Pre-season screening currently has no value for injury prediction: The development and internal validation of a multivariable prognostic model to predict indirect muscle injury risk in elite football (soccer) players

ABSTRACTBackgroundIn elite football (soccer), periodic health examination (PHE) could provide prognostic factors to predict injury risk.ObjectiveTo develop and internally validate a prognostic model to predict individual indirect (non-contact) muscle injury (IMI) risk during a season in elite footballers, only using PHE-derived candidate prognostic factors.MethodsRoutinely collected preseason PHE and injury data were used from 119 players over 5 seasons (1st July 2013 to 19th May 2018). Ten candidate prognostic factors (12 parameters) were included in model development. Multiple imputation was used to handle missing values. The outcome was any time-loss, index indirect muscle injury (I-IMI) affecting the lower extremity. A full logistic regression model was fitted, and a parsimonious model developed using backward-selection to remove non-significant factors. Predictive performance was assessed through calibration, discrimination and decision-curve analysis, averaged across all imputed datasets. The model was internally validated using bootstrapping and adjusted for overfitting.ResultsDuring 317 participant-seasons, 138 I-IMIs were recorded. The parsimonious model included only age and frequency of previous IMIs; apparent calibration was perfect but discrimination was modest (C-index = 0.641, 95% confidence interval (CI): 0.580 to 0.703), with clinical utility evident between risk thresholds of 37-71%. After validation and overfitting adjustment, performance deteriorated (C-index = 0.580; calibration-in-the-large =-0.031, calibration slope =0.663).ConclusionThe selected PHE data were insufficient prognostic factors from which to develop a useful model for predicting IMI risk in elite footballers. Further research should prioritise identifying novel prognostic factors to improve future risk prediction models in this field.Trial registration numberNCT03782389KEY POINTSFactors measured through preseason screening generally have weak prognostic strength for future indirect muscle injuries and further research is needed to identify novel, robust prognostic factors.Because of sample size restrictions, and until the evidence base improves, it is likely that any further attempts at creating a prognostic model at individual club level would also suffer from poor performance.The value of using preseason screening data to make injury predictions or to select bespoke injury prevention strategies remains to be demonstrated, so screening should only be considered as useful for detection of salient pathology or for rehabilitation/ performance monitoring purposes at this time.

Download Full-text

Can prognostic factors for indirect muscle injuries in elite football (soccer) players be identified using data from preseason screening? An exploratory analysis using routinely-collected periodic health examination records

10.1101/2021.01.15.21249653 ◽

2021 ◽

Author(s):

Tom Hughes ◽

Richard D. Riley ◽

Michael J. Callaghan ◽

Jamie C. Sergeant

Keyword(s):

Injury Risk ◽

Football Players ◽

Health Examination ◽

Periodic Health Examination ◽

Muscle Injuries ◽

Time Loss ◽

Logistic Regression Models ◽

Non Linear ◽

Multivariable Analyses ◽

Using Data

ABSTRACTThis study used periodic health examination (PHE) data from 134 outfield elite male football players, over 5 seasons (1st July 2013 to 19th May 2018). Univariable and multivariable logistic regression models were used to determine prognostic associations between 36 variables and time-loss, lower extremity index indirect muscle injuries (I-IMIs). Non-linear associations were explored using fractional polynomials. During 317 participant-seasons, 138 I-IMIs were recorded. Univariable associations were determined for previous calf indirect muscle injury (IMI) frequency (OR=1.80, 95% confidence interval (CI) = 1.09 to 2.97), hamstring IMI frequency (OR=1.56, 95% CI=1.17 to 2.09), if the most recent hamstring IMI occurred > 12 months but < 3 years prior to PHE (OR= 2.95, 95% CI = 1.51 to 5.73) and age (OR =1.12 per 1-year increase, 95% CI = 1.06 to 1.18). Multivariable analyses demonstrated that if a player’s most recent previous hamstring IMI was >12 months but <3 years prior to PHE (OR= 2.24, 95% CI = 1.11 to 4.53), then this was the only variable with added prognostic value over and above age (OR=1.12 per 1-year increase, 95%CI = 1.05 to 1.18). Allowing non-linear associations conferred no advantage over linear ones. Therefore, PHE has limited use for injury risk prediction.

