<p>Bone cancer, although less common than other types of cancer, can affect people of all ages with varying incidence rates globally. One of the United Nations' Sustainable Development Goals is to achieve health and well-being for all. The use of Artificial Intelligence (AI) for diagnosing bone cancer is crucial to achieving this goal. Deep learning models have demonstrated efficiency in processing medical images, and several imaging technologies are available for research on bone cancer. Histology images are crucial in bone cancer research, as they provide detailed visual information about the cellular and tissue characteristics of tumors. However, there is limited research on the use of artificial intelligence for histology imagery in bone cancer detection. A new deep learning-based framework for automatically screening bone cancer, particularly osteosarcoma, is proposed to create a Clinical Decision Support System (CDSS). This framework utilizes a novel hybrid deep learning model, known as the Hybrid Bone Cancer Detection Network (HBCDNet), which combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models to enhance bone cancer detection performance. An algorithm called Hybrid Deep Learning-based Osteosarcoma Detection (HDL-OD) for cancer screening using histology images is introduced. The novelty of HBCDNet lies in its ability to improve the modus operandi for disease prediction. An empirical study using the benchmark dataset Osteosarcoma-Tumor-Assessment shows that the proposed hybrid deep learning model, HBCDNet, achieves the highest accuracy of 97.81% in binary classification and 96.13% in multi-class classification, providing reassurance about its reliability to the community. The potential integration of the HBCDNet model into healthcare applications holds promise for assisting doctors in automatically screening bone cancers, thereby improving patient outcomes and healthcare efficiency.</p>