[Application of pretrained model based on electronic medical record in recognition of acute respiratory infection].

Objective: To evaluate the recognition of acute respiratory infection (ARI) by a pretrained model based on electronic medical records (EMRs). Methods: 38 581 EMRs were obtained from Chongqing University Three Gorges Hospital in December 2021. Bidirectional encoder representation from transformers (BERT) pretrained model was used to identify ARI in EMRs. The results of medical professionals were considered as the gold standard to calculate the sensitivity, specificity, Kappa value, and area under the curve of the receiver operating characteristic (AUC). Results: There were 3 817 EMRs in the test set, with 1 200 ARIs. A total of 1 205 cases were determined as ARI by the model, with a sensitivity of 92.67% (1 112/1 200) and a specificity of 96.45% (2 524/2 617). The model identified ARI with similar accuracy in males and females (AUCs 0.95 and 0.94, respectively), and was more accurate in identifying ARI cases in those aged less than 18 than in adults 18-59 and adults 60 and older (AUCs 0.94, 0.89 and 0.94, respectively). The current model had a better identification of ARIs in outpatient patients than that in hospitalized patients, with AUCs of 0.74 and 0.95, respectively. Conclusion: The use of the BERT pretrained model based on EMRs has a good performance in the recognition of ARI cases, especially for the outpatients and juveniles. It shows a great potential to be applied to the monitoring of ARI cases in medical institutions.

[Evaluation of demand of resources for laboratory testing and prevention and control of COVID-19 in the context of global pandemic].

Objective: To rapidly evaluate the level of healthcare resource demand for laboratory testing and prevention and control of corona virus disease 2019 (COVID-19) in different epidemic situation, and prepare for the capacity planning, stockpile distribution, and funding raising for infectious disease epidemic response. Methods: An susceptible, exposed, infectious, removed infectious disease dynamics model with confirmed asymptomatic infection cases and symptomatic hospitalized patients was introduced to simulate different COVID-19 epidemic situation and predict the numbers of hospitalized or isolated patients, and based on the current COVID-19 prevention and control measures in China, the demands of resources for laboratory testing and prevention and control of COVID-19 were evaluated. Results: When community or local transmission or outbreaks occur and total population nucleic acid testing is implemented, the need for human resources is 3.3-89.1 times higher than the reserved, and the current resources of medical personal protective equipment and instruments can meet the need. The surge in asymptomatic infections can also increase the human resource demand for laboratory testing and pose challenge to the prevention and control of the disease. When vaccine protection coverage reach ≥50%, appropriate adjustment of the prevention and control measures can reduce the need for laboratory and human resources. Conclusions: There is a great need in our country to reserve the human resources for laboratory testing and disease prevention and control for the response of the possible epidemic of COVID-19. Challenges to human resources resulted from total population nucleic acid testing and its necessity need to be considered. Conducting non-pharmaceutical interventions and encouraging more people to be vaccinated can mitigate the shock on healthcare resource demand in COVID-19 prevention and control.

Tobacco use in Vietnam. Prevalence, predictors, and the role of the transnational tobacco corporations.

OBJECTIVE: To describe tobacco use in Vietnam and the impact of transnational tobacco corporations there. DESIGN: In cities, a multistage cluster design; in communes, a systematic sample design, using face-to-face interviews in all sites. SETTING: Hanoi, Ho Chi Minh City, and 2 rural communes in Vietnam. PARTICIPANTS: Random samples totaling 2004 men and women aged 18 years or older. MAIN OUTCOME MEASURES: Prevalence and correlates of tobacco smoking, amount and duration of smoking, age at initiation, quitting behavior, knowledge of health hazards of and attitudes toward smoking, and cigarette brand smoked, preferred, and recognized as most widely advertised. RESULTS: Smoking prevalence among men (n=970) was 72.8% and 4.3% among women (n=1031). Male smokers had smoked a mean of 15.5 years; the median age at initiation was 19.5 years. Among male smokers, 16% smoked non-Vietnamese cigarettes. More than twice as many (38%), however, said that they would prefer to smoke a non-Vietnamese brand if they could afford the cost. Among those who recalled any cigarette advertising (38%), 71% recalled a non-Vietnamese brand as the most commonly advertised. Male smokers who were significantly more likely to smoke non-Vietnamese brands lived in the south, were engaged in blue collar or business/service occupations, earned higher incomes, and lived in urban areas. CONCLUSIONS: Vietnam has the highest reported male smoking prevalence rate in the world. Unless forceful steps are taken to reduce smoking among men and prevent the uptake of smoking by youth and women, Vietnam will face a tremendous health and economic burden in the near future. Implementation of a comprehensive national tobacco control campaign together with international regulation will be the keys to the eradication of the tobacco epidemic in Vietnam and throughout the developing world.