1.Research on intelligent medicine based on knowledge graph
Siwei YU ; Hao FAN ; Fei WANG ; Lei XU
Chinese Medical Equipment Journal 2017;38(3):109-111,126
Objective To discuss the use of knowledge graph technology to connect various trivial and fragmented knowledge in various medical information systems and support comprehensive knowledge retrieval and intelligent medical applications such as Q & A and clinical decision support.Methods Based on the construction of medical field ontology and semantic labeling of medical knowledge base,the medical knowledge graph was constructed and applied to intelligent medicine,with chronic disease taken as an example.Results The construction method of medical knowledge graph and its application in semantic analysis,reasoning and disease-assisted diagnosis system based on medical knowledge base were put forward.Conclusion The application of intelligent medicine based on knowledge graph will play an important role in contradiction between the supply of high-quality medical resources and increasing medical requirements.
2.Clinical characteristics and prognostic analysis of children with acute pancreatitis in the pediatric intensive care unit
Siwei WANG ; Fei WANG ; Yiping ZHOU ; Jiaying DOU ; Yun CUI ; Yucai ZHANG
Chinese Pediatric Emergency Medicine 2022;29(4):266-270
Objective:To investigate the clinical characteristics and prognosis of children with acute pancreatitis(AP)admitted to the pediatric intensive care unit(PICU).Methods:The etiology, clinical data, imaging features, complications, and outcomes of children with AP admitted to PICU at Shanghai Children′s Hospital from July 2016 to June 2021 were retrospectively analyzed.Results:Totally, 47 patients with AP including 24 males and 23 females were enrolled.The mean age was 84(48, 144)months.Four patients with mild AP, 5 patients with moderately severe AP(MSAP)and 38 cases with severe AP(SAP)were diagnosed.The main etiology was drug-related pancreatitis in 23 cases(48.9%). The organ dysfunction mainly included shock in 28 cases(59.6%), acute respiratory failure in 21 cases(44.7%), gastrointestinal disorders in 30 cases(63.8%), and coagulopathy in 29 cases(61.7%). The complications included capillary leakage syndrome in 18 cases(38.3%)and hyperglycemia(>8 mmol/L)in 24 cases(51.1%). Serum amylase and lipase levels were increased in 47 cases(100%). There were significant differences in blood lactate[3.0(2.1, 4.5)mmol/L vs.1.6(1.1, 3.1)mmol/L, P=0.013], and the use of vasoactive drugs[15.0(0, 75.0)vs.0(0, 8.8), P=0.035] between drug-induced pancreatitis and non-drug-induced pancreatitis.All the patients′conditions were improved after treatment and transferred out of PICU. Conclusion:The etiology of acute pancreatitis in children is mainly drug-related, and the main organ dysfunction includes shock, acute respiratory failure, gastrointestinal dysfunction and coagulation dysfunction.The prognosis of childhood pancreatitis is good.
3.Construction of a global health talent training evaluation index system based on bibliometric analysis
Xiaoqing TAO ; Xuejiao MA ; Siwei FEI ; Lei DUAN ; Shan LÜ ; Jiani WU
Chinese Journal of Schistosomiasis Control 2024;36(2):191-197
Objective To identify the current research hotspots of global health training, and construct a global health talent training evaluation index system. Methods Publications pertaining to global health talent training evaluation were retrieved in China National Knowledge Infrastructure, Wanfang Database, and Web of Science Core Collection from 2003 to 2022, and keywords were extracted from eligible publications for co-occurrence and cluster analyses using the CiteSpace software. Based on keywords clustering results, a global health talent training evaluation index system was constructed using a context, input, process, and product (CIPP) evaluation model as a theoretical framework. Results A total of 692 Chinese publications and 1 264 English publications were included. Keyword co-occurrence and cluster analyses yielded 10 Chinese and 10 English keyword clusters, and the 10 Chinese keyword clusters included analytic hierarchy process, health diplomacy, personnel structure, crossdiscipline, educational assessment, global health discipline development, training needs, curriculum program, quality evaluation and logistics support, while the English keyword clusters included evidence-based practice, capacity building, global health, quality of life, machine learning, leadership, sub-Saharan Africa, health equity, global health security and global health diplomacy. Based on keyword clustering, a global health talent training evaluation index system was constructed with CIPP as the theoretical framework, which contained 4 primary indicators, 15 secondary indicators and 59 tertiary indicators, and the primary indicators included 4 dimensions of context evaluation, input evaluation, process evaluation and product evaluation. Conclusions A global health talent training evaluation index system has been constructed, which provides an effective evaluation tool and quantitative evidence for future global health talent training.