective observational cohort study. Level of Evidence: Level 2. Methods: Baseline data were collected on 922 US Army soldiers/warrior athletes (mean age, 24.7 ± 5.2 years; mean body mass index, 26.8 ± 3.4 kg/m2) using surveys and physical measures. Injury occurrence and health care utilization were collected for 1 year. Variables were compared in healthy versus injured participants using independent t tests or chi-square analysis. Significantly different factors between each group were entered into a logistic regression equation. Receiver operating characteristic curve and accuracy statistics were calculated for regression variables. Results: Of the 922 warrior athletes, 38.8% suffered a time-loss injury (TLI). Overall, 35 variables had a significant relationship with TLIs. The logistic regression equation, consisting of 11 variables of interest, was significant (adjusted R2 = 0.21; odds ratio, 5.7 [95% CI, 4.1-7.9]; relative risk, 2.5 [95% CI, 2.1-2.9]; area under the curve, 0.73). Individuals with 2 variables had a sensitivity of 0.89, those with 7 or more variables had a specificity of 0.94. Conclusion: The sum of individual risk factors (prior injury, prior work restrictions, lower perceived recovery from injury, asymmetrical ankle dorsiflexion, decreased or asymmetrical performance on the Lower and Upper Quarter Y-Balance test, pain with movement, slower 2-mile run times, age, and sex) produced a highly sensitive and specific multivariate model for TLI in military servicemembers. Clinical Relevance: A better understanding of characteristics associated with future injury risk can provide a foundation for prevention programs designed to reduce medical costs and time lost.

Predicting Success or Failure on Probation: Factors Associated with Felony Probation Outcomes

1997 ◽  
Vol 43 (3) ◽  
pp. 314-327 ◽  
Author(s):  
Barbara Sims ◽  
Mark Jones
Keyword(s):  
Risk Assessment ◽  
North Carolina ◽  
Logistic Regression ◽  
Regression Equation ◽  
Probation Officers ◽  
Chi Square ◽  
Factors Associated ◽  
Predicting Success ◽  
Chi Square Analysis ◽  
Logistic Regression Equation

This study examined the factors associated with success or failure on probation for 2,850 North Carolina felony probationers who were removed from supervision between July 1 and October 31, 1993. Probationers were profiled on various demographic, sentence, and probation characteristics. Chi-square analysis was used to determine differences within various subgroups of the sample, and logistic regression was used to predict failure on probation in two separate models. The findings suggest that risk assessment items used by probation officers to determine level of supervision for probationers perform well in a logistic regression equation.

scholarly journals Development of a new sternal dehiscence prediction scale for decision making in sternal closure techniques after cardiac surgery

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Ehab Nooh ◽  
Colin Griesbach ◽  
Johannes Rösch ◽  
Michael Weyand ◽  
Frank Harig
Keyword(s):  
Logistic Regression ◽  
Risk Score ◽  
Characteristic Curve ◽  
Multivariable Analysis ◽  
Individual Risk ◽  
Dependent Diabetes Mellitus ◽  
Analysis Model ◽  
Multivariable Logistic Regression Model ◽  
Sternal Dehiscence ◽  
Multivariable Logistic Regression

Abstract Background After sternotomy, the spectrum for sternal osteosynthesis comprises standard wiring and more complex techniques, like titanium plating. The aim of this study is to develop a predictive risk score that evaluates the risk of sternum instability individually. The surgeon may then choose an appropriate sternal osteosynthesis technique that is risk- adjusted as well as cost-effective. Methods Data from 7.173 patients operated via sternotomy for all cardiovascular indications from 2008 until 2017 were retrospectively analyzed. Sternal dehiscence occurred in 2.5% of patients (n = 176). A multivariable analysis model examined pre- and intraoperative factors. A multivariable logistic regression model and a backward elimination based on the Akaike Information Criterion (AIC) a logistic model were selected. Results The model showed good sensitivity and specificity (area under the receiver-operating characteristic curve, AUC: 0.76) and several predictors of sternal instability could be evaluated. Multivariable logistic regression showed the highest Odds Ratios (OR) for reexploration (OR 6.6, confidence interval, CI [4.5–9.5], p < 0.001), obesity (body mass index, BMI > 35 kg/m2) (OR 4.23, [CI 2.4–7.3], p < 0.001), insulin-dependent diabetes mellitus (IDDM) (OR 2.2, CI [1.5–3.2], p = 0.01), smoking (OR 2.03, [CI 1.3–3.08], p = 0.001). After weighting the probability of sternum dehiscence with each factor, a risk score model was proposed scaling from − 1 to 5 points. This resulted in a risk score ranging up to 18 points, with an estimated risk for sternum complication up to 74%. Conclusions A weighted scoring system based on individual risk factors was specifically created to predict sternal dehiscence. High-scoring patients should receive additive closure techniques.

