Mobile networks have an ever-increasing presence in critical infrastructure, enabling just-in-time monitoring and real-time control in various domains, from energy and transport to healthcare. However, the security of these systems is now vulnerable to new cybersecurity threats from this integration. Evaluating the potential of behavioral analytics and anomaly detection in securing mobile networks for critical infrastructure. This paper presents a novel Multi-Layer Adaptive Anomaly Detection System (MAADS) that utilizes recent advances in machine learning (ML) to identify anomalies and detect novel threats in mobile networks. MAADS detects anomalies in mobile networks across three layers: network traffic, user mobility, and device behavior. It does this through privacy-preserving data collection, multi-model anomaly detection, and an adaptive response framework. The empirical evaluation of the proposed system shows that MAADS can detect anomalies with 95% precision and 93% recall. It is demonstrated to identify 87% of anomalies not detected by standard ML-based systems. It also maintains its performance up to 100,000 nodes and consistently performs across other critical infrastructure sectors. The analysis and comparison of MAADS with existing solutions show that it outperforms existing techniques in terms of the ability to adapt to novel threats and the explainability of the detected anomalies.
Introduction:Rheumatoid arthritis (RA) is a chronic systemic autoimmune disease and often affects the temporomandibular joint (TMJ), causing progressive degenerative alterations that severely affect the quality of life of the patients, their mastication, and their general functional abilities. TMJ has not been adequately studied as a clinical aspect of RA despite the fact that it may occur in the earliest stages of the disease, with a few symptoms, and because no specific surveillance guidelines have been put in place. The timely prevention of degenerative alterations with timely therapeutic responses and the most effective imaging options to holistically evaluate TMJ are a highly debated subject of rheumatological and dental medicine. Materials and Methods:Sixty RA patients with the American College of Rheumatology/European League against Rheumatism 2010 classification criteria and 30 age- and sex-matched healthy people without TMJ disorders or systemic inflammatory conditions were enrolled in this cross-sectional control study. TMJ bilateral measures were conducted using standardized cone-beam computed tomography (CBCT) measures to assess the changes in the bone including erosions, osteophytes, cysts in the subchondral area and joint space width (JSW) measurement, and the musculoskeletal ultrasound (MSKUS) examination that measured the soft-tissue pathology of joint effusion, synovial hypertrophy and the associated vascularity, and the erosion of the articular disc. These statistical analyses consisted of independent t-tests when comparing continuous variables, Chi-square when comparing categorical variables, and Cohen's kappa coefficient when measuring inter-observer and intermodality agreement. Results:RA patients exhibited much more prevalent rates of osseous degenerative alterations than in healthy controls: Cortical erosions (68.3% vs. 10.0%, P < 0.001), osteophytes (45.0% vs. 6.7%, P < 0.001), subchondral cysts (31.7% vs. 3.3% P = 0.002) and significantly smaller mean JSW (1.8 0.5 mm vs. 2.5) similar pathological alterations of the soft tissue were also frequent among the RA cohort: Joint effusion (71.7% vs. 16.7, P = 0.001), active synovitis with Doppler signal (63.3% vs. 13.3, P = 0.001), and anterior displacement of the disc (38.3% vs. 10.0, P = 0.004). CBCT and MSKUS had a high intermodal consensus when it comes to detecting erosion (K = 0.75) and moderate consensus when detecting synovitis (K = 0.62). Conclusion:CBCT and MSKUS are useful in detecting different but complementary features of TMJ degeneration in RA patients, with the former being the best in revealing the detailed presence of the changes in the surroundings in a more detailed way, and the latter being the best in identifying and characterizing the presence of soft-tissue pathology and active inflammation. The combination of both modalities greatly improves diagnostic accuracy of the whole process of assessment and has more overall joint evaluation, which in turn benefits the evidence-based clinical decision-making and timely management intervention in patients with RA with TMJ involvement.
Periodontitis is a chronic inflammatory disease in which adjunctive local drug delivery may improve treatment outcomes. Therefore, it is of interest to evaluate the effectiveness of sub gingival curcumin and aloe vera chips used with scaling and root planing in 45 patients with Stage II Grade A periodontitis. All treatment groups showed significant improvements in clinical parameters, while the aloe vera chip produced greater early pocket depth reduction. The curcumin chip showed a significantly greater reduction in Aggregatibacter actinomycetemcomitans than scaling and root planing alone after 3 months. Thus, both curcumin and aloe vera chips provided beneficial adjunctive effects and may improve the management of Stage II Grade A periodontitis.
Thin gingival phenotype increases susceptibility to gingival recession and aesthetic compromise, while predictable minimally invasive approaches for phenotype enhancement remain limited. Sixty adults with thin gingival phenotype (GT <1.5 mm) were randomized to i-PRF alone or i-PRF+ microneedling (MN), with gingival thickness, keratinized tissue width, plaque index and BOP% measured at baseline, 3 and 6 months. Data were analyzed using appropriate parametric/non-parametric tests, repeated-measures ANOVA and Bonferroni correction (α=0.05). Both treatments significantly improved GT, KTW, PI and BOP%. i-PRF+MN produced a greater GT gain (Δ0.58 mm vs Δ0.42 mm; p<0.001); keratinized tissue width gains were similar. Thus, adjunctive microneedling with i-PRF offers superior gingival thickness augmentation as a minimally invasive option.
Background Failure of root canal treatment (RCT) significantly affects patient outcomes and dental practice. Understanding the association between root canal morphology and RCT outcomes can help predict treatment success. This study aimed to analyze the predictive role of root canal morphology in RCT failure. Methods This retrospective study included 224 patients who underwent RCT. Demographic data, tooth type, and root canal morphology were also recorded. Univariate and multivariate logistic regression analyses were performed to identify predictors of RCT failure. Additionally, machine learning algorithms were employed to develop a predictive model that was evaluated using receiver operating characteristic (ROC) curves. Results Of the 224 RCTs, 112 (50%) were classified as successful and 112 (50%) as failure. Severe canal curvature (p < 0.001) and presence of accessory canals (p = 0.002) were significant predictors of failure. The final predictive model demonstrated an area under the ROC curve (AUC) of 0.83, indicating good accuracy in distinguishing between successful and failed RCTs. Conclusion These findings underscore the importance of root canal morphology in predicting RCT outcomes. Machine learning approaches can enhance clinical decision making, enabling better treatment planning for patients at a higher risk of RCT failure.