Systemic Corticosteroid Uses in Endodontics-Part 1: Managing Postoperative Pain.

INTRODUCTION: This study aimed to systematically search and review all available literature regarding systemic (oral or locally injected) corticosteroids in endodontics to assess their effect on postoperative pain. METHODS: A search was conducted using PubMed, Cochrane Library, Embase, Scopus, Dentistry & Oral Science, and ProQuest. Randomized controlled trials enrolling participants undergoing endodontic treatment and assessing the presence of pain and pain scores at 6, 12, and 24 hours postoperatively were included. We synthesize the effect measures using risk ratios (RRs), standardized mean differences (SMDs), and their corresponding 95% confidence intervals (CIs). Meta-analysis was performed using the random-effects inverse variance method. The level of significance was set at P < .05. The certainty of the evidence was evaluated using Grading of Recommendations, Assessment, Development and Evaluation approach. RESULTS: A total of 2303 participants from 29 trials were included. Patients who received corticosteroids were significantly less likely to report pain at 6 hours (RR = 2.5; 95% CI, 1.74-3.61; P < .00001), 12 hours (RR = 2.10; 95% CI, 1.53-2.90; P < .00001), and 24 hours (RR = 1.77; 95% CI, 1.38-2.28; P < .00001) postoperatively. Furthermore, they reported lower pain intensity at 6 hours (SMD = - 0.82; 95% CI, -1.17 to -0.48; P < .00001), 12 hours (SMD = - 0.63; 95% CI, -0.75 to -0.51; P < .00001), and 24 hours (SMD = - 0.68; 95% CI, -0.90 to -0.46; P < .00001) postoperatively. CONCLUSIONS: Moderate certainty evidence indicates that the use of systemic corticosteroids likely results in a moderate to large reduction in postoperative endodontic pain.

Systemic Corticosteroid Uses in Endodontics-Part 2: Enhancing the Success of Local Anesthesia.

INTRODUCTION: Chronic inflammation in irreversible pulpitis leads to heightened sensitivity of nociceptive receptors, resulting in persistent hyperalgesia. This poses significant challenges in achieving effective anesthesia for patients with irreversible pulpitis. Various anesthetic techniques and pharmacological approaches have been employed to enhance the success of local anesthesia. Recently, the preemptive use of anti-inflammatory agents, specifically corticosteroids, has gained attention and shown promising results in randomized controlled trials. This systemic review and meta-analysis aimed to evaluate the impact of systemically administered corticosteroids on enhancing anesthetic success in patients undergoing endodontic treatment. METHODS: A comprehensive search was conducted across multiple databases including PubMed, Cochrane Library, Embase, Scopus, Dentistry & Oral Science, and ProQuest. Additionally, the references of primary studies and related systematic reviews were manually searched for additional relevant publications. The primary outcome assessed was the success of anesthesia, and the effect measure was risk ratio using the random-effects inverse variance method. Statistical significance was set at P < .05. The certainty of the evidence was evaluated using the Grading of Recommendations, Assessment, Development, and Evaluation approach. RESULTS: Twelve studies involving 917 participants were analyzed to determine the frequency of successful anesthesia. The corticosteroid group demonstrated a significantly higher number of patients achieving successful anesthesia (risk ratio = 1.66; 95% confidence interval, 1.34-2.06;P < .00001). However, heterogeneity within the pooled data analysis was observed (I2 = 57%, P = .007). CONCLUSIONS: Moderate certainty evidence indicates that preemptive use of systemic corticosteroids enhances the success of local anesthesia, specifically inferior alveolar nerve block, in cases of irreversible pulpitis.

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning.

