1.Comparison between ARMA model and LSTM deep neural network in predictive effect on onset trend of pulmonary tuberculosis in Jiashi County of Xinjiang
Kerimu MUNIRE ; Yimamu MAIWULAJIANG ; Maimaiti MEIHERIBAN ; Liping ZHANG ; Yanling ZHENG
Chongqing Medicine 2024;53(22):3375-3379
Objective To use the auto-regressive moving average(ARMA)model and long short term memory(LSTM)depth neural network to predict the incidence trend of pulmonary tuberculosis in Jiashi County.Methods The legal infectious disease report data in this area from January 2014 to June 2023 were collected to construct the data set,in which the onset data of pulmonary tuberculosis from January 2014 to De-cember 2021 were used to the model construction and the data from January 2022 to June 2023 were used to the model verification.The Eviews7.2 and MATLAB2023a softwares were used to construct the ARMA mode and LSTM neural network.The monthly onset number of pulmonary tuberculosis from 2022 to 2023 was pre-dicted.Results The root-mean-square error(RMSE)of the optimal ARMA model and LSTM neural network verification from January 2014 to June 2023 was 26.494 and 12.713 respectively,suggesting that the fitting effect of LSTM neural network was better than that of ARMA model.The predictive results by adopting the LSTM neural network was basically consistent with the actual onset situation.Conclusion The LSTM neural network has good fitting and predicting effect for the onset trend in Jiashi County,which could provide the theoretical reference for predicting the onset number of pulmonary tuberculosis in the future in this area.
2.Epidemiological analysis of registered tuberculosis cases in Kashgar District, Xinjiang Uygur Autonomous Region from 2011 to 2020
Tusun DIERMULATI ; Xiaoyan HUANG ; Abulimiti MAIWEILANJIANG ; Yimamu MAIWULAJIANG ; Xiaowang PENG ; Abudureyimu TUERHONG ; Yinhao LU ; Yi HE
Shanghai Journal of Preventive Medicine 2022;34(11):1090-1095
ObjectiveTo determine the current status and characteristics of tuberculosis (TB) registration and treatment in Kashgar, and to provide scientific evidence for targeted prevention and control measures in future. MethodsKashgar registered TB cases information in 2011 to 2020 was exported from the National Tuberculosis Management Information System. Descriptive epidemiological analysis was conducted using Stata 12.0. ResultsFrom 2011 to 2020, number of Kashgar registered TB patients showed rising trend, followed by a falling one. Average proportion of annual decline in registered TB incidence was 40.48% from 2018 to 2020. From 2011 to 2016, number of registered TB patients in women was always higher than that in men, with a gender ratio (male : female) of about 0.90. In 2017, the gender ratio was 1.00. From 2018 to 2020, the gender ratios were 1.05, 1.20, and 1.12, respectively. Moreover, number of registered TB cases increased with age (χ2=547.79, P<0.001). Proportion of registered TB cases was relatively large in Shache County (16.43%‒23.64%), Yengisar County (9.51%‒13.87%) , Kashgar City (8.11%‒11.40%), Yecheng County (6.98%‒13.40%) and Bachu County(4.92%‒16.65%). Proportion of recurrent TB cases in Kashgar had increased to 27.29%, 20.77% and 28.39% in 2018, 2019 and 2020, respectively. Multivariate analysis showed that age, drug resistance, calendar year and etiological diagnosis were significantly correlated with the proportion of recurrent cases (all P<0.05). ConclusionSince 2018, TB incidence has decreased significantly due to the increasing efforts for identification and treatment of TB cases. However, Kashgar remains facing a high TB incidence. TB cases that are elderly, drug-resistant and positive for pathogen are susceptible to recurrent treatment. In future, targeted prevention and control measures should be improved for these groups.