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

2021 ◽  
pp. 1-10
Author(s):  
I. Krug ◽  
J. Linardon ◽  
C. Greenwood ◽  
G. Youssef ◽  
J. Treasure ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Prediction Rule ◽  
Predictive Performance ◽  
Individual Risk ◽  
European Project ◽  
Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

scholarly journals Development and validation of a clinical and genetic model for predicting risk of severe COVID-19

2021 ◽  
Author(s):  
Gillian S. Dite ◽  
Nicholas M. Murphy ◽  
Richard Allman
Keyword(s):  
Logistic Regression ◽  
Genetic Model ◽  
Characteristic Curve ◽  
Accurate Prediction ◽  
Training Dataset ◽  
Validation Dataset ◽  
Individual Risk ◽  
Prototype Model ◽  
List Type ◽  
New Model

SummaryClinical and genetic risk factors for severe COVID-19 are often considered independently and without knowledge of the magnitudes of their effects on risk. Using SARS-CoV-2 positive participants from the UK Biobank, we developed and validated a clinical and genetic model to predict risk of severe COVID-19. We used multivariable logistic regression on a 70% training dataset and used the remaining 30% for validation. We also validated a previously published prototype model. In the validation dataset, our new model was associated with severe COVID-19 (odds ratio per quintile of risk=1.77, 95% confidence interval [CI]=1.64, 1.90) and had excellent discrimination (area under the receiver operating characteristic curve=0.732, 95% CI=0.708, 0.756). We assessed calibration using logistic regression of the log odds of the risk score, and the new model showed no evidence of over- or under-estimation of risk (α=−0.08; 95% CI=−0.21, 0.05) and no evidence or over- or under-dispersion of risk (β=0.90, 95% CI=0.80, 1.00). Accurate prediction of individual risk is possible and will be important in regions where vaccines are not widely available or where people refuse or are disqualified from vaccination, especially given uncertainty about the extent of infection transmission among vaccinated people and the emergence of SARS-CoV-2 variants of concern.Key resultsAccurate prediction of the risk of severe COVID-19 can inform public heath interventions and empower individuals to make informed choices about their day-to-day activities.Age and sex alone do not accurately predict risk of severe COVID-19.Our clinical and genetic model to predict risk of severe COVID-19 performs extremely well in terms of discrimination and calibration.

scholarly journals Logistic regression model to predict acute uncomplicated and complicated appendicitis

2019 ◽  
Vol 101 (2) ◽  
pp. 107-118 ◽  
Author(s):  
MMR Eddama ◽  
KC Fragkos ◽  
S Renshaw ◽  
M Aldridge ◽  
G Bough ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Multivariate Analysis ◽  
Odds Ratio ◽  
Web Application ◽  
Univariate Analysis ◽  
Complicated Appendicitis ◽  
Regression Equation ◽  
Normal Appendix ◽  
Uncomplicated Appendicitis ◽  
Logistic Regression Equation

Introduction While patients with acute uncomplicated appendicitis may be treated conservatively, those who suffer from complicated appendicitis require surgery. We describe a logistic regression equation to calculate the likelihood of acute uncomplicated appendicitis and complicated appendicitis in patients presenting to the emergency department with suspected acute appendicitis. Materials and methods A cohort of 895 patients who underwent appendicectomy were analysed retrospectively. Depending on the final histology, patients were divided into three groups; normal appendix, acute uncomplicated appendicitis and complicated appendicitis. Normal appendix was considered the reference category, while acute uncomplicated appendicitis and complicated appendicitis were the nominal categories. Multivariate and univariate regression models were undertaken to detect independent variables with significant odds ratio that can predict acute uncomplicated appendicitis and complicated appendicitis. Subsequently, a logistic regression equation was generated to produce the likelihood acute uncomplicated appendicitis and complicated appendicitis. Results Pathological diagnosis of normal appendix, acute uncomplicated appendicitis and complicated appendicitis was identified in 188 (21%), 525 (59%) and 182 patients (20%), respectively. The odds ratio from a univariate analysis to predict complicated appendicitis for age, female gender, log2 white cell count, log2 C-reactive protein and log2 bilirubin were 1.02 (95% confidence interval, CI, 1.01, 1.04), 2.37 (95% CI 1.51, 3.70), 9.74 (95% CI 5.41, 17.5), 1.57 (95% CI 1.40, 1.74), 2.08 (95% CI 1.56, 2.76), respectively. For the same variable, similar odds ratios were demonstrated in a multivariate analysis to predict complicated appendicitis and univariate and multivariate analysis to predict acute uncomplicated appendicitis. Conclusions The likelihood of acute uncomplicated appendicitis and complicated appendicitis can be calculated by using the reported predictive equations integrated into a web application at www.appendistat.com. This will enable clinicians to determine the probability of appendicitis and the need for urgent surgery in case of complicated appendicitis.

