Novel statistical time series data augmentation and machine learning based classification of unobtrusive respiration data for respiration Digital Twin model.

Digital Twin (DT), a concept of Healthcare (4.0), represents the subject's biological properties and characteristics in a digital model. DT can help in monitoring respiratory failures, enabling timely interventions, personalized treatment plans to improve healthcare, and decision-support for healthcare professionals. Large-scale implementation of DT technology requires extensive patient data for accurate monitoring and decision-making with Machine Learning (ML) and Deep Learning (DL). Initial respiration data was collected unobtrusively with the ESP32 Wi-Fi Channel State Information (CSI) sensor. Due to limited respiration data availability, the paper proposes a novel statistical time series data augmentation method for generating larger synthetic respiration data. To ensure accuracy and validity in the augmentation method, correlation methods (Pearson, Spearman, and Kendall) are implemented to provide a comparative analysis of experimental and synthetic datasets. Data processing methodologies of denoising (smoothing and filtering) and dimensionality reduction with Principal Component Analysis (PCA) are implemented to estimate a patient's Breaths Per Minute (BPM) from raw respiration sensor data and the synthetic version. The methodology provided the BPM estimation accuracy of 92.3% from raw respiration data. It was observed that out of 27 supervised classifications with k-fold cross-validation, the Bagged Tree ensemble algorithm provided the best ML-supervised classification. In the case of binary-class and multi-class, the Bagged Tree ensemble showed accuracies of 89.2% and 83.7% respectively with combined real and synthetic respiration dataset with the larger synthetic dataset. Overall, this provides a blueprint of methodologies for the development of the respiration DT model.

Design and Modelling of Graphene-Based Flexible 5G Antenna for Next-Generation Wearable Head Imaging Systems.

Arguably, 5G and next-generation technology with its key features (specifically, supporting high data rates and high mobility platforms) make it valuable for coping with the emerging needs of medical healthcare. A 5G-enabled portable device receives the sensitive detection signals from the head imaging system and transmits them over the 5G network for real-time monitoring, analysis, and storage purposes. In terms of material, graphene-based flexible electronics have become very popular for wearable and healthcare devices due to their exceptional mechanical strength, thermal stability, high electrical conductivity, and biocompatibility. A graphene-based flexible antenna for data communication from wearable head imaging devices over a 5G network was designed and modelled. The antenna operated at the 34.5 GHz range and was designed using an 18 µm thin graphene film for the conductive radiative patch and ground with electric conductivity of 3.5 × 105 S/m. The radiative patch was designed in a fractal fashion to provide sufficient antenna flexibility for wearable uses. The patch was designed over a 1.5 mm thick flexible polyamide substrate that made the design suitable for wearable applications. This paper presented the 3D modelling and analysis of the 5G flexible antenna for communication in a digital care-home model. The analyses were carried out based on the antenna's reflection coefficient, gain, radiation pattern, and power balance. The time-domain signal analysis was carried out between the two antennas to mimic real-time communication in wearable devices.

Evaluation of Unobtrusive Microwave Sensors in Healthcare 4.0-Toward the Creation of Digital-Twin Model.

The prevalence of chronic diseases and the rapid rise in the aging population are some of the major challenges in our society. The utilization of the latest and unique technologies to provide fast, accurate, and economical ways to collect and process data is inevitable. Industry 4.0 (I4.0) is a trend toward automation and data exchange. The utilization of the same concept of I4.0 in healthcare is termed Healthcare 4.0 (H4.0). Digital Twin (DT) technology is an exciting and open research field in healthcare. DT can provide better healthcare in terms of improved patient monitoring, better disease diagnosis, the detection of falls in stroke patients, and the analysis of abnormalities in breathing patterns, and it is suitable for pre- and post-surgery routines to reduce surgery complications and improve recovery. Accurate data collection is not only important in medical diagnoses and procedures but also in the creation of healthcare DT models. Health-related data acquisition by unobtrusive microwave sensing is considered a cornerstone of health informatics. This paper presents the 3D modeling and analysis of unobtrusive microwave sensors in a digital care-home model. The sensor is studied for its performance and data-collection capability with regards to patients in care-home environments.

Habb-e-Asgand, polyherbal Unani formulation, protects liver and antioxidative enzymes against paracetamol induced hepatotoxicity.

Abstract Context: Habb-e-Asgand, a polyherbal Homeopathy/Unani drug from Hamdard Wakf Laboratory, India, used in arthritis, gout and joint pain, is a mixture of many herbal medicinal plants. Scientific attempts to test and validate its efficacy are meager. Objective: To evaluate the hepatoprotective and antioxidative potential of Habb-e-Asgand against paracetamol toxicity. Materials and methods: Swiss albino male mice (n = 5/group) were treated with Habb-e-Asgand (250 mg/kg, body weight (b.w.) in normal saline orally for 14 days followed by a single dose of paracetamol (400 mg/kg b.w./normal saline) intraperitoneally 24 h before euthanization. We estimated liver function (LFTs) using diagnostic kits, while antioxidant enzymes, cytochrome P450 (CYP) and lipid peroxidation (LPO) were measured using spectrophotometric methods. Results: Paracetamol alone induced LFTs enzymes significantly (p < 0.05 and p < 0.01, 0.001), serum glutamate pyruvate transaminase (SGPT, ∼70%), serum glutamate oxaloacetate transaminase (SGOT, ∼20%), alkaline phosphatase (ALP, ∼20%), total bilirubin (∼30%), CYP activity (∼50%) and LPO (∼45%), while it significantly inhibited the activity of antioxidant enzymes glutathione reductase (GR, ∼35%), glutathione peroxidase (GPx, ∼40%), glutathione S-tranferase (GST, ∼16%), catalase (CAT, ∼84%) and glutathione (GSH, ∼30%) contents. Habb-e-Asgand alone and in combination of paracetamol significantly (p < 0.05, 0.01, 0.001) decreased LFT levels (20-25%), CYP activity (∼45%) and LPO level (∼25%), while it induced antioxidant enzyme activity (GR, ∼15%; GPx, ∼17%; GST, ∼20% and CAT, ∼60%). Discussion: Paracetamol metabolites may be mediating production of reactive oxidant species (ROS) and liver injury, which are attenuated by Habb-e-Asgand antioxidant constituents. Conclusion: Habb-e-Asgand may be used as a prophylaxis for ROS related liver injury.