Summary of key studies in deep learning for fracture analysis and non-union prediction

ReferenceStudy focusMain findingPerformance parameters
Porter et al. (2016) [13]Automated measurement of fracture callus using portable softwareQuantitatively monitored callus progression, indicating potential for early non-union detectionImproved measurement consistency
Kalmet et al. (2020) [19]Deep learning for fracture detectionDemonstrated reliable fracture detection on radiographsEnhanced sensitivity and specificity over traditional methods
Chung et al. (2018) [20]Automated detection and classification of proximal humerus fracturesAchieved high accuracy in detecting and classifying proximal humerus fracturesAccuracy metrics comparable to expert assessments
Tanzi et al. (2020) [21]X-ray bone fracture classification using deep learningEstablished a baseline for fracture classification accuracy with potential for further improvementAccuracy values in line with clinical expectations
Stojadinovic et al. (2011) [15]Prognostic naïve Bayesian classifier for non-union predictionDeveloped a Bayesian model to predict fracture healing outcomes following shock wave therapySpecific performance metrics are not detailed
Degenhart et al. (2023) [18]Computer-based mechanobiological fracture healing model for predicting non-unionProposed a simulation model predicting healing outcomes after intramedullary nailing with promising resultsPreliminary findings: detailed metrics require further validation