Fractures are the most common large organ trauma in humans. The initial inflammatory re-sponse promotes bone healing during the initial post-fracture phase, but chronic and persistent inflammation due to infection or other factors does not contribute to the healing process. The precise mechanisms by which immune cells and their cytokines are regulated in bone healing remain unclear. The use of mesenchymal stem cells (MSCs) for cellular therapy of bones injury is a novel clinical treatment approach. Bone progenitor MSCs not only differentiate into bone, but also interact with the immune system to promote the healing process. We review in vitro and in vivo studies on the role of the immune system and bone marrow MSCs in bone healing and their interactions. A deeper understanding of this paradigm may provide clues to potential therapeu-tic targets in the healing process, thereby improving the reliability and safety of clinical applica-tions of MSCs to promote bone healing.

The diagnosis of papillary thyroid carcinoma has always been a concerned and challenging issue and it is very important and meaningful to have a definite diagnosis before the operation. In this study, we tried to use an artificial intelligence algorithm instead of medical statistics to analyze the genetic fingerprint from gene chip results to identify papillary thyroid carcinoma. We trained 20 artificial neural network models with differential genes and other important genes related to the cell metabolic cycle as the list of input features, and apply them to the diagnosis of papillary thyroid cancer in the independent validation data set. The results showed that when we used the DEGs and all genes lists as input features the models got the best diagnostic performance with AUC=98.97% and 99.37% and the accuracy were both 96%. This study revealed that the proposed artificial neural network models constructed with genetic fingerprints could achieve a prediction of papillary thyroid carcinoma. Such models can support clinicians to make more accurate clinical diagnoses. At the same time, it provides a novel idea for the application of artificial intelligence in clinical medicine.