Owing to the sensitive nature of healthcare data, the aforementioned approach to transferring patient data to central servers creates serious security and privacy issues. In addition, blockchain distributed ledger technology has introduced immutable storage and decentralized data management capability, which handles a large number of distributed nodes of E-Healthcare transactions via a serverless network, but in a limited manner because of blockchain-enabled resources. In this scenario, the medical industries are concerned about constituting an innovation in health information preservation and exchanging service delivery protocols without the connectivity of an untrusted third-party infrastructure. In this study, we proposed a blockchain hyperledger fabric-enabled consortium architecture called BIoMT, which provides security, integrity, transparency, and provenance to health-related transactions and exchanges sensitive clinical information in a serverless peer-to-peer (P2P) secure network environment. A consensus is designed and created to reduce the rate of blockchain resource constraints on the Internet of Medical Things (IoMT). The privacy of individual health transactions before sharing is protected using the NuCypher Re-Encryption mechanism, which increases security and provides medical ledger integrity and transparency. Smart contracts are created and deployed to automate device registration, exchange transactions, and ledger preservation in immutable storage (filecoin) after cross verification and validation. The experimental results show that the proposed BIoMT reduces the computational cost by 26.13%, and the robust medical node generation increases to 60.37%. Thus, only 31.79% and 74.21% of IoMT-related information and serverless P2P network usage are maintained and saved, respectively.

With widespread usage of online social networks and its popularity, social networking platforms have given us incalculable opportunities than ever before, and its benefits are undeniable. Despite benefits, people may be humiliated, insulted, bullied, and harassed by anonymous users, strangers, or peers. In this study, we have proposed a cyberbullying detection framework to generate features from Twitter content by leveraging a pointwise mutual information technique. Based on these features, we developed a supervised machine learning solution for cyberbullying detection and multi-class categorization of its severity in Twitter. In the study we applied Embedding, Sentiment, and Lexicon features along with PMI-semantic orientation. Extracted features were applied with Naïve Bayes, KNN, Decision Tree, Random Forest, and Support Vector Machine algorithms. Results from experiments with our proposed framework in a multi-class setting are promising both with respect to Kappa, classifier accuracy and f-measure metrics, as well as in a binary setting. These results indicate that our proposed framework provides a feasible solution to detect cyberbullying behavior and its severity in online social networks. Finally, we compared the results of proposed and baseline features with other machine learning algorithms. Findings of the comparison indicate the significance of the proposed features in cyberbullying detection.

Background: Source case investigation, for children with tuberculosis (TB), is conducted to establish the source of infection and to minimize the extent of on-going transmission from infectious persons in the community. The aim of the study was to evaluate the secondary TB cases and to investigate the risk factors in developing TB among the household contacts (HHC) of children with active TB. Methods: A prospective cross-sectional study was conducted where 443 caregivers, of 508 children with active TB receiving treatment, were interviewed using a structured questionnaire. Logistic regression analysis was used to examine the risk factors for TB. Results: A total of 2397 family members at the median of 5 persons were recorded. Of these, 223 (9.3%) were screened on symptoms basis and 35 (15.7%) of these contacts were diagnosed with TB. Multivariate analysis revealed HHC with TB (OR = 15.288, 95% CI: 5.378–43.457), HHC with smoking (OR = 7.094, 95% CI: 2.128–23.648), and contact of > 18 h with TB individual (OR = 4.681, 95% CI: 1.198–18.294) as statistically significant risk factors of TB among the HHC. Conclusion: With the current system of contact screening for TB, only 9.3% of all HHC were screened. The low rates of contacts screened are possibly a repercussion of the passive nature of the program, which mainly depend on distinctive clinical symptoms being experienced by the contacts. Strategies are required to certify adherence with contact screening among children with active TB and to critically consider the factors responsible for TB transmission.

