Wedam Nyaaba
Wedam Nyaaba has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alexa R. Lauinger
Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, IL, United States
1 shared publication - Gregory M. Polites
Carle Illinois College of Medicine, Urbana, IL
1 shared publication - Helen Kemprecos
Carle Illinois College of Medicine, Urbana, IL
1 shared publication K.A. El-Nagdy
Faculty of Engineering, Mining Department, Suez University, Suez, Egypt
1 shared publicationNeema Darabi
Carle Illinois College of Medicine, Urbana, IL
1 shared publicationPaul M. Arnold
Carle Illinois College of Medicine, Urbana, IL
1 shared publication
Latest Publications
- Open Access
- 21 October 2026
- Published by Wolters Kluwer Health in Spine Open
- Vol. 2 (4)
Early Prediction of Prolonged Hospitalization After Penetrating Spinal Cord Injury: A Machine Learning Analysis of the National Trauma Data Bank
Study Design: Retrospective cohort study using the American College of Surgeons National Trauma Data Bank (NTDB) from 2017 to 2023. Prolonged hospital length of stay (LOS) was defined as exceeding the 75th percentile of the cohort distribution (>26 d). Objective: To develop and internally validate machine learning (ML) models for predicting prolonged LOS after penetrating spinal cord injury (pSCI) and to identify clinically available admission-stage predictors that retain useful performance in a reduced-feature model. Summary of Background Data: pSCI is a distinct subset of spinal cord injury with high morbidity and resource utilization, primarily affecting younger, socioeconomically vulnerable populations. pSCI-specific LOS prediction models remain limited. Materials and Methods: We studied 2912 adults with pSCI; 665 (22.8%) had prolonged LOS. We trained logistic regression, Naïve Bayes, decision tree, random forest, adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), support vector machine, and deep neural network (DNN) models with five-fold cross-validation and an independent hold-out test set. The four strongest full-feature models were retrained on a clinically motivated set of 10 early-available predictors. SHapley Additive exPlanations (SHAP) analyses provided model interpretation. Sensitivity analyses tested robustness across alternative LOS thresholds. Results: Patients with prolonged LOS had markedly higher rates of pressure ulcer (26.2% vs . 2.5%), deep vein thrombosis (12.0% vs. 1.6%), sepsis (5.1% vs . 0.8%), and pulmonary embolism (6.0% vs . 1.0%; all P ≤0.001). Full-feature models achieved hold-out ROC AUCs of 65% to 72%, with XGBoost performing best (72.44%). A 10-variable reduced model retained comparable discrimination (DNN-reduced ROC AUC: 67.48%). Discrimination was consistent across alternative LOS threshold definitions (ROC AUC: 0.66–0.70). Conclusion: ML models using routinely available admission-stage variables identify patients at risk for prolonged hospitalization after pSCI with modest but clinically meaningful discrimination. A parsimonious 10-variable reduced model retains useful performance, supporting early risk stratification, discharge planning, and resource allocation. External validation is needed before clinical implementation. Level of Evidence: Level III [OCEMB Levels of Evidence Working Group 2011].
- 21 October 2026
- Published by Wolters Kluwer Health in Spine Open
- Vol. 2 (4)
Open AccessEarly Prediction of Prolonged Hospitalization After Penetrating Spinal Cord Injury: A Machine Learning Analysis of the National Trauma Data Bank
Study Design: Retrospective cohort study using the American College of Surgeons National Trauma Data Bank (NTDB) from 2017 to 2023. Prolonged hospital length of stay (LOS) was defined as exceeding the 75th percentile of the cohort distribution (>26 d). Objective: To develop and internally validate machine learning (ML) models for predicting prolonged LOS after penetrating spinal cord injury (pSCI) and to identify clinically available admission-stage predictors that retain useful performance in a reduced-feature model. Summary of Background Data: pSCI is a distinct subset of spinal cord injury with high morbidity and resource utilization, primarily affecting younger, socioeconomically vulnerable populations. pSCI-specific LOS prediction models remain limited. Materials and Methods: We studied 2912 adults with pSCI; 665 (22.8%) had prolonged LOS. We trained logistic regression, Naïve Bayes, decision tree, random forest, adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), support vector machine, and deep neural network (DNN) models with five-fold cross-validation and an independent hold-out test set. The four strongest full-feature models were retrained on a clinically motivated set of 10 early-available predictors. SHapley Additive exPlanations (SHAP) analyses provided model interpretation. Sensitivity analyses tested robustness across alternative LOS thresholds. Results: Patients with prolonged LOS had markedly higher rates of pressure ulcer (26.2% vs . 2.5%), deep vein thrombosis (12.0% vs. 1.6%), sepsis (5.1% vs . 0.8%), and pulmonary embolism (6.0% vs . 1.0%; all P ≤0.001). Full-feature models achieved hold-out ROC AUCs of 65% to 72%, with XGBoost performing best (72.44%). A 10-variable reduced model retained comparable discrimination (DNN-reduced ROC AUC: 67.48%). Discrimination was consistent across alternative LOS threshold definitions (ROC AUC: 0.66–0.70). Conclusion: ML models using routinely available admission-stage variables identify patients at risk for prolonged hospitalization after pSCI with modest but clinically meaningful discrimination. A parsimonious 10-variable reduced model retains useful performance, supporting early risk stratification, discharge planning, and resource allocation. External validation is needed before clinical implementation. Level of Evidence: Level III [OCEMB Levels of Evidence Working Group 2011].
- 24 February 2014
- Published by Taylor & Francis in International Journal of Mining, Reclamation and Environment
- Vol. 29 (3) , 201-212
Optimisation of mine ventilation networks using the Lagrangian algorithm for equality constraints
This work presents a new method of mine ventilation network optimisation as standard non-linear programming problem and discusses the use of a novel first-order Lagrangian (FOL) algorithm for equality constraints as a solution tool for these problems. Slack variables have been defined to transform such inequality constraints into their corresponding equality forms. The problem is then converted to non-linear problem with equality constrains. The methodology adopted in this paper is capable of dealing with the non-linear convex model with significant savings on computational efforts due to its use of only first derivatives. A MATLAB programme has been developed based on the FOL method to solve a generalised mine ventilation network optimisation problem. To study the validity and the viability of the FOL programme, the programme has been applied to already published network problems and both results are identical.
- 24 February 2014
- Published by Taylor & Francis in International Journal of Mining, Reclamation and Environment
- Vol. 29 (3) , 201-212
Optimisation of mine ventilation networks using the Lagrangian algorithm for equality constraints
This work presents a new method of mine ventilation network optimisation as standard non-linear programming problem and discusses the use of a novel first-order Lagrangian (FOL) algorithm for equality constraints as a solution tool for these problems. Slack variables have been defined to transform such inequality constraints into their corresponding equality forms. The problem is then converted to non-linear problem with equality constrains. The methodology adopted in this paper is capable of dealing with the non-linear convex model with significant savings on computational efforts due to its use of only first derivatives. A MATLAB programme has been developed based on the FOL method to solve a generalised mine ventilation network optimisation problem. To study the validity and the viability of the FOL programme, the programme has been applied to already published network problems and both results are identical.