scholarly journals Incidence and Risk Factors of Postoperative Pulmonary Complications in Noncardiac Chinese Patients: A Multicenter Observational Study in University Hospitals

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Yue Jin ◽  
Guohao Xie ◽  
Haihong Wang ◽  
Lielie Jin ◽  
Jun Li ◽  
...  
Keyword(s):  
Risk Factors ◽  
Characteristic Curve ◽  
Risk Index ◽  
Pulmonary Complications ◽  
Hospital Length Of Stay ◽  
Chinese Patients ◽  
Individual Risk ◽  
Postoperative Pulmonary Complications ◽  
University Hospitals ◽  
Predictive Risk

Purpose. To assess the incidence of postoperative pulmonary complications (PPCs) in Chinese inpatients, and to develop a brief predictive risk index.Methods. Between August 6, 2012, and August 12, 2012, patients undergoing noncardiac operations in four university hospitals were enrolled. The cohort was divided into two subsamples, cohort 1 to develop a predictive risk index of PPCs and cohort 2 to validate it.Results. 1673 patients were enrolled. PPCs were recorded for 163 patients (9.7%), of whom the hospital length of stay (LOS) was longer (P<0.001). The mortality was 1.84% in patients with PPCs and 0.07% in those without. Logistic Regression modeling in cohort 1 identified nine independent risk factors, including smoking, respiratory infection in the last month, preoperative antibiotic use, preoperative saturation of peripheral oxygen, surgery site, blood lost, postoperative blood glucose, albumin, and ventilation. The model was validated within cohort 2 with an area under the receiver operating characteristic curve of 0.90 (95% CI 0.86 to 0.94).Conclusions. PPCs are common in noncardiac surgical patients and are associated with prolonged LOS in China. The current study developed a risk index, which can be used to assess individual risk of PPCs and guide individualized perioperative respiratory care.

scholarly journals A Bayesian Model to Analyze the Association of Rheumatoid Arthritis With Risk Factors and Their Interactions

2021 ◽  
Vol 9 ◽  
Author(s):  
Leon Lufkin ◽  
Marko Budišić ◽  
Sumona Mondal ◽  
Shantanu Sur
Keyword(s):  
Rheumatoid Arthritis ◽  
Risk Factors ◽  
Characteristic Curve ◽  
Strong Association ◽  
Mixed Data ◽  
Validation Dataset ◽  
Individual Risk ◽  
Third Order ◽  
Cross Sectional ◽  
Organ Systems

Rheumatoid arthritis (RA) is a chronic autoimmune disorder that commonly manifests as destructive joint inflammation but also affects multiple other organ systems. The pathogenesis of RA is complex where a variety of factors including comorbidities, demographic, and socioeconomic variables are known to associate with RA and influence the progress of the disease. In this work, we used a Bayesian logistic regression model to quantitatively assess how these factors influence the risk of RA, individually and through their interactions. Using cross-sectional data from the National Health and Nutrition Examination Survey (NHANES), a set of 11 well-known RA risk factors such as age, gender, ethnicity, body mass index (BMI), and depression were selected to predict RA. We considered up to third-order interactions between the risk factors and implemented factor analysis of mixed data (FAMD) to account for both the continuous and categorical natures of these variables. The model was further optimized over the area under the receiver operating characteristic curve (AUC) using a genetic algorithm (GA) with the optimal predictive model having a smoothed AUC of 0.826 (95% CI: 0.801–0.850) on a validation dataset and 0.805 (95% CI: 0.781–0.829) on a holdout test dataset. Apart from corroborating the influence of individual risk factors on RA, our model identified a strong association of RA with multiple second- and third-order interactions, many of which involve age or BMI as one of the factors. This observation suggests a potential role of risk-factor interactions in RA disease mechanism. Furthermore, our findings on the contribution of RA risk factors and their interactions to disease prediction could be useful in developing strategies for early diagnosis of RA.

