A REFINED YOLOV8 BASED DEEP LEARNING FRAMEWORK FOR AUTOMATED DETECTION AND DIFFERENTIATION OF WRIST FRACTURE TYPES

*Muhammad Fahd Rafique Khan — 2026-10-16

Bone fractures are among the most common musculoskeletal injuries, particularly those affecting the wrist, shoulder, and arm, and their timely identification is essential for effective treatment and patient recovery. This study explores the application of YOLOv8, a deep learning-based object detection model, for identifying fractures in the radius and ulna, the two bones that play a vital role in forearm and wrist function. To support reliable fracture detection, an annotated dataset was developed through systematic data collection in collaboration with physiotherapists, with particular emphasis on accurately locating fracture regions in medical images. Several data augmentation techniques, including Mosaic, MixUp, and Copy-Paste, were incorporated into the training process to increase data variability, address potential limitations in the dataset, and improve the model’s ability to recognize different fracture patterns. These techniques also helped expose the model to a broader range of image variations, potentially improving its generalization to previously unseen cases. The experimental analysis included the baseline YOLOv8 model, the improved iYOLOv8 + GC architecture, and optimized model configurations to examine their effectiveness in detecting different types of wrist fractures. Particular attention was given to comparing precision, recall, and F1-score to understand the strengths and limitations of each approach rather than relying on a single performance indicator. The baseline YOLOv8 model achieved an accuracy of 0.87, a precision of 0.87, a recall of 0.88, and an F1-score of 0.86. These results indicate that the model can identify fracture-related patterns while maintaining a relatively balanced relationship between precision and recall. In comparison, the iYOLOv8 + GC variant reportedly achieved a precision of 97.2%, suggesting a strong ability to correctly identify predicted fracture cases.

However, a higher precision value alone does not necessarily indicate better overall performance, making it important to consider recall, F1-score, and other relevant evaluation measures when comparing the models. The findings therefore demonstrate the importance of evaluating both conventional and enhanced YOLOv8 architectures to determine their suitability for automated fracture detection. Furthermore, the use of deep learning can potentially reduce the time required for preliminary image assessment and help clinicians identify suspicious fracture regions more efficiently. Such automated assistance may be particularly valuable in clinical environments where large numbers of radiographic images require examination. Nevertheless, the model should be considered a potential decision-support tool rather than a replacement for qualified medical professionals. Further evaluation using larger, independent, and clinically diverse datasets is necessary to establish its reliability across different patient populations and imaging conditions. Overall, this research highlights the potential of YOLOv8-based approaches to improve the efficiency and consistency of radius and ulna fracture detection, providing a foundation for future developments in AI-assisted medical image analysis and wrist injury management.

Keywords: Wrist injuries; ulna and radius fractures; YOLOv8; deep learning; fracture detection.

https://doi.org/10.5281/zenodo.23410176

A UNIFIED STATISTICAL–MACHINE LEARNING FRAMEWORK FOR CAUSAL DISCOVERY, EXPLAINABILITY, AND UNCERTAINTY QUANTIFICATION IN HIGH-DIMENSIONAL DATA

Asif Sumeer — 2026-10-26

High-dimensional data present substantial challenges for reliable prediction, interpretable modelling, causal discovery, and uncertainty quantification. Although statistical learning and explainable artificial intelligence have advanced considerably, these components are often investigated independently, limiting their combined effectiveness in scientific discovery and evidence-based decision-making. This study proposes a unified statistical–machine learning framework that integrates data preprocessing, dimensionality assessment, regularized prediction, model explainability, causal discovery, and uncertainty evaluation within a coherent analytical workflow. The framework is evaluated using a dataset comprising 5,000 observations and 500 numerical features, with Elastic Net regression employed to examine predictive performance and identify informative feature relationships. Model performance is assessed using the coefficient of determination (R²), root mean squared error (RMSE), and mean absolute error (MAE), while coefficient interpretation, permutation-based feature importance, SHAP analysis, resampling, and sensitivity assessment provide complementary approaches for examining model behaviour and result stability. The predictive model achieved an (R²) of 0.795, an RMSE of 0.446, and an MAE of 0.360, indicating that it explained 79.5% of the variation in the prediction target on the held-out evaluation data. These findings demonstrate the predictive potential of regularized machine learning in high-dimensional settings and establish a quantitative basis for integrating predictive performance with interpretability and uncertainty assessment. The proposed framework also emphasizes a fundamental distinction between predictive associations and causal relationships: feature importance and predictive accuracy alone cannot establish causation. Reliable causal discovery requires explicit structural assumptions, appropriate treatment of potential confounding, and systematic validation of the inferred relationships. By bringing statistical modelling, explainable artificial intelligence, causal reasoning, and uncertainty assessment together, this study provides a methodological foundation for more transparent, robust, and scientifically defensible analysis of complex data. The framework has potential applications in healthcare, financial risk assessment, environmental modelling, and other domains where accurate predictions must be accompanied by interpretable evidence and carefully evaluated uncertainty.

Spectrum of Engineering Sciences

A REFINED YOLOV8 BASED DEEP LEARNING FRAMEWORK FOR AUTOMATED DETECTION AND DIFFERENTIATION OF WRIST FRACTURE TYPES

A UNIFIED STATISTICAL–MACHINE LEARNING FRAMEWORK FOR CAUSAL DISCOVERY, EXPLAINABILITY, AND UNCERTAINTY QUANTIFICATION IN HIGH-DIMENSIONAL DATA