Purpose/Significance To improve the performance of named entity recognition(NER)model of Chinese electronic medi-cal records(EMR)for better organization and mining of medical information.Method/Process The ERNIE-BiGRU-Attention-CRF NER model of Chinese EMR is constructed.Firstly,the ERNIE1.0 pre-training model is used to generate word vectors with semantic features,and then BiGRU is utilized to capture the global semantic features and grammatical structural features,which are fed into the Attention mechanism to further enhance the capture of the semantic features,and finally,the CRF decoding layer is connected to output the label sequences with the maximum global probability.Result/Conclusion Comparison experiments and ablation experiments are car-ried out on the publicly available medical text dataset CCKS2017,and examples analysis is conducted using the generated model.The model proposed in this paper achieves better recognition results.

Objective:To summarize the experience of robot-assisted enucleation of tumors located in uncinate process of pancreas.Methods:This is a retrospective case series study. The clinical data of patients with robot-assisted enucleation of tumors located in the uncinate process of pancreas at the Department of Gastroenterology and Pancreatic Surgery,Zhejiang Provincial People′s Hospital from June 2019 to December 2023 were retrospectively analyzed. A total of 16 cases were enrolled,including 10 males and 6 females,with an age( M(IQR)) of 56(21)years (range: 28 to 77 years),and body mass index of 22.4(2.3)kg/m 2 (range:19.8 to 25.6 kg/m 2). Follow-up was asked every 6 to 12 months after the first 3-month postoperative follow-up through out-patient service or via telephone. Results:In total 16 cases,there were 11 cases with pancreatic enucleation,and 5 cases with resection of the uninate process. The operation time was 70(60) minutes (range: 40 to 165 minutes),and the blood loss was 30(13)ml (range: 10 to 80 ml). The rate of pancreatic fistula was 5/16. The length of stay was 8(6)days (range: 5 to 33 days). The pathological finding included non-functional neuroendocrine tumor( n=3),insulinoma( n=2),introductal papillary mucinous neoplasm ( n=5),solid pseudopapillary neoplasm ( n=2),mucinous cystadenoma ( n=1),serous cystadenoma ( n=2),pseudocyst ( n=1). Follow-up as of March 12, 2024, the follow-up time was 16(12)months (range: 3 to 41 months). All patients had no new onset diabetes and no dyspepsia. Conclusion:Robot-assisted surgical system can be used for local resection of uncinate process tumors of pancreas,and the quality of life of patients can be improved.

Objective:To summarize the experience of robot-assisted enucleation of tumors located in uncinate process of pancreas.Methods:This is a retrospective case series study. The clinical data of patients with robot-assisted enucleation of tumors located in the uncinate process of pancreas at the Department of Gastroenterology and Pancreatic Surgery,Zhejiang Provincial People′s Hospital from June 2019 to December 2023 were retrospectively analyzed. A total of 16 cases were enrolled,including 10 males and 6 females,with an age( M(IQR)) of 56(21)years (range: 28 to 77 years),and body mass index of 22.4(2.3)kg/m 2 (range:19.8 to 25.6 kg/m 2). Follow-up was asked every 6 to 12 months after the first 3-month postoperative follow-up through out-patient service or via telephone. Results:In total 16 cases,there were 11 cases with pancreatic enucleation,and 5 cases with resection of the uninate process. The operation time was 70(60) minutes (range: 40 to 165 minutes),and the blood loss was 30(13)ml (range: 10 to 80 ml). The rate of pancreatic fistula was 5/16. The length of stay was 8(6)days (range: 5 to 33 days). The pathological finding included non-functional neuroendocrine tumor( n=3),insulinoma( n=2),introductal papillary mucinous neoplasm ( n=5),solid pseudopapillary neoplasm ( n=2),mucinous cystadenoma ( n=1),serous cystadenoma ( n=2),pseudocyst ( n=1). Follow-up as of March 12, 2024, the follow-up time was 16(12)months (range: 3 to 41 months). All patients had no new onset diabetes and no dyspepsia. Conclusion:Robot-assisted surgical system can be used for local resection of uncinate process tumors of pancreas,and the quality of life of patients can be improved.

