Search

Percutaneous coronary intervention (PCI) has become a vital treatment approach for coronary artery disease, but the clinical data of PCI cannot be directly utilized due to its unstructured characteristics. The existing clinical named entity recognition (CNER) has been used to identify specific entities such as body parts, drugs, and diseases, but its specific potential in PCI clinical texts remains largely unexplored. How to effectively use CNER to deeply mine the information in the existing PCI clinical records is worth studying. In this paper, a total of 24 267 corpora are collected from the Cardiovascular Disease Treatment Center of the People's Hospital of Liaoning Province in China. We select three types of clinical record texts of fine-grained PCI surgical information, from which 5.8% of representative surgical records of PCI patients are selected as datasets for labeling. To fully utilize global information and multi-level semantic features, we design a novel character-level vector embedding method and further propose a new hybrid model based on it. Based on the classic Bidirectional Long Short-Term Memory Network (BiLSTM), the model further integrates Convolutional Neural Networks (CNNs) and Bidirectional Encoder Representations from Transformers (BERTs) for feature extraction and representation, and finally uses Conditional Random Field (CRF) for decoding and predicting label sequences. This hybrid model is referred to as BCC-BiLSTM in this paper. In order to verify the performance of the proposed hybrid model for extracting PCI surgical information, we simultaneously compare both representative traditional and intelligent methods. Under the same circumstances, compared with other intelligent methods, the BCC-BiLSTM proposed in this paper reduces the word vector dimension by 15%, and the F1 score reaches 86.2% in named entity recognition of PCI clinical texts, which is 26.4% higher than that of HMM. The improvement is 1.2% higher than BiLSTM + CRF and 0.7% higher than the most popular BERT + BiLSTM + CRF. Compared with the representative models, the hybrid model has better performance and can achieve optimal results faster in the model training process, so it has good clinical application prospects. [ABSTRACT FROM AUTHOR]

Machine learning provides increasingly reliable assistance for medical experts in diagnosing coronary heart disease. This study proposes a deep learning hybrid model based coronary heart disease (CAD) prediction method, which can significantly improve the prediction accuracy compared to traditional solutions. This research scheme is based on the data of 7291 patients and proposes a hybrid model, which uses two different deep neural network models and a recurrent neural network model as the main model for training. The prediction results based on the main model training use a k-nearest neighbor model for secondary training so as to improve the accuracy of coronary heart disease prediction. The comparison between the model prediction results and the clinical diagnostic results shows that the prediction model has a prediction accuracy rate of 82.8%, a prediction precision rate of 87.08%, a prediction recall rate of 88.57%, a prediction F1-score of 87.82%, and an area under the curve value of 0.8 in the test set. Compared to single model machine learning predictions, the hybrid model has a significantly improved accuracy and has effectively solved the problem of overfitting. A deep learning based CAD prediction hybrid model that combines multiple weak models into a strong model can fully explore the complex inter-relationships between various features under limited feature values and sample size, improve the evaluation indicators of the prediction model, and provide effective auxiliary support for CAD diagnosis. [ABSTRACT FROM AUTHOR]

Recent studies have found that cardiac stem cells (CSCs) are present in the adult heart. CSCs play an important role in maintaining the balance of the number of myocardial cells. The purpose of this study was to examine characteristics of human CSCs and their correlation with clinical characteristics of patients. We collected heart auricles of 105 patients (age range, 1–78 years; mean, 55.6 ± 17.0 years) undergoing cardiac surgery to obtain CSCs. We assayed the percentage of c-kit positive (c-kit+) CSCs with flow cytometry. Plasma Nɛ-(carboxymethyl)lysine (CML) concentrations were measured by enzyme-linked immunosorbent assay. The percentage of c-kit+ CSCs was 4.96 ± 3.12% (0.98–17.17%), and this was significantly negatively correlated with age, the presence of diabetes mellitus (DM) and coronary heart disease (CHD) (r values were −0.797 [P < 0.01], −0.500 [P < 0.01] and −0.250 [P = 0.011], respectively). The percentage of c-kit+ CSCs was significantly negatively correlated with CML concentrations (r = −0.859, P < 0.01). The percentage of c-kit+ CSCs decreases with ageing and is further decreased in patients with DM and/or CHD. Furthermore, plasma CML concentrations may have potential as an indicator of the number of c-kit+ CSCs. [ABSTRACT FROM AUTHOR]

Background: Nε-carboxymethyl-lysine (CML) is a major advanced glycation end-product (AGEs) widely found in foods. The aim of our study was to evaluate how exogenous CML-peptide is dynamically absorbed from the gastrointestinal tract and eliminated by renal tubular secretion using microPET imaging. Methods: The present study consisted of three investigations. In study I, we synthesized the imaging tracer 18F-CML by reacting N-succinimidyl 4-18F-fluorobenzoate (18F-SFB) with CML. In study II, the biological activity of 18F-CML was evaluated in RAW264.7 cells and HepG2 cells. In study III, the biodistribution and elimination of AGEs in ICR mice were studied in vivo following tail vein injection and intragastric administration of 18F-CML. Result: The formation of 18F-CML was confirmed by comparing its retention time with the corresponding reference compound 19F-CML. The radiochemical purity (RCP) of 18F-CML was >95%, and it showed a stable character in vitro and in vivo. Uptake of 18F-CML by RAW264.7 cells and HepG2 cells could be inhibited by unmodified CML. 18F-CML was quickly distributed via the blood, and it was rapidly excreted through the kidneys 20 min after tail vein injection. However, 18F-CML was only slightly absorbed following intragastric administration. After administration of 18F-CML via a stomach tube, the radioactivity was completely localized in the stomach for the first 15 min. At 150 min post intragastric administration, intense accumulation of radioactivity in the intestines was still observed. Conclusions: PET technology is a powerful tool for the in vivo analysis of the gastrointestinal absorption of orally administered drugs. 18F-CML is hardly absorbed by the gastrointestinal tract. It is rapidly distributed and eliminated from blood following intravenous administration. Thus, it may not be harmful to healthy bodies. Our study showed the feasibility of noninvasively imaging 18F-labeled AGEs and was the first to describe CML-peptide gastrointestinal absorption by means of PET. [ABSTRACT FROM AUTHOR]