Download Full-text

The Value of Preseason Screening for Injury Prediction: The Development and Internal Validation of a Multivariable Prognostic Model to Predict Indirect Muscle Injury Risk in Elite Football (Soccer) Players

Sports Medicine - Open ◽

10.1186/s40798-020-00249-8 ◽

2020 ◽

Vol 6 (1) ◽

Author(s):

Tom Hughes ◽

Richard D. Riley ◽

Michael J. Callaghan ◽

Jamie C. Sergeant

Keyword(s):

Muscle Injury ◽

Injury Risk ◽

Prognostic Model ◽

Soccer Players ◽

Internal Validation ◽

Injury Prediction

Download Full-text

A study protocol for the development and internal validation of a multivariable prognostic model to determine lower extremity muscle injury risk in elite football (soccer) players, with further exploration of prognostic factors

Diagnostic and Prognostic Research ◽

10.1186/s41512-019-0063-8 ◽

2019 ◽

Vol 3 (1) ◽

Cited By ~ 2

Author(s):

Tom Hughes ◽

Richard Riley ◽

Jamie C. Sergeant ◽

Michael J. Callaghan

Keyword(s):

Logistic Regression ◽

Prognostic Factors ◽

Clinical Reasoning ◽

Prognostic Model ◽

Model Development ◽

Health Examination ◽

Prevention Strategies ◽

Internal Validation ◽

Risk Estimates ◽

Multivariable Logistic Regression

Abstract Background Indirect muscle injuries (IMIs) are a considerable burden to elite football (soccer) teams, and prevention of these injuries offers many benefits. Preseason medical, musculoskeletal and performance screening (termed periodic health examination (PHE)) can be used to help determine players at risk of injuries such as IMIs, where identification of PHE-derived prognostic factors (PF) may inform IMI prevention strategies. Furthermore, using several PFs in combination within a multivariable prognostic model may allow individualised IMI risk estimation and specific targeting of prevention strategies, based upon an individual’s PF profile. No such models have been developed in elite football and the current IMI prognostic factor evidence is limited. This study aims to (1) develop and internally validate a prognostic model for individualised IMI risk prediction within a season in elite footballers, using the extent of the prognostic evidence and clinical reasoning; and (2) explore potential PHE-derived PFs associated with IMI outcomes in elite footballers, using available PHE data from a professional team. Methods This is a protocol for a retrospective cohort study. PHE and injury data were routinely collected over 5 seasons (1 July 2013 to 19 May 2018), from a population of elite male players aged 16–40 years old. Of 60 candidate PFs, 15 were excluded. Twelve variables (derived from 10 PFs) will be included in model development that were identified from a systematic review, missing data assessment, measurement reliability evaluation and clinical reasoning. A full multivariable logistic regression model will be fitted, to ensure adjustment before backward elimination. The performance and internal validation of the model will be assessed. The remaining 35 candidate PFs are eligible for further exploration, using univariable logistic regression to obtain unadjusted risk estimates. Exploratory PFs will also be incorporated into multivariable logistic regression models to determine risk estimates whilst adjusting for age, height and body weight. Discussion This study will offer insights into clinical usefulness of a model to predict IMI risk in elite football and highlight the practicalities of model development in this setting. Further exploration may identify other relevant PFs for future confirmatory studies and model updating, or influence future injury prevention research.

Download Full-text

A novel GPU based intrusion detection system using deep autoencoder with Fruitfly optimization

SN Applied Sciences ◽

10.1007/s42452-021-04579-4 ◽

2021 ◽

Vol 3 (6) ◽

Author(s):

R. Sekhar ◽

K. Sasirekha ◽

P. S. Raja ◽

K. Thangavel

Keyword(s):

Intrusion Detection ◽

Intrusion Detection System ◽

Missing Values ◽

Detection System ◽

Radial Basis Function Network ◽

Detection Methods ◽

Support Vector ◽

Parameter Method ◽

List Type ◽

Fuzzy C Means

Abstract Intrusion Detection Systems (IDSs) have received more attention to safeguarding the vital information in a network system of an organization. Generally, the hackers are easily entering into a secured network through loopholes and smart attacks. In such situation, predicting attacks from normal packets is tedious, much challenging, time consuming and highly technical. As a result, different algorithms with varying learning and training capacity have been explored in the literature. However, the existing Intrusion Detection methods could not meet the desired performance requirements. Hence, this work proposes a new Intrusion Detection technique using Deep Autoencoder with Fruitfly Optimization. Initially, missing values in the dataset have been imputed with the Fuzzy C-Means Rough Parameter (FCMRP) algorithm which handles the imprecision in datasets with the exploit of fuzzy and rough sets while preserving crucial information. Then, robust features are extracted from Autoencoder with multiple hidden layers. Finally, the obtained features are fed to Back Propagation Neural Network (BPN) to classify the attacks. Furthermore, the neurons in the hidden layers of Deep Autoencoder are optimized with population based Fruitfly Optimization algorithm. Experiments have been conducted on NSL_KDD and UNSW-NB15 dataset. The computational results of the proposed intrusion detection system using deep autoencoder with BPN are compared with Naive Bayes, Support Vector Machine (SVM), Radial Basis Function Network (RBFN), BPN, and Autoencoder with Softmax. Article Highlights A hybridized model using Deep Autoencoder with Fruitfly Optimization is introduced to classify the attacks. Missing values have been imputed with the Fuzzy C-Means Rough Parameter method. The discriminate features are extracted using Deep Autoencoder with more hidden layers.