Objective: To investigate the application of metagenomic next-generation sequencing (mNGS) in detection of the rare or difficult-to-cultivate pathogens. Methods: One patient with acute lymphoblastic leukemia who went through allogeneic hematopoietic stem cell transplantation (allo-HSCT) developed symptoms of infection after transplantation. Conventional microbial culture, polymerase chain reaction (PCR), and mNGS combined with biological information analysis were performed with plasma and cerebrospinal fluid samples, the anti-infective treatment was adjusted according to the test results, and the efficacy was assessed. Results: No suspected pathogens were detected by microbial culture and PCR in the cerebrospinal fluid and plasma samples since the patient developed infection symptoms. However, Legionella pneumophila was analyzed by mNGS in the cerebrospinal fluid specimen on day 23 after allo-HSCT (reads count: 19 655), and it was considered as the principal pathogen after comprehensively evaluating the patient's clinical manifestations and the test results. Then the antimicrobial treatments were adjusted according to the patient's clinical manifestations and laboratory test results, and the number of gene sequences of Legionella pneumophila was monitored by mNGS method. Azithromycin, tigecycline, and other antibiotics effective for Legionella pneumophila were used after detecting this pathogen. A total of 15 mNGS analysis were performed during the 5-month period, and the highest number of Legionella pneumophila sequences monitored in the cerebrospinal fluid was 2 226, the lowest was 253 and eventually turned negative. The clinical symptoms and treatment outcomes were consistent with the mNGS monitoring results. Conclusions The mNGS technology has significant value in detection of the rare and difficult-to-cultivate pathogens. The mNGS technology provides a valuable supplement to microbial culture and PCR methods.

Objective To analyze the clinical courses and outcomes of COVID-19 cases and the influencing factors in Guangdong province and provide basis for the formulation or adjustment of medical care and epidemic control strategy for COVID-19. Methods We collected demographic data, medical histories, clinical courses and outcomes of 1 350 COVID-19 patients reported in Guangdong as of 4 March 2020 via epidemiological investigation and process tracking. Disease severity and clinical course characteristics of the patients and influencing factors of severe illness were analyzed in our study. Results Among 1 350 cases of COVID-19 cases in Guangdong, 72 (5.3%) and 1049 (77.7%) were mild and ordinary cases, 164 (12.1%) were severe cases, 58 (4.3%) were critical cases and 7 (0.5%) were fatal. The median duration of illness were 23 days ( P 25 - P 75 : 18-31 days) and the median length of hospitalization were 20 days ( P 25 - P 75 : 15-27 days). For severe cases, the median time of showing severe manifestations was on the 12th day after onset ( P 25 - P 75 : 9th to 15th days), and the median time of severe manifestation lasted for 8 days P 25 - P 75 : 4-14 days). Among 1 066 discharged/fetal cases, 36.4% (36/99) and 1.0% (1/99) of the mild cases developed to ordinary cases and severe cases respectively after admission; and 5.2% (50/968) and 0.6% (6/968) of the ordinary cases developed to severe cases, and critical cases respectively after admission. In severe cases, 11.4% developed to critical cases (10/88). The influencing factors for severe illness or worse included male (a HR =1.87, 95% CI : 1.43-2.46), older age (a HR =1.67, 95% CI : 1.51-1.85), seeking medical care on day 2-3 after onset (a HR =1.73, 95% CI : 1.20-2.50) pre-existing diabetes (a HR =1.75, 95% CI : 1.12-2.73) and hypertension (a HR =1.49, 95% CI : 1.06-2.09). Conclusions The course of illness and length of hospitalization of COVID-19 cases were generally long and associated with severity of disease clinical outcomes. The severe cases were mainly occurred in populations at high risk. In the epidemic period, classified management of COVID-19 cases should be promoted according to needs for control and prevention of isolation and treatment for the purpose of rational allocation of medical resources.