Twitter enables millions of active users to send and read concise messages on the internet every day. Yet some people use Twitter to propagate violent and threatening messages resulting in cyberbullying. Previous research has focused on whether cyberbullying behavior exists or not in a tweet (binary classification). In this research, we developed a model for detecting the severity of cyberbullying in a tweet. The developed model is a feature-based model that uses features from the content of a tweet, to develop a machine learning classifier for classifying the tweets as non-cyberbullied, and low, medium, or high-level cyberbullied tweets. In this study, we introduced pointwise semantic orientation as a new input feature along with utilizing predicted features (gender, age, and personality type) and Twitter API features. Results from experiments with our proposed framework in a multi-class setting are promising both with respect to Kappa (84%), classifier accuracy (93%), and F-measure (92%) metric. Overall, 40% of the classifiers increased performance in comparison with baseline approaches. Our analysis shows that features with the highest odd ratio: for detecting low-level severity include: age group between 19–22 years and users with <1 year of Twitter account activation; for medium-level severity: neuroticism, age group between 23–29 years, and being a Twitter user between one to two years; and for high-level severity: neuroticism and extraversion, and the number of times tweet has been favorited by other users. We believe that this research using a multi-class classification approach provides a step forward in identifying severity at different levels (low, medium, high) when the content of a tweet is classified as cyberbullied. Lastly, the current study only focused on the Twitter platform; other social network platforms can be investigated using the same approach to detect cyberbullying severity patterns.

The objective of this scientific study is to determine under which traffic conditions machinelearning-based routing control provides sufficient benefit over conventional equal-cost multi-path routing to justify its additional operational complexity. To address this objective, routing is formulated as a sequential decision-making problem and evaluated through a controlled empirical comparison in Network Simulator 3 using a fat-tree data-center topology. The study compares three controllers: a conventional equal-cost multi-path baseline, a supervised learning controller based on a temporal convolutional network, and a deep reinforcement learning controller based on a deep Q-network. Traffic workloads are derived from public Internet backbone, long-haul, and campus-network trace repositories, with additional distributed-denial-of-service traffic injected from a public attack dataset to construct four operating regimes: Core Internet, Long-Haul Diurnal, Enterprise Campus, and Stress/Attack. Performance is assessed using average and 99th-percentile flow completion time, receiver goodput, packet loss rate, and inference latency under heterogeneous trace-driven traffic conditions. The results show that both learning-based controllers improve latency and reliability relative to the conventional baseline, with the largest gains under volatile and adversarial traffic. In the aggregate medium-load evaluation, the deep reinforcement learning controller reduces average flow completion time by 33.4% and packet loss by 80.7% relative to equal-cost multi-path routing. The supervised controller is more competitive in stable regimes and delivers about half the inference latency of the reinforcement controller (0.8 ms versus 1.6 ms). These findings indicate that supervised learning is attractive when traffic is predictable and operational simplicity is important, whereas reinforcement learning is better justified when traffic non-stationarity, burstiness, and attack-driven stress make long-horizon adaptation more valuable.

Objective: This study is aimed at evaluating the impact of Type 2 diabetes mellitus (T2DM) duration on major adverse cardiovascular events (MACEs) after percutaneous coronary intervention (PCI). Methods: A single‐center prospective cohort study was conducted in which 465 T2DM patients undergoing PCI and completing the 1‐year follow‐up were enrolled. Patients were divided into three groups based on duration of DM: < 5 years, 5–10 years, and > 10 years. The primary endpoint was MACE, a composite of nonfatal myocardial infarction (MI), stroke, coronary artery bypass grafting (CABG), repeat PCI, and mortality. Results: The incidence of MACE increased progressively with longer diabetes duration: 3.7% (< 5 years), 8.1% (5–10 years), and 13.9% (> 10 years), with particularly higher rates of stroke (0.6%–3.0%) and repeat PCI (1.8%–6.0%) among T2DM patients after PCI. The Kaplan–Meier analysis demonstrated a clear stepwise rise in cumulative MACE incidence over 12 months, with the highest event rates observed in patients with diabetes for more than 10 years (log‐rank p < 0.004). Consistently, Cox proportional hazards models showed significantly elevated risk compared with the < 5‐year group, with adjusted hazard ratios of 3.16 (95% CI: 1.06–9.47, p = 0.039) for 5–10 years and 4.37 (95% CI: 1.59–12.01, p = 0.004) for > 10 years. Conclusion: Patients with longer duration (> 10 years) of T2DM had the highest incidence and hazard of adverse cardiovascular events compared to shorter duration (< 5 years and 5–10 years). These results suggest that targeted preventive strategies and closer post‐PCI monitoring are essential for patients with prolonged diabetes duration.