Research and publications

Permanent URI for this collectionhttps://hdl.handle.net/10315/43417

Browse

Recent Submissions

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item type: Item , Access status: Open Access ,
    Vertebral compression Fracture Risk in Spinal Metastases Patients Following Stereotactic Body Radiotherapy Using Quantitative Imaging Data and Machine Learning
    (Institute of Electrical and Electronics Engineers (IEEE), 2025-08-22) Gulta, Dawit; Chen, Stephen; Klein, Geoff; Ross, Tayler D; Rezkalla, Matthew; Palhares, Daniel M; Burgess, Laura; Detsky, Jay; Sahgal, Arjun; Whyne, Cari M; Hardisty, Michael
    Vertebral compression fractures (VCFs) occur in approximately 14% of patients with spinal metastases following treatment with Stereotactic Body Radiotherapy (SBRT). The Spinal Instability Neoplastic Score (SINS) is the current clinical standard for assessing potential mechanical instability in these patients; however, it has several limitations such as it is manually assessed, has an inconsistent relationship with fracture risk and is only semi-quantitative. This study used quantitative CT imaging biomarkers derived from SBRT treatment planning imaging and machine learning models (Logistic Regression, Random Forest, XGBoost, SVM, Gradient Boosting, AdaBoost, Neural Network) to predict vertebral compression fractures (VCF) following SBRT in spinal metastases patients (in 300 thoraco-lumbar vertebrae from 179 patients). The Random Forest model achieved the best performance (sensitivity: 0.64, specificity: 0.76, F1-score: 0.47), showing a 36% improvement in balanced accuracy over SINS. Feature importance analysis identified the quantitative imaging biomarkers, spinal alignment and bone lesion composition (lytic or blastic disease) as the strongest predictors. ML models demonstrated meaningful improvements over existing SINS assessment.
  • Thumbnail Image
    Item type: Item , Access status: Open Access ,
    The effect of elitist fitness-based selection on the escape from local optima
    (Elsevier, 2025-10-11) Chen, Stephen
    Random Search is the baseline that a metaheuristic must improve upon to be worth its added complexity. Random Search, in the form of Hill Climbing, cannot escape from local optima. A key claim of many metaheuristics is that they are able to escape from local optima. However, these claims are poorly tested and often based on imprecise definitions of what it means to escape from a local optimum in continuous domain search spaces. A practical and precise definition for an escape from a local optimum is developed. It is then shown how elitist fitness-based selection can lead to the rejection of exploratory search solutions, and this can cause many popular metaheuristics to degrade into (localized) Random Search in their attempts to escape from local optima. The explosion of new metaheuristics has often been just a repeated re-invention of localized Random Search for the key task of escaping from local optima.
  • Thumbnail Image
    Item type: Item , Access status: Open Access ,
    Simulation Optimization of Operating Room Schedules for Elective Surgeries
    (Springer, 2024-07-10) Maltseva, Daria; Chen, Stephen; Lex, Johnathan; Abbas, Aazad; Whyne, Cari
    Our specific problem is to create daily schedules of elective surgeries in a multiple operating room setting with the goals of minimizing the amount of overtime incurred and maintaining patient volumes. While surgical durations cannot always be perfectly estimated and vary by procedure and surgeon, our approach relies on leveraging the stochastic nature of surgical durations to simulate each operating day and understand the probability of incurring overtime under a certain schedule of surgeries. The heuristic optimization component of our approach investigates the probabilistic evaluation and strategically re-schedules surgeries. Through experimentation with three optimization techniques, two showed promising results being able to reduce the total number of overtime surgeries by 12–15%, equivalent to approximately 1h of total monthly overtime. Compared to the literature, this approach serves solely as a tool for improving schedules and can be used for supporting decision making at the hospital. Our contribution involves introducing the simulation optimization model and describing the data-driven approach to analyzing the scheduling problem.