Lakhasly

Bone tumors, especially malignant ones such as osteosarcoma and Ewing sarcoma, present a significant clinical challenge due to their complex pathology, varying treatment responses, and unpredictable patient outcomes.However, existing AI models for bone tumor classification are limited in number, often lack comprehensive evaluation, and rarely address the challenge of imbalanced datasets, where minority outcome classes (e.g., NED or AWD) are underrepresented, leading to biased predictions.Timely and accurate classification of these tumors into prognosis-related categories--No Evidence of Disease (NED), Alive With Disease (AWD), and Dead (D)--is critical for determining optimal treatment strategies, monitoring disease progression, and improving patient survival rates.

Bone tumors, especially malignant ones such as osteosarcoma and Ewing sarcoma, present a significant clinical challenge due to their complex pathology, varying treatment responses, and unpredictable patient outcomes. Timely and accurate classification of these tumors into prognosis-related categories—No Evidence of Disease (NED), Alive With Disease (AWD), and Dead (D)—is critical for determining optimal treatment strategies, monitoring disease progression, and improving patient survival rates.

Despite advances in medical imaging and pathology, traditional diagnostic methods remain time-consuming, require expert interpretation, and are prone to variability. Moreover, these methods often fail to fully utilize the vast amounts of structured clinical and demographic data available in modern healthcare systems. Recent developments in artificial intelligence, particularly machine learning (ML) and deep learning (DL), offer promising avenues for automating tumor classification and enhancing clinical decision support systems. However, existing AI models for bone tumor classification are limited in number, often lack comprehensive evaluation, and rarely address the challenge of imbalanced datasets, where minority outcome classes (e.g., NED or AWD) are underrepresented, leading to biased predictions.

Furthermore, few studies have explored and compared a wide range of ML algorithms alongside a deep learning model on a balanced dataset tailored for bone tumor prognosis. Without such comprehensive evaluation, it is difficult to determine the most effective modeling approach for real-world deployment.