Download Full-text

Ultrasound Imaging Evaluation of Textural Features in Athletes with Soleus Pathology—A Novel Case-Control Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18041983 ◽

2021 ◽

Vol 18 (4) ◽

pp. 1983 ◽

Cited By ~ 1

Author(s):

Blanca De-la-Cruz-Torres ◽

Emmanuel Navarro-Flores ◽

Daniel López-López ◽

Carlos Romero-Morales

Keyword(s):

Ultrasound Imaging ◽

Soleus Muscle ◽

Muscle Injury ◽

Intraclass Correlation ◽

Muscle Thickness ◽

Tendon Injury ◽

Muscle Injuries ◽

Imaging Evaluation ◽

Rater Reliability ◽

Group A

Background: the aim of this study was to compare the echotexture of patients with soleus muscle injury and age matched controls. Methods: a sample of 62 athletes was recruited at the private clinic and was divided in two group: a healthy group (n = 31) and a soleus pathology group whose athletes had soleus muscle injury, located in the central tendon (n = 31). The muscle thickness (MTh), echointensity (EI) and echovariation (EV) were analyzed. An intra-rater reliability test (Intraclass Correlation Coefficient-ICC) was performed in order to analyze the reliability of the values of the measurements. Results: Sociodemographic variables did not show statistically significant differences (p > 0.05). Ultrasound imaging measurements who reported statistically significant differences were EI (p = 0.001) and standard deviation (SD) (p = 0.001). MTh and EV variables did not show statistically significant differences (p = 0.381 and p = 0.364, respectively). Moreover, reliability values for the MTh (ICC = 0.911), EI (ICC = 0.982), SD (ICC = 0.955) and EV (ICC = 0.963). Based on these results the intra-rater reliability was considered excellent. Conclusion: Athletes with a central tendon injury of soleus muscle showed a lower EI when they were compared to healthy athletes. The echogenicity showed by the quantitative ultrasound imaging measurement may be a more objective parameter for the diagnosis and follow-up the soleus muscle injuries.

Download Full-text

Predicting hospital admissions from individual patient data (IPD): an applied example to explore key elements driving external validity

BMJ Open ◽

10.1136/bmjopen-2020-045572 ◽

2021 ◽

Vol 11 (8) ◽

pp. e045572

Author(s):

Andreas Daniel Meid ◽

Ana Isabel Gonzalez-Gonzalez ◽

Truc Sophia Dinh ◽

Jeanet Blom ◽

Marjan van den Akker ◽

...

Keyword(s):

Prognostic Model ◽

Prediction Models ◽

Hospital Admissions ◽

Absolute Risk ◽

External Validation ◽

Baseline Risk ◽

Study Heterogeneity ◽

Related Quality ◽

Individual Participant ◽

Risk Predictor

ObjectiveTo explore factors that potentially impact external validation performance while developing and validating a prognostic model for hospital admissions (HAs) in complex older general practice patients.Study design and settingUsing individual participant data from four cluster-randomised trials conducted in the Netherlands and Germany, we used logistic regression to develop a prognostic model to predict all-cause HAs within a 6-month follow-up period. A stratified intercept was used to account for heterogeneity in baseline risk between the studies. The model was validated both internally and by using internal-external cross-validation (IECV).ResultsPrior HAs, physical components of the health-related quality of life comorbidity index, and medication-related variables were used in the final model. While achieving moderate discriminatory performance, internal bootstrap validation revealed a pronounced risk of overfitting. The results of the IECV, in which calibration was highly variable even after accounting for between-study heterogeneity, agreed with this finding. Heterogeneity was equally reflected in differing baseline risk, predictor effects and absolute risk predictions.ConclusionsPredictor effect heterogeneity and differing baseline risk can explain the limited external performance of HA prediction models. With such drivers known, model adjustments in external validation settings (eg, intercept recalibration, complete updating) can be applied more purposefully.Trial registration numberPROSPERO id: CRD42018088129.

Download Full-text

Integrated analysis of methylation-driven genes and pretreatment prognostic factors in patients with hepatocellular carcinoma

BMC Cancer ◽

10.1186/s12885-021-08314-5 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Dongsheng He ◽

Shengyin Liao ◽

Lifang Cai ◽

Weiming Huang ◽

Xuehua Xie ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Prognostic Factors ◽

