Currently, the development of deep learning-based multimodal learning is advancing rapidly, and is widely used in the field of artificial intelligence-generated content, such as image-text conversion and image-text generation. Electronic health records are digital information such as numbers, charts, and texts generated by medical staff using information systems in the process of medical activities. The multimodal fusion method of electronic health records based on deep learning can assist medical staff in the medical field to comprehensively analyze a large number of medical multimodal data generated in the process of diagnosis and treatment, thereby achieving accurate diagnosis and timely intervention for patients. In this article, we firstly introduce the methods and development trends of deep learning-based multimodal data fusion. Secondly, we summarize and compare the fusion of structured electronic medical records with other medical data such as images and texts, focusing on the clinical application types, sample sizes, and the fusion methods involved in the research. Through the analysis and summary of the literature, the deep learning methods for fusion of different medical modal data are as follows: first, selecting the appropriate pre-trained model according to the data modality for feature representation and post-fusion, and secondly, fusing based on the attention mechanism. Lastly, the difficulties encountered in multimodal medical data fusion and its developmental directions, including modeling methods, evaluation and application of models, are discussed. Through this review article, we expect to provide reference information for the establishment of models that can comprehensively utilize various modal medical data.
ObjectiveTo summarized the clinical experience on laparoscopic radical surgery in patients with advanced distal gastric cancer. MethodsThe clinical data of 26 patients with advanced distant gastric cancer undergoing laparoscopic gastrectomy were retrospectively analyzed. ResultsLaparoscopic distal gastrectomy was performed successfully in all patients. The operation time was (283.2±27.6) min (270-450 min) and the blood loss was (178.4±67.4) ml (80-350 ml). The time of gastrointestinal function recovery was (2.8±1.2) d (2-4 d), out of bed activity time was (1.5±0.4) d (1-3 d) and liquid diet feeding was (3.5±1.4) d (3-4 d). The hospital stay was (10.0±2.6) d (7-13 d). The number of harvested lymph nodes was 11 to 34 (17.8±7.3). The distance from proximal surgical margin to tumor was (7.0±2.1) cm (5-12 cm) and the distance from distal surgical margin to tumor was (5.5±1.8) cm (4-8 cm), thus surgical margins were negative in all samples. All patients were followed up for 3-48 months (mean 18.5 months), two patients with poorly differentiated adenocarcinoma died of extensive metastasis in 13 and 18 months, respectively, and other patients survived well. ConclusionsLaparoscopic radical gastrectomy with D2 lymphadenectomy for advanced gastric cancer is safe and feasible. However, the advantage of laparoscopic technique over the conventional open surgery requires further study.
Objective To detect expression of miR-106a-5p in gastric cancer cells and gastric cancer tissue, and to analyze relationship between it’s expression with clinicopathologic characteristics, and in addition, to analyze its target genes and enriched pathway with bioinformatics method. Methods The expressions of miR-106a-5p in the different differentiation of gastric cancer cells AGS (well differentiation), MKN-28 (middle differentiation), HGC-27 (undifferentiation), MGC-803 (low differentiation), BGC-823 (low differentiation), MKN-45 (middle differentiation) and SGC-7901 (middle differentiation), the normal gastric mucosal epithelial cells GES-1, and the gastric cancer tissue and the corresponding adjacent tissue were detected by the real-time fluorescent quantitative PCR. Furthermore, the target genes of miR-106a-5p were predicted by using more than three softwares affiliated to mirWALK web database and the signal pathways of target genes were enriched by DAVID 6.7 software. Results The expressions of miR-106a-5p in the different differentiation degree of the gastric cancer cells (AGS, SGC-7901, MKN-45, MGC-803, BGC-823, and HGC-27) were up-regulated except the MKN-28 cell line as compared with the normal gastric mucosa cell line GES-1 (P<0.010 orP<0.001), and the expression of miR-106a-5p in the gastric cancer tissue was also up-regulated as compared with the corresponding adjacent tissue, the expression of miR-106a-5p in the gastric cancer tissue was associated with the lymph node metastasis or the invasion depth. The results of the bioinformatics analysis showed that the target genes of miR-106a-5p were enriched in the multiple signaling pathways associated with the cancer. Conclusion miR-106a-5p is a molecular marker of high expression in gastric cancer and a potential cancer gene associated with lymph node metastasis and invasion depth.
Wearable monitoring, which has the advantages of continuous monitoring for a long time with low physiological and psychological load, represents a future development direction of monitoring technology. Based on wearable physiological monitoring technology, combined with Internet of Things (IoT) and artificial intelligence technology, this paper has developed an intelligent monitoring system, including wearable hardware, ward Internet of Things platform, continuous physiological data analysis algorithm and software. We explored the clinical value of continuous physiological data using this system through a lot of clinical practices. And four value points were given, namely, real-time monitoring, disease assessment, prediction and early warning, and rehabilitation training. Depending on the real clinical environment, we explored the mode of applying wearable technology in general ward monitoring, cardiopulmonary rehabilitation, and integrated monitoring inside and outside the hospital. The research results show that this monitoring system can be effectively used for monitoring of patients in hospital, evaluation and training of patients’ cardiopulmonary function, and management of patients outside hospital.
Internet of Things (IoT) technology plays an important role in smart healthcare. This paper discusses IoT solution for emergency medical devices in hospitals. Based on the cloud-edge-device architecture, different medical devices were connected; Streaming data were parsed, distributed, and computed at the edge nodes; Data were stored, analyzed and visualized in the cloud nodes. The IoT system has been working steadily for nearly 20 months since it run in the emergency department in January 2021. Through preliminary analysis with collected data, IoT performance testing and development of early warning model, the feasibility and reliability of the in-hospital emergency medical devices IoT was verified, which can collect data for a long time on a large scale and support the development and deployment of machine learning models. The paper ends with an outlook on medical device data exchange and wireless transmission in the IoT of emergency medical devices, the connection of emergency equipment inside and outside the hospital, and the next step of analyzing IoT data to develop emergency intelligent IoT applications.