Search

Abstract Background Postoperative pain is a prevalent symptom experienced by patients undergoing surgical procedures. This study aims to develop deep learning algorithms for predicting acute postoperative pain using both essential patient details and real-time vital sign data during surgery. Methods Through a retrospective observational approach, we utilized Graph Attention Networks (GAT) and graph Transformer Networks (GTN) deep learning algorithms to construct the DoseFormer model while incorporating an attention mechanism. This model employed patient information and intraoperative vital signs obtained during Video-assisted thoracoscopic surgery (VATS) surgery to anticipate postoperative pain. By categorizing the static and dynamic data, the DoseFormer model performed binary classification to predict the likelihood of postoperative acute pain. Results A total of 1758 patients were initially included, with 1552 patients after data cleaning. These patients were then divided into training set (n = 931) and testing set (n = 621). In the testing set, the DoseFormer model exhibited significantly higher AUROC (0.98) compared to classical machine learning algorithms. Furthermore, the DoseFormer model displayed a significantly higher F1 value (0.85) in comparison to other classical machine learning algorithms. Notably, the attending anesthesiologists' F1 values (attending: 0.49, fellow: 0.43, Resident: 0.16) were significantly lower than those of the DoseFormer model in predicting acute postoperative pain. Conclusions Deep learning model can predict postoperative acute pain events based on patients' basic information and intraoperative vital signs.

Abstract Background Immune-mediated rejection was the major cause of graft dysfunction. Although the advances in immunosuppressive agents have markedly reduced the incidence of T-cell-mediated rejection after transplantation. However, the incidence of antibody-mediated rejection (AMR) remains high. Donor-specific antibodies (DSAs) were considered the major mediators of allograft loss. Previously, we showed that treatment with 18-kDa translocator protein (TSPO) ligands inhibited the differentiation and effector functions of T cells and reduced the rejection observed after allogeneic skin transplantation in mice. This study we further investigate the effect of TSPO ligands on B cells and DSAs production in the recipients of mixed-AMR model. Methods In vitro, we explored the effect of treatment with TSPO ligands on the activation, proliferation, and antibody production of B cells. Further, we established a heart-transplantation mixed-AMR model in rats. This model was treated with the TSPO ligands, FGIN1-27 or Ro5-4864, to investigate the role of ligands in preventing transplant rejection and DSAs production in vivo. As TSPO was the mitochondrial membrane transporters, we then investigated the TSPO ligands effect on mitochondrial-related metabolic ability of B cells as well as expression of downstream proteins. Results In vitro studies, treatment with TSPO ligands inhibited the differentiation of B cells into CD138+CD27+ plasma cells; reduced antibodies, IgG and IgM, secretion of B cells; and suppressed the B cell activation and proliferation. In the mixed-AMR rat model, treatment with FGIN1-27 or Ro5-4864 attenuated DSA-mediated cardiac-allograft injury, prolonged graft survival, and reduced the numbers of B cells, including IgG+ secreting B cells, T cells and macrophages infiltrating in grafts. For the further mechanism exploration, treatment with TSPO ligands inhibited the metabolic ability of B cells by downregulating expression of pyruvate dehydrogenase kinase 1 and proteins in complexes I, II, and IV of the electron transport chain. Conclusions We clarified the mechanism of action of TSPO ligands on B-cell functions and provided new ideas and drug targets for the clinical treatment of postoperative AMR.

Perioperative neurocognitive disorders (PNDs) are frequent complications associated with cognitive impairment during the perioperative period, including acute postoperative delirium and long-lasting postoperative cognitive dysfunction. There are some risk factors for PNDs, such as age, surgical trauma, anesthetics, and the health of the patient, but the underlying mechanism has not been fully elucidated. Pyroptosis is a form of programmed cell death that is mediated by the gasdermin protein and is involved in cognitive dysfunction disorders. The canonical pathway induced by nucleotide oligomerization domain (NOD)-, leucine-rich repeat (LRR)- and pyrin domain-containing protein 3 (NLRP3) inflammasomes contributes to PNDs, which suggests that targeting NLRP3 inflammasomes may be an effective strategy for the treatment of PNDs. Therefore, inhibiting upstream activators and blocking the assembly of the NLRP3 inflammasome may attenuate PNDs. The present review summarizes recent studies and systematically describes the pathogenesis of NLRP3 activation and regulation and potential therapeutics targeting NLRP3 inflammasomes in PNDs patients.

The leaf area index (LAI) is an essential biophysical parameter for describing the vegetation canopy structure and predicting its growth and productivity. Using unmanned aerial vehicle (UAV) hyperspectral imagery to accurately estimate the LAI is of great significance for Spartina alterniflora (S. alterniflora) growth status monitoring. In this study, UAV hyperspectral imagery and the LAI of S. alterniflora during the flourishing growth period were acquired. The hyperspectral data were preprocessed with Savitzky–Golay (SG) smoothing, and the first derivative (FD) and the second derivative (SD) spectral transformations of the data were then carried out. Then, using the band combination index (BCI) method, the characteristic bands related to the LAI were extracted from the hyperspectral image data obtained with the UAV, and spectral indices (SIs) were constructed through the characteristic bands. Finally, three machine learning (ML) regression methods—optimized support vector regression (OSVR), optimized random forest regression (ORFR), and optimized extreme gradient boosting regression (OXGBoostR)—were used to establish LAI estimation models. The results showed the following: (1) the three ML methods accurately predicted the LAI, and the optimal model was provided by the ORFR method, with an R2 of 0.85, an RMSE of 0.19, and an RPD of 4.33; (2) the combination of FD SIs improved the model accuracy, with the R2 value improving by 41.7%; (3) the band combinations screened using the BCI method were mainly concentrated in the red and near-infrared bands; (4) the higher LAI was distributed on the seaward side of the study area, while the lower LAI was located at the junction between the S. alterniflora and the tidal flat. This study serves as both theoretical and technological support for research on the LAI of S. alterniflora and as a solid foundation for the use of UAV remote sensing technologies in the supervisory control of S. alterniflora.