Migraine headache (MH) classification using machine learning methods with data augmentation.

Migraine headache, a prevalent and intricate neurovascular disease, presents significant challenges in its clinical identification. Existing techniques that use subjective pain intensity measures are insufficiently accurate to make a reliable diagnosis. Even though headaches are a common condition with poor diagnostic specificity, they have a significant negative influence on the brain, body, and general human function. In this era of deeply intertwined health and technology, machine learning (ML) has emerged as a crucial force in transforming every aspect of healthcare, utilizing advanced facilities ML has shown groundbreaking achievements related to developing classification and automatic predictors. With this, deep learning models, in particular, have proven effective in solving complex problems spanning computer vision and data analytics. Consequently, the integration of ML in healthcare has become vital, especially in developing countries where limited medical resources and lack of awareness prevail, the urgent need to forecast and categorize migraines using artificial intelligence (AI) becomes even more crucial. By training these models on a publicly available dataset, with and without data augmentation. This study focuses on leveraging state-of-the-art ML algorithms, including support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), decision tree (DST), and deep neural networks (DNN), to predict and classify various types of migraines. The proposed models with data augmentations were trained to classify seven various types of migraine. The proposed models with data augmentations were trained to classify seven various types of migraine. The revealed results show that DNN, SVM, KNN, DST, and RF achieved an accuracy of 99.66%, 94.60%, 97.10%, 88.20%, and 98.50% respectively with data augmentation highlighting the transformative potential of AI in enhancing migraine diagnosis.

Nano-residronate loaded κ-carrageenan-based injectable hydrogels for bone tissue regeneration.

Bone tissue possesses intrinsic regenerative capabilities to address deformities; however, its ability to repair defects caused by severe fractures, tumor resections, osteoporosis, joint arthroplasties, and surgical reconsiderations can be hindered. To address this limitation, bone tissue engineering has emerged as a promising approach for bone repair and regeneration, particularly for large-scale bone defects. In this study, an injectable hydrogel based on kappa-carrageenan-co-N-isopropyl acrylamide (κC-co-NIPAAM) was synthesized using free radical polymerization and the antisolvent evaporation technique. The κC-co-NIPAAM hydrogel's cross-linked structure was confirmed using Fourier transform infrared spectra (FTIR) and nuclear magnetic resonance (1H NMR). The hydrogel's thermal stability and morphological behavior were assessed using thermogravimetric analysis (TGA) and scanning electron microscopy (SEM), respectively. Swelling and in vitro drug release studies were conducted at varying pH and temperatures, with minimal swelling and release observed at low pH (1.2) and 25 °C, while maximum swelling and release occurred at pH 7.4 and 37oC. Cytocompatibility analysis revealed that the κC-co-NIPAAM hydrogels were biocompatible, and hematoxylin and eosin (H&E) staining demonstrated their potential for tissue regeneration and enhanced bone repair compared to other experimental groups. Notably, digital x-ray examination using an in vivo bone defect model showed that the κC-co-NIPAAM hydrogel significantly improved bone regeneration, making it a promising candidate for bone defects.

Biofunctional Hyaluronic Acid/κ-Carrageenan Injectable Hydrogels for Improved Drug Delivery and Wound Healing.

The in situ injectable hydrogel system offers a widespread range of biomedical applications in prompt chronic wound treatment and management, as it provides self-healing, maintains a moist wound microenvironment, and offers good antibacterial properties. This study aimed to develop and evaluate biopolymer-based thermoreversible injectable hydrogels for effective wound-healing applications and the controlled drug delivery of meropenem. The injectable hydrogel was developed using the solvent casting method and evaluated for structural changes using proton nuclear magnetic resonance, Fourier transforms infrared spectroscopy, thermogravimetric analysis, and scanning electron microscopy. The results indicated the self-assembly of hyaluronic acid and kappa-carrageenan and the thermal stability of the fabricated injectable hydrogel with tunable gelation properties. The viscosity assessment indicated the in-situ gelling ability and injectability of the hydrogels at various temperatures. The fabricated hydrogel was loaded with meropenem, and the drug release from the hydrogel in phosphate buffer saline (PBS) with a pH of 7.4 was 96.12%, and the simulated wound fluid with a pH of 6.8 was observed to be at 94.73% at 24 h, which corresponds to the sustained delivery of meropenem. Antibacterial studies on P. aeruginosa, S. aureus, and E. coli with meropenem-laden hydrogel showed higher zones of inhibition. The in vivo studies in Sprague Dawley (SD) rats presented accelerated healing with the drug-loaded injectable hydrogel, while 90% wound closure with the unloaded injectable hydrogel, 70% in the positive control group (SC drug), and 60% in the negative control group was observed (normal saline) after fourteen days. In vivo wound closure analysis confirmed that the developed polymeric hydrogel has synergistic wound-healing potential.

Self-crosslinked chitosan/κ-carrageenan-based biomimetic membranes to combat diabetic burn wound infections.

Diabetic wound infection often leads to compromised healing with frequent chances of sepsis, amputation and even death. Traditional patient care emphasized on early debridement and fluid resuscitation followed by intravenous antibiotics therapy. However, compromised vasculature often limit the systemic effect of antibiotics. Current study focused formulation of chitosan HCl, κ- carrageenan and PVA based physical cross-linked hydrogel membrane dressings loaded with cefotaxime sodium (CTX), for potential diabetic burn wound healing by adopting solvent casting method. Results of mechanical strength shows tensile strength and % elongation of 12.63 ± 0.25 and 48 ±3.05 respectively. Water vapor transmission rate (WVTR) depicts that despite of formulation KCP3 and KCP6, all hydrogel membranes have WVTR value in range of ideal dressing i.e., 2000-2500 g/m2/day. Whereas, all hydrogel membranes have oxygen permibility values more than 8.2 mg/ml. Bacterial penetration analysis confirms the barrier property of formulated membranes. Drug loaded hydrogel membrane showed control release up to 24 hr which provide protection against bacterial proliferation. Present study aims to constructs diabetic burn rat model which demonstrate that CTX loaded hydrogel membrane shown significantly rapid wound closure higher re-epithelization and numerous granulation tissue formation as compared to positive and negative control group. Conclusively, it is confirmed that formulated hydrogel membranes are beneficial and can be considered as a promising membrane dressing to treat diabetic burn wound.