This study aimed to establish and validate machine learning models for prognosis prediction in endodontic microsurgery, avoiding treatment failure and supporting clinical decision-making. A total of 234 teeth from 178 patients were included in this study. We developed gradient boosting machine (GBM) and random forest (RF) models. For each model, 80% of the data were randomly selected for the training set and the remaining 20% were used as the test set. A stratified 5-fold cross-validation approach was used in model training and testing. Correlation analysis and importance ranking were conducted for feature selection. The predictive accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the curve (AUC) of receiver operating characteristic (ROC) curves were calculated to evaluate the predictive performance. There were eight important predictors, including tooth type, lesion size, type of bone defect, root filling density, root filling length, apical extension of post, age, and sex. For the GBM model, the predictive accuracy was 0.80, with a sensitivity of 0.92, specificity of 0.71, PPV of 0.71, NPV of 0.92, F1 of 0.80, and AUC of 0.88. For the RF model, the accuracy was 0.80, with a sensitivity of 0.85, specificity of 0.76, PPV of 0.73, NPV of 0.87, F1 of 0.79, and AUC of 0.83. The trained models were developed by eight common variables, showing the potential ability to predict the prognosis of endodontic microsurgery. The GBM model outperformed the RF model slightly on our dataset. Clinicians can use machine learning models for preoperative analysis in endodontic microsurgery. The models are expected to improve the efficiency of clinical decision-making and assist in clinician-patient communication.

Caries is the most common and extensive oral chronic disease. Due to the lack of anti-caries properties, traditional caries filling materials can easily cause secondary caries and lead to treatment failure. Nanomaterials can interfere with the bacteria metabolism, inhibit the formation of biofilm, reduce demineralization, and promote remineralization, which is expected to be an effective strategy for caries management. The nanotechnology in anti-caries materials, especially nano-adhesive and nano-composite resin, has developed fast in recent years. In this review, the antibacterial nanomaterials, remineralization nanomaterials, and nano-drug delivery systems are reviewed. We are aimed to provide a theoretical basis for the future development of anti-caries nanomaterials.

Large bone defects, often arising from trauma or infection, pose a considerable therapeutic challenge due to their limited capacity for spontaneous healing, thus requiring bone graft materials for effective reparative procedures. The persistence of inflammation and elevated levels of reactive oxygen species (ROS) within these defect sites significantly impede bone regeneration process. Addressing this, an injectable hydrogel system with ROS-responsive functionality is developed, specifically tailored to the high ROS microenvironment characteristic of bone defects. This system incorporates hyaluronic acid functionalized with dopamine to introduce catechol moieties, and employs 4-formylphenylboronic acid as a crosslinking agent to form a dynamic hydrogel matrix (HAC) with carboxymethyl chitosan. The HAC hydrogel serves as a carrier for dimethyl fumarate (DMF), a compound with established anti-inflammatory and antioxidant effects, enabling its controlled release in response to ROS levels. Herein, we investigated the physicochemical properties of DMF loaded hydrogel (DHAC) by microstructure observation, in vitro degradation assay, self-healing test, injectability experiments, DMF drug release assay. Meanwhile, we systematically investigated its effects on inflammation, intracellular ROS, and osteogenesis. Consequently, the DHAC significantly reduced pro-inflammatory cytokines secreted by RAW264.7 cells and scavenged intracellular ROS in MC3T3 cells. This effect was accompanied by an augmentation in the osteogenic potential of MC3T3 cells and a promotion in the repair of cranial defects in rats. The DHAC, which exhibits anti-inflammatory, antioxidant, and osteogenic activity, hold great potential as an effective strategy for the management of large bone defects. STATEMENT OF SIGNIFICANCE: Here, a novel dimethyl fumarate-loaded ROS-responsive hydrogel system was developed for effective treatment of large bone defects. Our findings demonstrated that the hydrogel not only promotes bone regeneration but also controls inflammation, addressing two critical challenges in bone healing. Comprehensive evaluations show significant improvements in bone formation and reduction of pro-inflammatory cytokines in animal models. Additionally, the hydrogel exhibits excellent reactive oxygen species scavenging ability, effectively modulating oxidative stress in the bone defect microenvironment. Findings suggest the hydrogel system may serve as a promising therapeutic strategy for clinical management of critical-sized bone defects.