FT-GAT: Graph neural network for predicting spontaneous breathing trial success in patients with mechanical ventilation.

BACKGROUND AND OBJECTIVES: Intensive care unit (ICU) physicians perform weaning procedures considering complex clinical situations and weaning protocols; however, liberating critical patients from mechanical ventilation (MV) remains challenging. Therefore, this study aims to aid physicians in deciding the early liberation of patients from MV by developing an artificial intelligence model that predicts the success of spontaneous breathing trials (SBT). METHODS: We retrospectively collected data of 652 critical patients (SBT success: 641, SBT failure: 400) who received MV at the Chungbuk National University Hospital (CBNUH) ICU from July 2020 to July 2022, including mixed and trauma ICUs. Patients underwent SBTs according to the CBNUH weaning protocol or physician's decision, and SBT success was defined as extubation performed by the physician on the SBT day. Additionally, our dataset comprised 11 numerical and 2 categorical features that can be obtained for any ICU patient, such as vital signs and MV setting values. To predict SBT success, we analyzed tabular data using a graph neural network-based approach. Specifically, the graph structure was designed considering feature correlation, and a novel deep learning model, called feature tokenizer graph attention network (FT-GAT), was developed for graph analysis. FT-GAT transforms the input features into high-dimensional embeddings and analyzes the graph via the attention mechanism. RESULTS: The quantitative evaluation results indicated that FT-GAT outperformed conventional models and clinical indicators by achieving the following model performance (AUROC): FT-GAT (0.80), conventional models (0.69-0.79), and clinical indicators (0.65-0.66) CONCLUSIONS: Through timely detection critical patients who can succeed in SBTs, FT-GAT can help prevent long-term use of MV and potentially lead to improvement in patient outcomes.

Effectiveness of the use of an oscillating positive expiratory pressure device in bronchiectasis with frequent exacerbations: a single-arm pilot study.

Impaired airway clearance in patients with non-cystic fibrosis bronchiectasis causes frequent bacterial infection, chronic inflammation, and progressive tissue destruction. We aimed to evaluate whether an oscillating positive expiratory pressure (OPEP) device could allow effective sputum expectoration and prevent acute exacerbations in patients with bronchiectasis who had frequent acute exacerbations. This open-label, single-arm, prospective study included 17 patients who experienced three or more acute exacerbations in the past year. We evaluated the prevention of acute exacerbations, subjective symptom improvement, and change in sputum amount during the use of the Aerobika (Trudell Medical International, London, ON) OPEP device twice daily for 6 months. Of all enrolled patients, only two acute exacerbations occurred during the study period, indicating a significant decrease compared with the number of acute exacerbations before the device use (p < 0.001). Additionally, Bronchiectasis Health Questionnaire score changed from 58.7 to 66.6, showing significant improvement over the treatment period (p < 0.001). The largest sputum volume was observed 3 months after OPEP device use (baseline: 10 ml, 3rd month 25 ml, p = 0.325). There were no major adverse events related to the use of OPEP devices. Twice-daily physiotherapy with OPEP device in patients with bronchiectasis who have frequent exacerbations may facilitate symptomatic improvement and prevention of acute exacerbations without serious adverse events.

Recent advances in biological macromolecule based tissue-engineered composite scaffolds for cardiac tissue regeneration applications.

Tissue engineering has become a primary research topic for the treatment of diseased or damaged cardiac tissue, which is a global healthcare concern. Current tissue engineering strategies utilise biomimetic scaffolds and cells that promote healthy growth and regeneration of cardiac tissue. Successful cardiac tissue engineering (CTE) requires scaffolds that mimic the natural anisotropy and microstructure of native tissues, while simultaneously supporting proliferation and differentiation and acting as a natural extracellular matrix (ECM) substitute until it is replaced by the body's residing cells. Among the various types of scaffolding materials, naturally occurred biological macromolecules, synthetic polymers, electroconductive polymers and electroconductive nanoparticles are utilised due to their unique biological and physicochemical properties. In this context, naturally occurred biological macromolecules has gained significant attention in designing tissue engineered composite scaffolds for cardiac tissue regeneration applications due to their excellent biocompatibility, cytocompatibility, biodegradability, and low immunogenicity. The objective of this review is to summarize the micro and macro architecture of the heart and its functional properties and provides a firm summarization of recent progress in biological macromolecules based composites scaffolds with innovative fabrication techniques so that it may help the design of novel substitutes for cardiac tissue regeneration application.