scholarly journals MetS Risk Score: A Clear Scoring Model to Predict a 3-Year Risk for Metabolic Syndrome

2018 ◽  
Vol 50 (09) ◽  
pp. 683-689 ◽  
Author(s):  
Tian-Tian Zou ◽  
Yu-Jie Zhou ◽  
Xiao-Dong Zhou ◽  
Wen-Yue Liu ◽  
Sven Van Poucke ◽  
...  
Keyword(s):  
Risk Factors ◽  
Metabolic Syndrome ◽  
Risk Score ◽  
Validation Cohort ◽  
Medical Center ◽  
Characteristic Curve ◽  
Model Development ◽  
Predictive Performance ◽  
Risk Scores ◽  
Individual Risk

AbstractAlthough several risk factors for metabolic syndrome (MetS) have been reported, there are few clinical scores that predict its incidence. Therefore, we created and validated a risk score for prediction of 3-year risk for MetS. Three-year follow-up data of 4395 initially MetS-free subjects, enrolled for an annual physical examination from Wenzhou Medical Center were analyzed. Subjects at enrollment were randomly divided into the training and the validation cohort. Univariate and multivariate logistic regression models were employed for model development. The selected variables were assigned an integer or half-integer risk score proportional to the estimated coefficient from the logistic model. Risk scores were tested in a validation cohort. The predictive performance of the model was tested by computing the area under the receiver operating characteristic curve (AUROC). Four independent predictors were chosen to construct the MetS risk score, including BMI (HR=1.906, 95% CI: 1.040–1.155), FPG (HR=1.507, 95% CI: 1.305–1.741), DBP (HR=1.061, 95% CI: 1.002–1.031), HDL-C (HR=0.539, 95% CI: 0.303–0.959). The model was created as –1.5 to 4 points, which demonstrated a considerable discrimination both in the training cohort (AUROC=0.674) and validation cohort (AUROC=0.690). Comparison of the observed with the estimated incidence of MetS revealed satisfactory precision. We developed and validated the MetS risk score with 4 risk factors to predict 3-year risk of MetS, useful for assessing the individual risk for MetS in medical practice.

scholarly journals Risk Factors for Neonatal Sepsis: A Retrospective Case-Control Study among Neonates Who Were Delivered by Caesarean Section at the Trauma and Specialist Hospital, Winneba, Ghana

2018 ◽  
Vol 2018 ◽  
pp. 1-7 ◽  
Author(s):  
Peter Adatara ◽  
Agani Afaya ◽  
Solomon Mohammed Salia ◽  
Richard Adongo Afaya ◽  
Anthony K. Kuug ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Caesarean Section ◽  
Neonatal Sepsis ◽  
Case Control Study ◽  
Case Control ◽  
Multivariate Logistic Regression ◽  
Retrospective Case ◽  
Chi Square Analysis ◽  
Control Study

The third Sustainable Development Goal (SDG) for child health, which targets ending preventable deaths of neonates and children under five years of age by 2030, may not be met without substantial reduction of neonatal sepsis-specific mortality in developing countries. This study aimed at assessing the prevalence and risk factors for neonatal sepsis among neonates who were delivered via caesarean section. A retrospective case-control study was conducted among neonates who were delivered via caesarean section at the Trauma and Specialist Hospital, Winneba, Ghana. Data collection lasted for 4 weeks. The extracted data were double-entered using Epidata software version 3.1 to address discrepancies of data entry. Descriptive statistics such as frequencies and percentages of neonatal characteristics were generated from the data. Both univariate and multivariate logistic regression were used to determine associations between neonatal sepsis and neonatal characteristics with odds ratios, 95% confidence intervals, and p values calculated using variables that showed significant association (p<0.05) in the chi-square analysis for the multivariate logistic regression. A total of 383 neonates were recruited; 67 (17.5%) had sepsis (cases). The neonatal risk factors associated with sepsis were birth weight (χ2=6.64, p=0.036), neonatal age (χ2=38.31, p<0.001), meconium passed (χ2=12.95, p<0.001), reason for CS (χ2=24.27, p<0.001), and the duration of stay on admission (χ2=36.69, p<0.001). Neonatal sepsis poses a serious threat to the survival of the newborn as the current study uncovered 6.0% deaths among sepsis cases. The findings of this study highlight the need for routine assessment of neonates in order to identify risk factors for neonatal sepsis and to curb the disease burden on neonatal mortality.

Sign in / Sign up

Export Citation Format

Share Document