Driver drowsiness is one of the main causes of traffic accidents today. In recent years, driver drowsiness detection has suffered from issues integrating deep learning (DL) with Internet-of-things (IoT) devices due to the limited resources of IoT devices, which pose a challenge to fulfilling DL models that demand large storage and computation. Thus, there are challenges to meeting the requirements of real-time driver drowsiness detection applications that need short latency and lightweight computation. To this end, we applied Tiny Machine Learning (TinyML) to a driver drowsiness detection case study. In this paper, we first present an overview of TinyML. After conducting some preliminary experiments, we proposed five lightweight DL models that can be deployed on a microcontroller. We applied three DL models: SqueezeNet, AlexNet, and CNN. In addition, we adopted two pretrained models (MobileNet-V2 and MobileNet-V3) to find the best model in terms of size and accuracy results. After that, we applied the optimization methods to DL models using quantization. Three quantization methods were applied: quantization-aware training (QAT), full-integer quantization (FIQ), and dynamic range quantization (DRQ). The obtained results in terms of the model size show that the CNN model achieved the smallest size of 0.05 MB using the DRQ method, followed by SqueezeNet, AlexNet MobileNet-V3, and MobileNet-V2, with 0.141 MB, 0.58 MB, 1.16 MB, and 1.55 MB, respectively. The result after applying the optimization method was 0.9964 accuracy using DRQ in the MobileNet-V2 model, which outperformed the other models, followed by the SqueezeNet and AlexNet models, with 0.9951 and 0.9924 accuracies, respectively, using DRQ.

TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications.

Recently, the Internet of Things (IoT) has gained a lot of attention, since IoT devices are placed in various fields. Many of these devices are based on machine learning (ML) models, which render them intelligent and able to make decisions. IoT devices typically have limited resources, which restricts the execution of complex ML models such as deep learning (DL) on them. In addition, connecting IoT devices to the cloud to transfer raw data and perform processing causes delayed system responses, exposes private data and increases communication costs. Therefore, to tackle these issues, there is a new technology called Tiny Machine Learning (TinyML), that has paved the way to meet the challenges of IoT devices. This technology allows processing of the data locally on the device without the need to send it to the cloud. In addition, TinyML permits the inference of ML models, concerning DL models on the device as a Microcontroller that has limited resources. The aim of this paper is to provide an overview of the revolution of TinyML and a review of tinyML studies, wherein the main contribution is to provide an analysis of the type of ML models used in tinyML studies; it also presents the details of datasets and the types and characteristics of the devices with an aim to clarify the state of the art and envision development requirements.

Comparison of the antibacterial activity of calcium silicate- and epoxy resin-based endodontic sealers against Enterococcus faecalis biofilms: a confocal laser-scanning microscopy analysis.

This study assessed the antibacterial activity of BioRoot RCS in comparison with that of the Totalfill BC and AH Plus sealers against Enterococcus faecalis biofilms in dentinal tubules using confocal laser-scanning microscopy. Sixty-six root dentin halves were prepared and sterilized. Three sections were used to ensure sterilization. The remaining were inoculated with E. faecalis. Three specimens were examined to verify the viability of biofilms. The sixty specimens were randomly divided into four groups: AH Plus, BioRoot RCS, Totalfill BC sealer, and no sealer. The specimens were incubated for 1, 7, and 30 days. The specimens were stained and four corners of each disc were scanned. Statistical analysis was performed using two-way ANOVA and Tukey's post hoc test. Almost half of the bacteria were dead in BioRoot RCS group on day 1 and in Totalfill BC group on day 7. All sealers killed significantly more bacteria than the control after 30 days (P < .05). On day 7, Totalfill BC showed a significantly higher percentage of dead bacteria than BioRoot RCS (P < .05). On day 30, the BioRoot RCS group registered the highest percentage of dead cells (61.75%), which was significantly higher than the percentages of the AH Plus and Totalfill BC groups (P < .05). Calcium silicate-based root canal sealers exerted antimicrobial effects against E. faecalis biofilms. The antibacterial activity of BioRoot RCS was significantly higher than that of the Totalfill BC and AH Plus sealers after 30 days of exposure.