Risk Score ◽

Prognostic Model ◽

Cox Regression ◽

The Cancer Genome Atlas ◽

Integrated Analysis ◽

Calibration Plot ◽

Clinical Parameters ◽

T Stage

Abstract Background The potential reversibility of aberrant DNA methylation indicates an opportunity for oncotherapy. This study aimed to integrate methylation-driven genes and pretreatment prognostic factors and then construct a new individual prognostic model in hepatocellular carcinoma (HCC) patients. Methods The gene methylation, gene expression dataset and clinical information of HCC patients were downloaded from The Cancer Genome Atlas (TCGA) database. Methylation-driven genes were screened with a Pearson’s correlation coefficient less than − 0.3 and a P value less than 0.05. Univariable and multivariable Cox regression analyses were performed to construct a risk score model and identify independent prognostic factors from the clinical parameters of HCC patients. The least absolute shrinkage and selection operator (LASSO) technique was used to construct a nomogram that might act to predict an individual’s OS, and then C-index, ROC curve and calibration plot were used to test the practicability. The correlation between clinical parameters and core methylation-driven genes of HCC patients was explored with Student’s t-test. Results In this study, 44 methylation-driven genes were discovered, and three prognostic signatures (LCAT, RPS6KA6, and C5orf58) were screened to construct a prognostic risk model of HCC patients. Five clinical factors, including T stage, risk score, cancer status, surgical method and new tumor events, were identified from 13 clinical parameters as pretreatment-independent prognostic factors. To avoid overfitting, LASSO analysis was used to construct a nomogram that could be used to calculate the OS in HCC patients. The C-index was superior to that from previous studies (0.75 vs 0.717, 0.676). Furthermore, LCAT was found to be correlated with T stage and new tumor events, and RPS6KA6 was found to be correlated with T stage. Conclusion We identified novel therapeutic targets and constructed an individual prognostic model that can be used to guide personalized treatment in HCC patients.

Download Full-text

A novel prognostic model for angioimmunoblastic T-cell lymphoma: A retrospective study of 55 cases

Journal of International Medical Research ◽

10.1177/03000605211013274 ◽

2021 ◽

Vol 49 (5) ◽

pp. 030006052110132

Author(s):

Jie Sun ◽

Sha He ◽

Hong Cen ◽

Da Zhou ◽

Zhe Li ◽

...

Keyword(s):

Prognostic Factors ◽

T Cell ◽

Prognostic Model ◽

Proportional Hazards Model ◽

Cell Lymphoma ◽

Initial Diagnosis ◽

Cox Proportional Hazards Model ◽

T Cell Lymphoma ◽

Chinese Patients ◽

Angioimmunoblastic T Cell Lymphoma

Objective To explore prognostic factors and develop an accurate prognostic prediction model for angioimmunoblastic T-cell lymphoma (AITL). Methods Clinical data from Chinese patients with newly diagnosed AITL were retrospectively analysed. Overall survival (OS) and progression-free survival (PFS) were estimated using Kaplan-Meier method survival curves; prognostic factors were determined using a Cox proportional hazards model. The sensitivity and specificity of the predicted survival rates were compared using area under the curve (AUC) of receiver operating characteristic (ROC) curves. Results The estimated 5-year OS and PFS of 55 eligible patients with AITL were 22% and 3%, respectively. Multivariate analysis showed that the presence of pneumonia, and serous cavity effusions at initial diagnosis were significant prognostic factors for OS. Based on AUC ROC values, our novel prognostic model was superior to IPI and PIT based models and suggested better diagnostic accuracy. Conclusions Our prognostic model based on pneumonia, and serous cavity effusions at initial diagnosis enabled a balanced classification of AITL patients into different risk groups.

Download Full-text

Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18105332 ◽

2021 ◽

Vol 18 (10) ◽

pp. 5332

Author(s):

Po-Hsiang Lin ◽

Jer-Guang Hsieh ◽

Hsien-Chung Yu ◽

Jyh-Horng Jeng ◽

Chiao-Lin Hsu ◽

...

Keyword(s):

Barrett’S Esophagus ◽

Risk Prediction ◽

Barrett's Esophagus ◽

Gastrointestinal Endoscopy ◽

Prediction Models ◽

Upper Gastrointestinal Endoscopy ◽

Health Examination ◽

Endoscopic Screening ◽

Risk Prediction Models ◽

Upper Gastrointestinal

Determining the target population for the screening of Barrett’s esophagus (BE), a precancerous condition of esophageal adenocarcinoma, remains a challenge in Asia. The aim of our study was to develop risk prediction models for BE using logistic regression (LR) and artificial neural network (ANN) methods. Their predictive performances were compared. We retrospectively analyzed 9646 adults aged ≥20 years undergoing upper gastrointestinal endoscopy at a health examinations center in Taiwan. Evaluated by using 10-fold cross-validation, both models exhibited good discriminative power, with comparable area under curve (AUC) for the LR and ANN models (Both AUC were 0.702). Our risk prediction models for BE were developed from individuals with or without clinical indications of upper gastrointestinal endoscopy. The models have the potential to serve as a practical tool for identifying high-risk individuals of BE among the general population for endoscopic screening.

Download Full-text